diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..521784494aef90a6c65d93d8560bfde82a3b06d6 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text
+sf_log.txt filter=lfs diff=lfs merge=lfs -text
diff --git a/.summary/0/events.out.tfevents.1700364845.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1700364845.rhmmedcatt-proliant-ml350-gen10
new file mode 100644
index 0000000000000000000000000000000000000000..849cd4c7d2ef7cbaab60ad8ea45a0cc6dd2c8071
--- /dev/null
+++ b/.summary/0/events.out.tfevents.1700364845.rhmmedcatt-proliant-ml350-gen10
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2df6b5f974b4b478379efdd7c94b17e734e474dda873a49ce97a87c01e9ae24
+size 89592527
diff --git a/.summary/1/events.out.tfevents.1700364845.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1700364845.rhmmedcatt-proliant-ml350-gen10
new file mode 100644
index 0000000000000000000000000000000000000000..fbf424b404e63a16242b4530e1e7ebc1723e131f
--- /dev/null
+++ b/.summary/1/events.out.tfevents.1700364845.rhmmedcatt-proliant-ml350-gen10
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d111d8bbaf68873cb57f1cd57bda5ec46bca63ab8467c029c043bff5e09be130
+size 47062591
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..c671adce2299fcb641221076ad98bdf403c21fa3
--- /dev/null
+++ b/README.md
@@ -0,0 +1,189 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+model-index:
+- name: APPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: atari_qbert
+      type: atari_qbert
+    metrics:
+    - type: mean_reward
+      value: 45602.50 +/- 2068.10
+      name: mean_reward
+      verified: false
+---
+
+## About the Project
+
+This project is an attempt to maximise performance of high sample throughput APPO RL models in Atari environments in as carbon efficient a manner as possible using a single, not particularly high performance single machine. It is about demonstrating the generalisability of on-policy algorithms to create good performance quickly (by sacrificing sample efficiency) while also proving that this route to RL production is accessible to even hobbyists like me (I am a gastroenterologist not a computer scientist). 
+
+In terms of throughput I am managing to reach throughputs of 2,500 - 3,000 across both policies using sample factory using two Quadro P2200's (not particularly powerful GPUs) each loaded up about 60% (3GB). Previously using the stable baselines 3 (sb3) implementation of PPO it would take about a week to train an atari agent to 100 million timesteps synchronously. By comparison the sample factory async implementation takes only just over 2 hours to achieve the same result. That is about 84 times faster with only typically a 21 watt burn per GPU. I am thus very grateful to Alex Petrenko and all the sample factory team for their work on this.
+
+## Project Aims
+
+This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it anywhere near sota performance. 
+
+I then re-trained the models with 100 million timesteps- at this point 2 environments maxed out at sota performance (Pong and Freeway) with four approaching sota performance - (atlantis, boxing, tennis and fishingderby.) =6/57 near sota. 
+
+The aim now is to try and reach state-of-the-art (SOTA) performance on a further block of atari environments using up to 1 billion training timesteps initially with appo. I will flag the models with SOTA when they reach at or near these levels. 
+
+After this I will switch on V-Trace to see if the Impala variations perform any better with the same seed (I have seeded '1234')
+
+
+## About the Model
+
+The hyperparameters used in the model are described in my shell script on my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his parameters, I saved time and energy by using many of his tuned hyperparameters to reduce carbon inefficiency:
+```
+hyperparameters =  {
+  "help": false,
+  "algo": "APPO",
+  "env": "atari_asteroid",
+  "experiment": "atari_asteroid_APPO",
+  "train_dir": "./train_atari",
+  "restart_behavior": "restart",
+  "device": "gpu",
+  "seed": 1234,
+  "num_policies": 2,
+  "async_rl": true,
+  "serial_mode": false,
+  "batched_sampling": true,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 1,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 16,
+  "num_envs_per_worker": 2,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 4,
+  "rollout": 128,
+  "recurrence": 1,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1.0,
+  "reward_clip": 1000.0,
+  "value_bootstrap": false,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.0004677351413,
+  "value_loss_coeff": 0.5,
+  "kl_loss_coeff": 0.0,
+  "exploration_loss": "entropy",
+  "gae_lambda": 0.95,
+  "ppo_clip_ratio": 0.1,
+  "ppo_clip_value": 1.0,
+  "with_vtrace": false,
+  "vtrace_rho": 1.0,
+  "vtrace_c": 1.0,
+  "optimizer": "adam",
+  "adam_eps": 1e-05,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 0.0,
+  "learning_rate": 0.0003033891184,
+  "lr_schedule": "linear_decay",
+  "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
+  "obs_subtract_mean": 0.0,
+  "obs_scale": 255.0,
+  "normalize_input": true,
+  "normalize_input_keys": [
+    "obs"
+  ],
+  "decorrelate_experience_max_seconds": 0,
+  "decorrelate_envs_on_one_worker": true,
+  "actor_worker_gpus": [],
+  "set_workers_cpu_affinity": true,
+  "force_envs_single_thread": false,
+  "default_niceness": 0,
+  "log_to_file": true,
+  "experiment_summaries_interval": 3,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": true,
+  "heartbeat_interval": 10,
+  "heartbeat_reporting_interval": 60,
+  "train_for_env_steps": 100000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 120,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": 1200,
+  "save_best_every_sec": 5,
+  "save_best_metric": "reward",
+  "save_best_after": 100000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    512,
+    512
+  ],
+  "encoder_conv_architecture": "convnet_atari",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": false,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "relu",
+  "policy_initialization": "orthogonal",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": false,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": false,
+  "env_gpu_actions": false,
+  "env_gpu_observations": true,
+  "env_frameskip": 4,
+  "env_framestack": 4,
+  "pixel_format": "CHW"
+}
+
+  ```
+
+
+    
+A(n) **APPO** model trained on the **atari_qbert** environment.
+
+This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Sample factory is a 
+high throughput on-policy RL framework. I have been using 
+Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+
+
+## Downloading the model
+
+After installing Sample-Factory, download the model with:
+```
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_qbert
+```
+
+    
+## Using the model
+
+To run the model after download, use the `enjoy` script corresponding to this environment:
+```
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_qbert --train_dir=./train_dir --experiment=APPO-atari_qbert
+```
+
+
+You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
+See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
+    
+## Training with this model
+
+To continue training with this model, use the `train` script corresponding to this environment:
+```
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_qbert --train_dir=./train_dir --experiment=APPO-atari_qbert --restart_behavior=resume --train_for_env_steps=10000000000
+```
+
+Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
+    
\ No newline at end of file
diff --git a/checkpoint_p0/best_001911416_489324544_reward_216.830.pth b/checkpoint_p0/best_001911416_489324544_reward_216.830.pth
new file mode 100644
index 0000000000000000000000000000000000000000..856f4050a88495c82a27467983560ff959e25fe1
--- /dev/null
+++ b/checkpoint_p0/best_001911416_489324544_reward_216.830.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5aec131ae9aaf68fc810a4ed74da365fb81720e873ce44497795a3ea34c48d3
+size 20721843
diff --git a/checkpoint_p0/checkpoint_001961560_504324096.pth b/checkpoint_p0/checkpoint_001961560_504324096.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8d1156ae8ca92173b762274bb7384e66516b807d
--- /dev/null
+++ b/checkpoint_p0/checkpoint_001961560_504324096.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df17ec575a0e265341485ef1bc0a835f49f822dea6fc1896188b0d8514ba240
+size 20722179
diff --git a/checkpoint_p0/checkpoint_001961752_504422400.pth b/checkpoint_p0/checkpoint_001961752_504422400.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ced5ac1674816cdf4aa6b8efdc5bf6cb7a88d2c3
--- /dev/null
+++ b/checkpoint_p0/checkpoint_001961752_504422400.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab53dd824b95c3d2c96baae921235bfeedb429e21ef9459b8e0aa4e1c2005e7
+size 20722179
diff --git a/checkpoint_p0/milestones/checkpoint_000012576_3219456.pth b/checkpoint_p0/milestones/checkpoint_000012576_3219456.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3168e29d383de50535b37f11b81cc70b5a20582a
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000012576_3219456.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef9a921a37c4e3134d3b0b962b065ffbffee909d6247facc8b5a152f8e62851
+size 20723035
diff --git a/checkpoint_p0/milestones/checkpoint_000025440_6512640.pth b/checkpoint_p0/milestones/checkpoint_000025440_6512640.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5458e07bfd2c144f7bde0821a719c682415b876f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000025440_6512640.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc89f2fa2b37a4ca99ec69d6c871b1e48f50e1b5311c99e8465cf7647f1bc08
+size 20723035
diff --git a/checkpoint_p0/milestones/checkpoint_000038464_9846784.pth b/checkpoint_p0/milestones/checkpoint_000038464_9846784.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e81a64dbb90bcb2251ab7b3a8f2be1ad0b89625e
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000038464_9846784.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6100cacac77d348bc7992dc0419b377cac68f99a3b855359aee8680635065af6
+size 20723035
diff --git a/checkpoint_p0/milestones/checkpoint_000051456_13172736.pth b/checkpoint_p0/milestones/checkpoint_000051456_13172736.pth
new file mode 100644
index 0000000000000000000000000000000000000000..553b30261b75e30cf049062c53dfd6e90bbb625d
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000051456_13172736.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59057c5e0c7e476155b3481e59a63eecd6604abad590cc97fffbeaaae8896ec7
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000064416_16490496.pth b/checkpoint_p0/milestones/checkpoint_000064416_16490496.pth
new file mode 100644
index 0000000000000000000000000000000000000000..64cd1bee6c1ba88ee0cef657d9026af38707be48
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000064416_16490496.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fcff4250a73eef24cd2e0ef4a771ce5202b265c2a1a1633ff5b04c3d111b911
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000077408_19816448.pth b/checkpoint_p0/milestones/checkpoint_000077408_19816448.pth
new file mode 100644
index 0000000000000000000000000000000000000000..458e73bf3f4da3c7542bf84a99bb7ceaa5502f6f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000077408_19816448.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75236bd736c3f67789f06f177f1e9d70078b0beb29efce8b5184f897fc887332
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000090368_23134208.pth b/checkpoint_p0/milestones/checkpoint_000090368_23134208.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4e91ea61d92a4e13c985a5b88c4cc81b8d2c7ef3
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000090368_23134208.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6bcfc22e3e7bdf5fb1a1fe8b576f2e40c2fde5b9d21022b3a9fa8ea5a7c881
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000103296_26443776.pth b/checkpoint_p0/milestones/checkpoint_000103296_26443776.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cb15708253ba2e460bb591afad30213d4c138c41
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000103296_26443776.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3264b4453671233dedab9fc48394f815629cf69743593731cb7b6b9a6ed17c6
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000116256_29761536.pth b/checkpoint_p0/milestones/checkpoint_000116256_29761536.pth
new file mode 100644
index 0000000000000000000000000000000000000000..db4bbd731c5db8dd0c2d406130fd5bc41417a0b3
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000116256_29761536.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b76614b369e1888255644c42422dfbe99bcca848ed8489237aed35f61b0f386
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000129248_33087488.pth b/checkpoint_p0/milestones/checkpoint_000129248_33087488.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b22ec3e23a442382f65ad38258c994f1b38b33ef
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000129248_33087488.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f6b2e15d82d4aa0210b0fed6b54a5efe7b60d6f9846eacac9e40c2596fb3ba
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000142208_36405248.pth b/checkpoint_p0/milestones/checkpoint_000142208_36405248.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4ebb5e68f5e8309b1453606deebc4172f471d6dc
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000142208_36405248.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6dc3f2405505a3b817372315f89beacc3e199c9872c089f05643f62e5875add
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000155200_39731200.pth b/checkpoint_p0/milestones/checkpoint_000155200_39731200.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c39b39e62a4dc308167d941dccb6bb0be4af03b0
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000155200_39731200.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9aaaeeca9b024f271270473ab5b48aac72a5f7e0e5b19a289f089ea4aff292
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000168160_43048960.pth b/checkpoint_p0/milestones/checkpoint_000168160_43048960.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b475b318a0fa55b2e86e9885fcc2daa8c94adb7a
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000168160_43048960.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83b96ba715d52f7842be695026b05e69a68ef241b16882d0a029c935f9ba8b2
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000181120_46366720.pth b/checkpoint_p0/milestones/checkpoint_000181120_46366720.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9db89a397396c347eba9b8e862020a99724541b3
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000181120_46366720.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a160a593b7e2c2c3bf1385ef5cbe4d80abb270156e51931c4e7400f78cd6e9b3
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000194080_49684480.pth b/checkpoint_p0/milestones/checkpoint_000194080_49684480.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d044c68fee2c47075bea759f574535264197fc32
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000194080_49684480.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5024b8b88c9009346836bb93626daee8f0d60cc17be9c5545f34e582106c861
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000207040_53002240.pth b/checkpoint_p0/milestones/checkpoint_000207040_53002240.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3e052e88bf6fe9091f507915a3fa890b756a4c9d
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000207040_53002240.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140d4dde7032fa189d7df8e356cd37dcdf1817a12c64347e958f0a7c2ecf8f7b
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000219968_56311808.pth b/checkpoint_p0/milestones/checkpoint_000219968_56311808.pth
new file mode 100644
index 0000000000000000000000000000000000000000..11aaa4e59ccb609fe8f5a29863cde7b2025f0876
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000219968_56311808.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b702e17c20965b010e4660a55dd662cd50d76f6e972dce96c7e9ed87aa2d02
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000232960_59637760.pth b/checkpoint_p0/milestones/checkpoint_000232960_59637760.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d685c43a5cc975a029ae71ef8755a49c79c21945
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000232960_59637760.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24bbc9807ae5f57e1fe9a16d6348fc4e9bf865ef4643a8926cb98fa489ea82ce
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000245952_62963712.pth b/checkpoint_p0/milestones/checkpoint_000245952_62963712.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8ca6cdd4aef5702215f16bfe4d0fc42074050d26
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000245952_62963712.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e90ccbd3a82ef12c87d9700aeb9e229ee52d6feb2e33e9426fea823103b525
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000258912_66281472.pth b/checkpoint_p0/milestones/checkpoint_000258912_66281472.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d632c562412610d98056d11c6af6f7cfd20360ce
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000258912_66281472.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cf6ca24acba6321a0e62162ed2d1e3b1ef534e3dd6bd8743ee1099f14a414f
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000271904_69607424.pth b/checkpoint_p0/milestones/checkpoint_000271904_69607424.pth
new file mode 100644
index 0000000000000000000000000000000000000000..763ed2210a675e80756d6d6c17de3a61a5456fa4
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000271904_69607424.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d79d3c029dc197f5f5b37eb565e917cf8940e0de647ba4a07effac720fc524d
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000284864_72925184.pth b/checkpoint_p0/milestones/checkpoint_000284864_72925184.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dadf698b20d0c83e4adeed31e2ded831a10de810
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000284864_72925184.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5216a5bf8e9a7b0c1f032ad4f1fad49f41bab98781e8975ac3bd4d37e91e3c
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000297824_76242944.pth b/checkpoint_p0/milestones/checkpoint_000297824_76242944.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b8122568126cb7d9d2bd6312b6cc745aa6ba3fdb
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000297824_76242944.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855e46d015eb2830655787fc7f4c889cb56fca06f11647ab027fe5806df0f429
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000310848_79577088.pth b/checkpoint_p0/milestones/checkpoint_000310848_79577088.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a00797694e357ea12e4e162a8adc2427c9870a4f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000310848_79577088.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d0bb3afb08ddd97ebad2bf041139a679c7e42b6e38ad858631a37fe44d2c826
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000323776_82886656.pth b/checkpoint_p0/milestones/checkpoint_000323776_82886656.pth
new file mode 100644
index 0000000000000000000000000000000000000000..11871483c1982c6a382b2736d4d620bcea6f894c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000323776_82886656.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:107ace74ee0165cbb5e66c686ac99ebc797f2119cafd9edd6bf995aeb2e3497c
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000336672_86188032.pth b/checkpoint_p0/milestones/checkpoint_000336672_86188032.pth
new file mode 100644
index 0000000000000000000000000000000000000000..46bd57e069fb7aa3867d908044c51359fd6d55ab
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000336672_86188032.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87dfa5cf43505790e960101ca5ec0f50ad381a5d8ad79b55e8306ec35a29da1f
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000349696_89522176.pth b/checkpoint_p0/milestones/checkpoint_000349696_89522176.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a2dedbc9489068ebd6a71f2450608eeec59b9bd3
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000349696_89522176.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be13370090e4f582b200f8ec4c4532e6de55dbd359517dea8c9a23ea3bffa7de
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000362752_92864512.pth b/checkpoint_p0/milestones/checkpoint_000362752_92864512.pth
new file mode 100644
index 0000000000000000000000000000000000000000..87fa360144cbbf214d75a8612e2db75ec4e0c7f6
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000362752_92864512.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7841197c8c0be19fe4a6b6bce98cc39f95b22599dd1a7a86f994fe404694d4b
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000375712_96182272.pth b/checkpoint_p0/milestones/checkpoint_000375712_96182272.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4b009fd1de7ae470506b3aa0e761e35a79583b89
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000375712_96182272.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f7b6e7fbf6f9dc06d86fc798707bb3c287827979ff6bd0d5728d6297e5e2bf
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000388736_99516416.pth b/checkpoint_p0/milestones/checkpoint_000388736_99516416.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b71a9a5946a1d64a10518655f0371d243e6bf539
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000388736_99516416.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44131a26c9bbbda1240154162ebf2968b8a27e93e9870c553310f47cd7cf6b2
+size 20723091
diff --git a/checkpoint_p0/milestones/checkpoint_000401728_102842368.pth b/checkpoint_p0/milestones/checkpoint_000401728_102842368.pth
new file mode 100644
index 0000000000000000000000000000000000000000..598b4e982a1b295d7e410341e1c5f315571636ff
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000401728_102842368.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59d7141b193bc7f71bc3084d5fe159dbb90f2255f8ad20803d409d6273aedac
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000414752_106176512.pth b/checkpoint_p0/milestones/checkpoint_000414752_106176512.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6ec4236cfec4ec79ad797f1c75c5d189771e0ba8
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000414752_106176512.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c88ee4e3408229ba4a4a7602882f2859d5d3c4fac2aff1f758abdc9e5ea378d
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000427808_109518848.pth b/checkpoint_p0/milestones/checkpoint_000427808_109518848.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c4aa34eaf5ebe2ec808e40da256c07aa18d53671
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000427808_109518848.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3809a26225729572d246f8d1ddea8409f6b8a8534214f3c07256052335894b50
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000440768_112836608.pth b/checkpoint_p0/milestones/checkpoint_000440768_112836608.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1ca016fdfd6e3f439488c3c562d500761133e51f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000440768_112836608.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dfb88def96f931a4b72ecc21fc8b4d938cb138246fe635474f2db211f677fcb
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000453728_116154368.pth b/checkpoint_p0/milestones/checkpoint_000453728_116154368.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cb138f21306d7b55efde3c97f5a9169564ffe98b
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000453728_116154368.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:981823c5e0a73cbc66e335ab10b3531de38e827350fde5d5662cea09cd86baf2
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000466688_119472128.pth b/checkpoint_p0/milestones/checkpoint_000466688_119472128.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cf25452dc48cc2a2e951cb1722fceea23f53cbb0
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000466688_119472128.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772937695ab663a1b8e097445edcedea91be274fd04eeed3b6dcc598ebd7ccbf
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000479680_122798080.pth b/checkpoint_p0/milestones/checkpoint_000479680_122798080.pth
new file mode 100644
index 0000000000000000000000000000000000000000..487d1e25330153def1a9b2b19103101611716109
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000479680_122798080.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f615091486fed779829e3f7958b2abf790872bac25a3517d5c6e964534c10eb
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000492640_126115840.pth b/checkpoint_p0/milestones/checkpoint_000492640_126115840.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0f7fb3acc8fe20d264015b60bb73506f504b0302
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000492640_126115840.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14eb46c34e1b49b3d8525a2729496cb19a92ab6f6f27090902b609a35e3b3c53
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000505568_129425408.pth b/checkpoint_p0/milestones/checkpoint_000505568_129425408.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ef8c93ecb74c326c4864d2048e2e5121d6c5efe1
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000505568_129425408.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252539a1e9dbef6bd2b0ab08f1f8a0a11a2874705b25ad07d0d83821ea88b323
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000518560_132751360.pth b/checkpoint_p0/milestones/checkpoint_000518560_132751360.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d20415afa87c52ee4c76fd3f6fecb5d9f2325fe8
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000518560_132751360.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d5800c36a6eff7e2027da9dd8a9d1011b530b3b14b24b35a1aa8220599adad
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000531552_136077312.pth b/checkpoint_p0/milestones/checkpoint_000531552_136077312.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ca64b813829f4b08fecad874d4aa8a24a56365c1
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000531552_136077312.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2c0f34c7d9017750afb2379f70eeaf04c775a4fde3ebed4beeeb1e33cc685a
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000544544_139403264.pth b/checkpoint_p0/milestones/checkpoint_000544544_139403264.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9ec0207cd1d80ae120a9ab18ae0c5a1367ea9b68
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000544544_139403264.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8326a6a1423c11272aca10e59dcaa071c25ba26750aa959ccedcb2f19c63181e
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000557440_142704640.pth b/checkpoint_p0/milestones/checkpoint_000557440_142704640.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0f46b9b30544fd4426f8204b9ed1f6c7c4a2de3e
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000557440_142704640.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a874efee483b6f722635c6d35807a9c603c35daf7f5cb2e6bea095bbe60b162
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000570464_146038784.pth b/checkpoint_p0/milestones/checkpoint_000570464_146038784.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1d4995d4281370e3eaedd9ffe2a2d1ae3df0eec8
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000570464_146038784.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eab8b23e82b602d1206e1f922daee301ab3ef83a03fd47a3c9212ef663f25cc
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000583456_149364736.pth b/checkpoint_p0/milestones/checkpoint_000583456_149364736.pth
new file mode 100644
index 0000000000000000000000000000000000000000..58850afcd2009abd22658fb438ebf3a5331920b0
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000583456_149364736.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045cb6c3360e5871b05c654654d3227c34b537a2ba0960d14d5cfa74ae533492
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000596352_152666112.pth b/checkpoint_p0/milestones/checkpoint_000596352_152666112.pth
new file mode 100644
index 0000000000000000000000000000000000000000..054014b5f5efa1fc82fc10a6d42211daccf50e2d
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000596352_152666112.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc48c0d75241635522e01657f145e0891078ccd6464f4082c72bff98cac9133
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000609312_155983872.pth b/checkpoint_p0/milestones/checkpoint_000609312_155983872.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4aff52798128ad775bbfa1e7aeda06b78aa8bbb0
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000609312_155983872.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d6b6a8131c1d75853389ade5fd89ddc16396ab3d545a318d14f0da47447468
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000622304_159309824.pth b/checkpoint_p0/milestones/checkpoint_000622304_159309824.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f4bcf9e1037934b28c2603864f695092ac088c6d
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000622304_159309824.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce011e5b26983f20ca8b587f4db1b6dfe2e0b7d26e92a39e70456505e191c335
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000635328_162643968.pth b/checkpoint_p0/milestones/checkpoint_000635328_162643968.pth
new file mode 100644
index 0000000000000000000000000000000000000000..879b72bdfb92fe14779de1f92b3a557df3d33e7b
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000635328_162643968.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549cc78f984378e73faeeb353cb4bb69caf1ad8c33c7de9023c6687ef95f5770
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000648256_165953536.pth b/checkpoint_p0/milestones/checkpoint_000648256_165953536.pth
new file mode 100644
index 0000000000000000000000000000000000000000..022bd5ddb987c01a8cfee32d08dc5863895caa4f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000648256_165953536.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33aeb589006554763c79a2a8d79f53d4faa8be3c9e27a49b01f2927f449cc550
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000661216_169271296.pth b/checkpoint_p0/milestones/checkpoint_000661216_169271296.pth
new file mode 100644
index 0000000000000000000000000000000000000000..211f0a40ad47459685fd46dad0af3abb0faabb07
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000661216_169271296.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ff0d4370d2bcca0a8ad074bc98949d3ad4bfbd60ac80e7fc51f0dbde691ebe
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000674144_172580864.pth b/checkpoint_p0/milestones/checkpoint_000674144_172580864.pth
new file mode 100644
index 0000000000000000000000000000000000000000..87dbe2795c97249edc23d9d9da2fd75c528228ed
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000674144_172580864.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b6b4f92560f15a3c02a8d58333ef97e40ab326b6fc16bed4068b5cd2d56107
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000687168_175915008.pth b/checkpoint_p0/milestones/checkpoint_000687168_175915008.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8f7968056cf171d69058024977c7d9dcec05ecad
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000687168_175915008.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d747584320ecd10f7a17a587728d430556ecb96fc7c4c78049fbdff85163f40
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000700088_179224576.pth b/checkpoint_p0/milestones/checkpoint_000700088_179224576.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9db9930fbea86db7179dcbc6a07ce64470d42780
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000700088_179224576.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcda9ffe08f7a5dedf47ce48ab0fb5b8749b9e41a865b917a6f5b0e0f8f3d95
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000713112_182558720.pth b/checkpoint_p0/milestones/checkpoint_000713112_182558720.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5faf467fa1a5a21508a5433dc9fb89672d06da46
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000713112_182558720.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a04fb9aef0a5061e856df9953fbcd6e1ca59ebf86f9b5be8d2941b4574e4df9
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000726072_185876480.pth b/checkpoint_p0/milestones/checkpoint_000726072_185876480.pth
new file mode 100644
index 0000000000000000000000000000000000000000..95daab854f9b0297f2490df72ff79f589cab9bd6
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000726072_185876480.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa9217b2fcaf57a8f819444b33c91f00523b35ad721ada8b143c743c1147aa6
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000739032_189194240.pth b/checkpoint_p0/milestones/checkpoint_000739032_189194240.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d3381de9b3b792cff4307d452a78664f991d4b65
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000739032_189194240.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb9fd6e0201a95d95a16e6678cae2427b285e17ec73f19ba5253cec2bba6e4e
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000752024_192520192.pth b/checkpoint_p0/milestones/checkpoint_000752024_192520192.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2ad383e150ca5cd947d82d44177b725749201cad
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000752024_192520192.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848b32d1cc5529147d844b0bb202b53420024706853d9198ae19cd0889093903
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000765016_195846144.pth b/checkpoint_p0/milestones/checkpoint_000765016_195846144.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e3841cd2d3f0845deb5655ce0f0ebf9bbc01c2a1
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000765016_195846144.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477dc0414dd97a09ee9f85d98721d101c2bb9ea851c22b6038b005645a8ec7e2
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000777976_199163904.pth b/checkpoint_p0/milestones/checkpoint_000777976_199163904.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d84056d51f082e2427219e96864b4181c3fe9b36
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000777976_199163904.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074c6aabab9bd90a7c1ff519447753447b66cfaf27964d4b93fb10545a910a8e
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000791000_202498048.pth b/checkpoint_p0/milestones/checkpoint_000791000_202498048.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fd81f52fa57ad443cee9b4c07754633a5884e41d
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000791000_202498048.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145f4d4e1a72298252a88ac615fadc209576eee345c3a77baafd18250b845a30
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000803544_205709312.pth b/checkpoint_p0/milestones/checkpoint_000803544_205709312.pth
new file mode 100644
index 0000000000000000000000000000000000000000..350a18290e0f621b00339934f639d2cff233768a
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000803544_205709312.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17681c3dc753e9f149a10aab2024d9d8b5df31c7104942c6c822fe4058c0ce73
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000816536_209035264.pth b/checkpoint_p0/milestones/checkpoint_000816536_209035264.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4580b335909927efdd05ffa85ff66a89a8235563
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000816536_209035264.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0334c21db034852d307b7aaae607c50b141f9da9e7f436e8e1ce1fe04b1580
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000829464_212344832.pth b/checkpoint_p0/milestones/checkpoint_000829464_212344832.pth
new file mode 100644
index 0000000000000000000000000000000000000000..16ebd64f5827ab5487fff45d1367f206e3c24531
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000829464_212344832.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93b164aa0eb411280c987d6dbfba4d16996837d87119a708e2ed03e60314ec6
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000842392_215654400.pth b/checkpoint_p0/milestones/checkpoint_000842392_215654400.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ba04ab923ca6295a45fc8b9dcc39c95a8b6e342c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000842392_215654400.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1860cbc9792d177fa68f2e1ee3dfe3302b0597a03b7e296c7a368cb2d053c8a2
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000855320_218963968.pth b/checkpoint_p0/milestones/checkpoint_000855320_218963968.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b33a8fbe6548bf2267aae2628e10c60e9ad0da8e
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000855320_218963968.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d560cd17efec6a3e7226f5c481288e60115cc6022970d1ada6832e89322199e4
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000868312_222289920.pth b/checkpoint_p0/milestones/checkpoint_000868312_222289920.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ee36e8166928f6f4444d83418295421a00b63a98
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000868312_222289920.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1be8672ef49ee0b2c1541b58b22c5399779375883fe464bf41a68aa9269ce6
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000881272_225607680.pth b/checkpoint_p0/milestones/checkpoint_000881272_225607680.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8f9e45414f5dfcdbb94e06c735cb50a5254545d6
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000881272_225607680.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d20f36b2e85f5978dd811269675f19e3f9201ea43cc35a087ef8e5116bbb0cb
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000894232_228925440.pth b/checkpoint_p0/milestones/checkpoint_000894232_228925440.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a60fda90fe6eaa52a159b2e207896fa92ebbc303
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000894232_228925440.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eaadc63b921b1ad7b255a49ca6e9b930f2d38e2361e37865c0abd2d8b5029f7
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000907256_232259584.pth b/checkpoint_p0/milestones/checkpoint_000907256_232259584.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0c009b8ea6313e4bcc0366366717110969d2d77c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000907256_232259584.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776ea17d9005b2e56ae61cbd571fb383e14f335812e7c168382c6dac9144f6b8
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000920280_235593728.pth b/checkpoint_p0/milestones/checkpoint_000920280_235593728.pth
new file mode 100644
index 0000000000000000000000000000000000000000..22e599c5190334e9e2a39b32924489edfe1e6bdf
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000920280_235593728.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2c151a15a3b716ef23bf3f79b1154539f0522a528f9d5ec99d9bf4f6c56194
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000933304_238927872.pth b/checkpoint_p0/milestones/checkpoint_000933304_238927872.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8f75bac71f624a97da27a920ba80a61ca1eacfeb
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000933304_238927872.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4bdae6fe4c04caabb24f570f03d71996fdf3b66a5f3d355726e13c977c98c4
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000946296_242253824.pth b/checkpoint_p0/milestones/checkpoint_000946296_242253824.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6778b0be3419ad808ebcc0b6c1354edb45e8c6c2
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000946296_242253824.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b558d0204c014dccaafef0daedede4ad8bdd69ad56eb3fba3fbee09ec809914
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000959288_245579776.pth b/checkpoint_p0/milestones/checkpoint_000959288_245579776.pth
new file mode 100644
index 0000000000000000000000000000000000000000..de6ed8fbe561e847a4e67d2885f977a3f98e4932
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000959288_245579776.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3695f0b646d49918325dff5ea5fc3aac18e1e31f97c195a98eb32844b607a2
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000972312_248913920.pth b/checkpoint_p0/milestones/checkpoint_000972312_248913920.pth
new file mode 100644
index 0000000000000000000000000000000000000000..aee0a50875a730ff919394525488cc6c27d32b94
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000972312_248913920.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3852a90c4c59131f2125490c2e96b2100a13f14122ab67f13f081bb5ad7f7
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000985304_252239872.pth b/checkpoint_p0/milestones/checkpoint_000985304_252239872.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a4a20d9c67d7026cdc98cfefe7620723da18b880
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000985304_252239872.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd442a0b3cc5ee48087af54dfca8f13ebf43b0d695a7054cc948d6b1851aa694
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_000998232_255549440.pth b/checkpoint_p0/milestones/checkpoint_000998232_255549440.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7b63e15495c0715474ac5491d356a652b4fdd440
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000998232_255549440.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a95117cc681e4493f873bbb7387f45d15afe5c482d600dedd6ea640d855c5302
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001011224_258875392.pth b/checkpoint_p0/milestones/checkpoint_001011224_258875392.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2f8149cdb72d6ecb33743ad49d81ccf098084c4f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001011224_258875392.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b509de81d14c71f1a973992c9444b64f286fb8577c58371d08987303308965f
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001024216_262201344.pth b/checkpoint_p0/milestones/checkpoint_001024216_262201344.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ef42d9d941e7a3057277af7b2546712f81aa816b
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001024216_262201344.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ea4112d0ad9edc1f56c8c3beac96910736751b2767c27f7b71c5db7398bc65
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001037176_265519104.pth b/checkpoint_p0/milestones/checkpoint_001037176_265519104.pth
new file mode 100644
index 0000000000000000000000000000000000000000..285b4669f9bb223985ccb707017471300a02cb3c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001037176_265519104.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ac411ed6c8368f4e531593652398c1aae1a7ef2a2de396c2bdb66682c14d13
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001050104_268828672.pth b/checkpoint_p0/milestones/checkpoint_001050104_268828672.pth
new file mode 100644
index 0000000000000000000000000000000000000000..aa54c033d5250dddb5347186aa779bfc955aabc1
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001050104_268828672.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:770eb712ac3fcfa97c4f758e57b42977acfeffb076aa206ce09ccaf8757bd5a5
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001063064_272146432.pth b/checkpoint_p0/milestones/checkpoint_001063064_272146432.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c45415ad07c0239863e701ac820631ff78cd4a48
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001063064_272146432.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7f080cfa4834faaf57d042834b2087d669962d621a3b8b1ad123fea63347af
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001075960_275447808.pth b/checkpoint_p0/milestones/checkpoint_001075960_275447808.pth
new file mode 100644
index 0000000000000000000000000000000000000000..81f55714d55a92cf7e082cb5b8d00d946eb4629a
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001075960_275447808.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed142c3a21d4aadc0fb70015b3a2137e82cf80c7f12f47ad172bb8705543f91a
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001088920_278765568.pth b/checkpoint_p0/milestones/checkpoint_001088920_278765568.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d7be060f53538dd056e55ca2d93e4f5911bafc3c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001088920_278765568.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442d729362cab11e746e40e4f79b8d784d9dc7231ee70f018437e5ebbe25e281
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001101912_282091520.pth b/checkpoint_p0/milestones/checkpoint_001101912_282091520.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6470c8aed8c3c05970d159b7f0ba760aad13878c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001101912_282091520.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72c9e7ab36414c94654ddbdb42ea1e5eaaae1abb1d1a983b7cda344246c4594
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001114904_285417472.pth b/checkpoint_p0/milestones/checkpoint_001114904_285417472.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fd3d6902dcc586e1263aef60f27352d8035c89b9
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001114904_285417472.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6d1ed347f74d04501986cad093a6a629250309374754c94479356f75e389c0
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001127800_288718848.pth b/checkpoint_p0/milestones/checkpoint_001127800_288718848.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b6753ca1730347a1c6656f05b19fd719abbaf66d
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001127800_288718848.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001cd34ca7964a26c9b9ffd33d9446c8da26c01a69c3fc118ecc801c818b3473
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001140760_292036608.pth b/checkpoint_p0/milestones/checkpoint_001140760_292036608.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4d9465db657683d716fc9367e8456193611e9741
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001140760_292036608.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb243d87a42fb3e06151851324c16f8633eb51f5466ac4ef7a0edbfe1334c57
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001153752_295362560.pth b/checkpoint_p0/milestones/checkpoint_001153752_295362560.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1bb19e3802bbcacbeb5d8c293295eac77a43a927
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001153752_295362560.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a8888be00b3b1d8bd59f5d803399919113c94ea97deba44ee8196f10092a54
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001166744_298688512.pth b/checkpoint_p0/milestones/checkpoint_001166744_298688512.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e5ec77311a358c80e5f69cd336cdc9f45831f480
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001166744_298688512.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6289d8cffb502a5993080163733646b4f1a70f7949dfd2fe50b61d879599305d
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001179768_302022656.pth b/checkpoint_p0/milestones/checkpoint_001179768_302022656.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5f8457c07454b5f4eeb7694f710997b474542fb0
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001179768_302022656.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e987c67d674c4eb671a3ec19c37292223786c5995d0dececfef83a991b130433
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001192696_305332224.pth b/checkpoint_p0/milestones/checkpoint_001192696_305332224.pth
new file mode 100644
index 0000000000000000000000000000000000000000..45e0269764f9145865a119b18f7635a4267c1dfe
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001192696_305332224.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba7df646ae4c6c855a0b2c76885f772213c65df8f51cf1f18b52d2a89b059c8
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001205624_308641792.pth b/checkpoint_p0/milestones/checkpoint_001205624_308641792.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6e33fc74413a65a01ca0faab7dbec3e5beadae63
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001205624_308641792.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd94183256d331106e9c8485c33fc663ed739e68a1ee94b8b4cfe480dd53a2c7
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001218424_311918592.pth b/checkpoint_p0/milestones/checkpoint_001218424_311918592.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b22e0cf2191de15f1e8203465e51374b46109b6d
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001218424_311918592.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3800596bc9f36cfae5836f3ad1ad24a9598c72be9120ab01335856dbbe9144ba
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001231128_315170816.pth b/checkpoint_p0/milestones/checkpoint_001231128_315170816.pth
new file mode 100644
index 0000000000000000000000000000000000000000..29f65861d0479b9bb9e6d8856ce3dcf1e060d8d7
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001231128_315170816.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72f5827b742d03b21f6531e4999356c41d2e73d1a114ed58272e52e24083fde
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001243960_318455808.pth b/checkpoint_p0/milestones/checkpoint_001243960_318455808.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cc0f90b5422880233c36cf4f77cd95ab8876682c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001243960_318455808.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9971faecb957c35011df256a3c3e81dc2739cc9fbe622442fb1ad933c4b26497
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001256824_321748992.pth b/checkpoint_p0/milestones/checkpoint_001256824_321748992.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d950ede9dcdbeff32933772c9abf9f8eb8cb8047
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001256824_321748992.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77797df216b4dda5f1419d659475ef6cac8cf5c63f788a10256da0cc6d43e713
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001269720_325050368.pth b/checkpoint_p0/milestones/checkpoint_001269720_325050368.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6a313701545732231cdeb292ace404a6d16c2d53
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001269720_325050368.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91433c117a0d7a22ea3cba64a32382d1105004aa8f5363a79ee2e8cc94f19719
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001282680_328368128.pth b/checkpoint_p0/milestones/checkpoint_001282680_328368128.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fc82651d394e4037ded21be3a0ec7f82dc104d88
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001282680_328368128.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6475f772a0715a1d012eb4232e5e6764fe90b47d2d68d6874a57309b8e5e88
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001295512_331653120.pth b/checkpoint_p0/milestones/checkpoint_001295512_331653120.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e7c6ef923051690845d69efd1f116d3d1efe8d7b
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001295512_331653120.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc0f77be1e1166f380d80bb55d809d6cb49bd1f01f2fa82c890c026a93bf899
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001308408_334954496.pth b/checkpoint_p0/milestones/checkpoint_001308408_334954496.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ec2e0b0be8684a6ad68b89e385b561bddccc0676
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001308408_334954496.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269c45de264dd1dbc7fdf06214c1fe54449313e63d84ec1efebba7a27d0564dd
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001321240_338239488.pth b/checkpoint_p0/milestones/checkpoint_001321240_338239488.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9d5da790c59110f62e06b93c5deacdd849d6e7d4
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001321240_338239488.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f032c53debe99a2cee2a8106c568b03ad2a1e75db852068af63e2af00d4958a4
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001334072_341524480.pth b/checkpoint_p0/milestones/checkpoint_001334072_341524480.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b20d85453fbe7b7047097ade20930f7ebb744fd5
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001334072_341524480.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4fe1a695d83d92d9ff23ef67f5f029ee46386487361f22ab11d96bd6bfe9d2c
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001346872_344801280.pth b/checkpoint_p0/milestones/checkpoint_001346872_344801280.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d578340d130cd35111b90cf785b7724637de8058
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001346872_344801280.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61df46b78a48a7193a735a6f2f575f36c4a81eca790edfdf230b79382bb40c34
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001359704_348086272.pth b/checkpoint_p0/milestones/checkpoint_001359704_348086272.pth
new file mode 100644
index 0000000000000000000000000000000000000000..44d1c9fbf29e03e9caec8b83261355ff57cd81b0
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001359704_348086272.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b466f8e9a76ca6fe8556dd622d8dd4b212041f493c9872a9888965aa364532
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001372600_351387648.pth b/checkpoint_p0/milestones/checkpoint_001372600_351387648.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c8c9ab496bdf4b7956009d15631f3230db1b5f61
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001372600_351387648.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c59e69a2d47828dbfa8fd8c5e8f85644e414271c583fa406128e39abb833376
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001385464_354680832.pth b/checkpoint_p0/milestones/checkpoint_001385464_354680832.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d33d1a686b1659c0f55111895afd008e061651a4
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001385464_354680832.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8458a95e1378d180c39bffea67a931478bf84def36a16c07a5ac577714d116
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001398232_357949440.pth b/checkpoint_p0/milestones/checkpoint_001398232_357949440.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b9595f0d586dd2d8b34d5b32f9217632256826bd
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001398232_357949440.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2070abbc98fcb4f5c249b797b877a1c7009cb0863e2c43f2e2076ade0868f3
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001411064_361234432.pth b/checkpoint_p0/milestones/checkpoint_001411064_361234432.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a84777254842c740778a72280dbb2e550d43aa2c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001411064_361234432.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa70e8aa9b12691bfff66245b759b331891e9fd897036c7cf2a542cdb503d9bd
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001423864_364511232.pth b/checkpoint_p0/milestones/checkpoint_001423864_364511232.pth
new file mode 100644
index 0000000000000000000000000000000000000000..63d9d6b08b2b7d1c5f8afe46ab738ee09aff5b16
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001423864_364511232.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d15380babfbbfd949f71228f31394adde1648773af4987628c539d547d5d89
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001436696_367796224.pth b/checkpoint_p0/milestones/checkpoint_001436696_367796224.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ae4fded172797dafdf109362aae1588868f2eaad
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001436696_367796224.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94aee0bab6fea992241c0beec9449140340416648a11bc893afa3509aa4042a8
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001449560_371089408.pth b/checkpoint_p0/milestones/checkpoint_001449560_371089408.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3ff3c074db0da71651c245518d81f664d57e1b71
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001449560_371089408.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ade9c2f9bb6df2dc4565abd8dd9f959a0022746444354101b385d4b68abc733
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001462392_374374400.pth b/checkpoint_p0/milestones/checkpoint_001462392_374374400.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b9c6df9ceb65f9b2cb7276ecd5e1025f238be67f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001462392_374374400.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c120efd5b23506205756d0ee3247dd6f925551a452462b1dc08437160a3d42
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001475256_377667584.pth b/checkpoint_p0/milestones/checkpoint_001475256_377667584.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4b82664305cad4b87cec8215d3387f82d4f73cd7
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001475256_377667584.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35f3a896dc886a6d3f58c940dee423db7e5d7c63e70a11e40bd05dd4362eb40
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001488152_380968960.pth b/checkpoint_p0/milestones/checkpoint_001488152_380968960.pth
new file mode 100644
index 0000000000000000000000000000000000000000..298cbe4c4866fbe8cee31e19093d0aae245c948b
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001488152_380968960.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5a29200657e83ff3eb5d638fab6acb57157cb868f41fd11378695246c9d1db
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001501016_384262144.pth b/checkpoint_p0/milestones/checkpoint_001501016_384262144.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ed2a7ef7a69acdefe05af44f65c86d153bf50ff8
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001501016_384262144.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45c2a98e6822636b503c8ea047269a099c1ccbad878490d7eae92253ab8cf30
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001513880_387555328.pth b/checkpoint_p0/milestones/checkpoint_001513880_387555328.pth
new file mode 100644
index 0000000000000000000000000000000000000000..871f072916474166f1d3d251a431eddd1ef95da2
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001513880_387555328.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c356bafe2c9c1ed4bac2fb229502750a31e3ce1647e630746f863a1c9a3a9deb
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001526744_390848512.pth b/checkpoint_p0/milestones/checkpoint_001526744_390848512.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a8b117852b8a9a2f838d900a990932ca73d08f0e
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001526744_390848512.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73974663d8a0fdefd571108293b3d350ddb897913a5defc7f6a3498a5e8bce81
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001539544_394125312.pth b/checkpoint_p0/milestones/checkpoint_001539544_394125312.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d93fc38f110196e77ef4a6657e85b867c0eec9bf
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001539544_394125312.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b25de3085782cac7a3e75aa377022604cc51bad2bbd2ef13f1ca33d7603936a
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001552440_397426688.pth b/checkpoint_p0/milestones/checkpoint_001552440_397426688.pth
new file mode 100644
index 0000000000000000000000000000000000000000..63bed58efe6becaaaac462bd85fb64bf062d68b0
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001552440_397426688.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bacbc7efad69c9c3967687696ea53b1e30ac98f4bc3b651af8f332c09e54b63c
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001565336_400728064.pth b/checkpoint_p0/milestones/checkpoint_001565336_400728064.pth
new file mode 100644
index 0000000000000000000000000000000000000000..651980ad9c468a5151dd9a708a0209800131f81f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001565336_400728064.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a533b058b6810544e50bbebfca2133bae29af189f74efcff21049c43e77eb1b6
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001578168_404013056.pth b/checkpoint_p0/milestones/checkpoint_001578168_404013056.pth
new file mode 100644
index 0000000000000000000000000000000000000000..59d506f081caa7095844f00e5bee9747f6e5f8c4
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001578168_404013056.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ca43ad344f077aa8d7cfbfa7cb3a2fe2849404aab703a1dbac4eeb90f94a84
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001590968_407289856.pth b/checkpoint_p0/milestones/checkpoint_001590968_407289856.pth
new file mode 100644
index 0000000000000000000000000000000000000000..23167cd6998212fbaa8c16f3a615d890f8c98761
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001590968_407289856.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab25fd51b2c752a5bd8e03d4de3f259cf5c715af52181542757fe2056607b5e
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001603832_410583040.pth b/checkpoint_p0/milestones/checkpoint_001603832_410583040.pth
new file mode 100644
index 0000000000000000000000000000000000000000..05d3860000c4be59b354c11313b76bda97f2995d
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001603832_410583040.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015f27d546b593be50fe5ec4f10546663aee3da1ba1f2f78154b03cb0a66b5b4
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001616728_413884416.pth b/checkpoint_p0/milestones/checkpoint_001616728_413884416.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c7cbc4f0460b3c99c7082d1393948439755d16af
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001616728_413884416.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4cd0b8a7c9b79f86b771be7578860c2469bbfcad18a942cd848b151ec23b61
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001629624_417185792.pth b/checkpoint_p0/milestones/checkpoint_001629624_417185792.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0589886009a821d83fcbb4a4e836f8a3715c67bc
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001629624_417185792.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2511a0b0dd3a072f377011ee432a58256f1857a0072627d5d71a86cbf79d43
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001642456_420470784.pth b/checkpoint_p0/milestones/checkpoint_001642456_420470784.pth
new file mode 100644
index 0000000000000000000000000000000000000000..653c8039ef6394579623fa38d55ed452223a7dc1
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001642456_420470784.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81f80832bfd06b9bb7deb57b8d6834ca4679186b1d70b7ddd718fea866a6c31
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001655288_423755776.pth b/checkpoint_p0/milestones/checkpoint_001655288_423755776.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b56a8b190087dcf6f0ab98f7582f68ecf0441a5b
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001655288_423755776.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6db01b633ecca53b0645f65f047d3e8503b75a437514f392f20561a167f1aa
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001668152_427048960.pth b/checkpoint_p0/milestones/checkpoint_001668152_427048960.pth
new file mode 100644
index 0000000000000000000000000000000000000000..66c92f22738f2c4378f89244e86f7be55228d6b3
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001668152_427048960.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200c05854708136cfdbe0f18e91db01e3e076e592f1fe0f3b635d728899fa345
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001681016_430342144.pth b/checkpoint_p0/milestones/checkpoint_001681016_430342144.pth
new file mode 100644
index 0000000000000000000000000000000000000000..62367909d487a4eaadac83bad7db7b98f6df138f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001681016_430342144.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b3f72a8bc1760c89a05d5cfeb9a1783265ee66f4f08206f80e6436cf3ae371
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001693944_433651712.pth b/checkpoint_p0/milestones/checkpoint_001693944_433651712.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9b3b8e8966a0db574fb60fdc4056ee0869b8dba3
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001693944_433651712.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7b47c662479d1cad0ee7436f213a958211614d44d3025565a1b100ee4f705e
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001706712_436920320.pth b/checkpoint_p0/milestones/checkpoint_001706712_436920320.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2a600c6686aff9e5fa97b60ce8daa046ee62b00e
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001706712_436920320.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c343cd94250a53e3d13da4277db07423589177fc2cfddf5d28eec0cc5940270
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001719640_440229888.pth b/checkpoint_p0/milestones/checkpoint_001719640_440229888.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b79f3f5834e88063327ef36af5de5f6de1f1086f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001719640_440229888.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b928ccf0f470c87739206ebfc3939aee928cae3db7e0e4669d8a61baf6ff2bb4
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001732024_443400192.pth b/checkpoint_p0/milestones/checkpoint_001732024_443400192.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a55081df4bcb0324a61f2cab0db0f706c5ae61b8
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001732024_443400192.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3e4720938f05edfcb2773dae66434780e34e94c73a9b8d7459cd82f7b18599
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001744984_446717952.pth b/checkpoint_p0/milestones/checkpoint_001744984_446717952.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b52f6d195c6ca11ae50c9085ae35fb84bf1dd678
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001744984_446717952.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd924c4f2b5677ee03b22e8aa1549e517a32bf24d647b67123abcded0ae3c5b2
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001757880_450019328.pth b/checkpoint_p0/milestones/checkpoint_001757880_450019328.pth
new file mode 100644
index 0000000000000000000000000000000000000000..65961eae2107801cf40888a604b59b16c60f8883
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001757880_450019328.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d723b2d7799b01723ef5511bc3513ba54e74f470591c6f905be8ede009357b6f
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001770808_453328896.pth b/checkpoint_p0/milestones/checkpoint_001770808_453328896.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0c7a44c2951e69c3b8f3eb686d7668b2019606ab
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001770808_453328896.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473683723e76fccdde877c77a17b83221edc0538d58d0eacb1c86b5fbfb07ef2
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001783768_456646656.pth b/checkpoint_p0/milestones/checkpoint_001783768_456646656.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1e7cda70f2be916ccaac62e8dc31677f6e49e5d5
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001783768_456646656.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e863861e85fcab470f685172e5c29032e000fc6f6591f74be0f52129147779e6
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001796760_459972608.pth b/checkpoint_p0/milestones/checkpoint_001796760_459972608.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1e0619b93a0947a91322737136539a88bad61c4b
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001796760_459972608.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:215d5b7032888168fa95346d929901c65892c0cb65938de1d8df4e1f0dd222eb
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001809688_463282176.pth b/checkpoint_p0/milestones/checkpoint_001809688_463282176.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d5791725077c452d193edbcc2a0ef6333250e011
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001809688_463282176.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1323e0e774bc1018bcdca1ccb15ec54d110158c281e1531a2b01a9e9086bf78b
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001822648_466599936.pth b/checkpoint_p0/milestones/checkpoint_001822648_466599936.pth
new file mode 100644
index 0000000000000000000000000000000000000000..de9c8cc669efc64cacc5334f5d69a6d15aba9173
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001822648_466599936.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1191bccfcf37861a42140af4f64341252029acaf75a814aa44f4c30139f4aa
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001835640_469925888.pth b/checkpoint_p0/milestones/checkpoint_001835640_469925888.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e4eaa013338f85f98cf3186754c489cc1b322b98
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001835640_469925888.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754a048ec47f62b25c0c6ecaba129b89a0b8537fcb642d1498568213e16d2721
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001848664_473260032.pth b/checkpoint_p0/milestones/checkpoint_001848664_473260032.pth
new file mode 100644
index 0000000000000000000000000000000000000000..86e9af55d2b9e2b9b5d2228f1e9067c09f8236af
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001848664_473260032.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6190c13150272b447370d95206de15595d2096440b9f65faff757e15620e736
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001861624_476577792.pth b/checkpoint_p0/milestones/checkpoint_001861624_476577792.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6ac70b0071c0a5fa91b483ad8c9dc3d710c06b14
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001861624_476577792.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d270f666bcf8d9fd2ca8868ac256fad05a6ba23003a84120dfb828a1f498e7c5
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001874552_479887360.pth b/checkpoint_p0/milestones/checkpoint_001874552_479887360.pth
new file mode 100644
index 0000000000000000000000000000000000000000..520ff758b90f29261f628316af952df60f5429a2
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001874552_479887360.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc06195b2a733ac040c9f5a21fce2a322b065176716c7cfd7b06a855ed3615a
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001887544_483213312.pth b/checkpoint_p0/milestones/checkpoint_001887544_483213312.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8febd4acebc76aa169804b6d83fa541d68b42aa1
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001887544_483213312.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422ab570f7f1b0c7e3a805206e03e98f1001d90810392ce4967b432f4b73d3cb
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001900504_486531072.pth b/checkpoint_p0/milestones/checkpoint_001900504_486531072.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f97ea1b671c277b3730d65cf5ffa787bd67f1ee4
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001900504_486531072.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aff416c7f8155e9793aefe004822a744cda668adc59c4fbc4ce9c304918e2ac
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001913496_489857024.pth b/checkpoint_p0/milestones/checkpoint_001913496_489857024.pth
new file mode 100644
index 0000000000000000000000000000000000000000..612effbf408f78f951cbf4928349ff5fd42814c2
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001913496_489857024.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f92f25a2599e3307b2bffbed63cbd584034cd1800e9e589f3b7bd77c5b23e7
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001926424_493166592.pth b/checkpoint_p0/milestones/checkpoint_001926424_493166592.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a9bbaad8a835158f64db3c6572f9462336cf4cd1
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001926424_493166592.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f2145ab53dc9d570d12fe0931b370840eca076b4ff0657af60a47de32d5834
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001939384_496484352.pth b/checkpoint_p0/milestones/checkpoint_001939384_496484352.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cfbaab0a45be339ed344412749d4327d26368541
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001939384_496484352.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffdced07605bbe84f4cc8b889fb40a8bdcb6171e7be5d8f39f486c36b0f28ba9
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001952376_499810304.pth b/checkpoint_p0/milestones/checkpoint_001952376_499810304.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9c9235bc2a3d14c9b78918d552412d5885fb6716
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001952376_499810304.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60aa28b2a50d840a45c72dd7e9e0e515c3692b5b8687fd7fe115c46e06e3f0ca
+size 20723147
diff --git a/checkpoint_p0/milestones/checkpoint_001959512_503275520.pth b/checkpoint_p0/milestones/checkpoint_001959512_503275520.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d2b003331ddcc018a243e3471b0016b473a4a9d3
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001959512_503275520.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d084004d70bfabb0e85e9fdae794ad3482d3e75244e93c2c3a91ab7d6ad42295
+size 20723083
diff --git a/checkpoint_p1/best_001948032_498696192_reward_219.910.pth b/checkpoint_p1/best_001948032_498696192_reward_219.910.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0aed04cab38557d4b94c034c6d2c59ff9018a387
--- /dev/null
+++ b/checkpoint_p1/best_001948032_498696192_reward_219.910.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4247bd0592180e5e15220232562c17b1ee76a99b068601faf2913062db62d37f
+size 20721843
diff --git a/checkpoint_p1/checkpoint_001952800_499916800.pth b/checkpoint_p1/checkpoint_001952800_499916800.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b29e7db36085005fec8fb98a612a2f0d5ad244e1
--- /dev/null
+++ b/checkpoint_p1/checkpoint_001952800_499916800.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83de9d15ad4e72072fc39c737c0a0e9faa49f1964bc2ff62ce9642bd74940005
+size 20722179
diff --git a/checkpoint_p1/checkpoint_001953136_500015104.pth b/checkpoint_p1/checkpoint_001953136_500015104.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d39f87d59e936cce2c7f2b4d6ebe1c3f1fa71b4f
--- /dev/null
+++ b/checkpoint_p1/checkpoint_001953136_500015104.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f53fe4b520d2a62bfb1d99e142df7c577f533952681adf9c5c07a0d356b3ce20
+size 20722179
diff --git a/checkpoint_p1/milestones/checkpoint_000012480_3194880.pth b/checkpoint_p1/milestones/checkpoint_000012480_3194880.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b256e8c76b9adce17a0fbe56d7267cff08d1a943
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000012480_3194880.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14ba112a7c9a9e6e8c2ef245da1bfbf68e4357aec4f9f906f75346b7b811e83
+size 20723035
diff --git a/checkpoint_p1/milestones/checkpoint_000025280_6471680.pth b/checkpoint_p1/milestones/checkpoint_000025280_6471680.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dee57a4b3a053507393ae645de9beca9b62f5a49
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000025280_6471680.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cfb04ccab1492cbdfc039b26b99889b914a211158e90ce2e2f76f401e0465dd
+size 20723035
diff --git a/checkpoint_p1/milestones/checkpoint_000038176_9773056.pth b/checkpoint_p1/milestones/checkpoint_000038176_9773056.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3eab79b6c1e0290a972ef87ad579730ea7d7f0e9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000038176_9773056.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98e32342bfab5998f34cde069d12067289ad226c9d31b9c331f2b098d69fabd
+size 20723035
diff --git a/checkpoint_p1/milestones/checkpoint_000051040_13066240.pth b/checkpoint_p1/milestones/checkpoint_000051040_13066240.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c95741bd0276c9f2658216313a995ce1dfe770a5
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000051040_13066240.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e299d9eb096e034d8cda39bca51a5f09e28a02c69471e38d8e19ba22726944
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000063904_16359424.pth b/checkpoint_p1/milestones/checkpoint_000063904_16359424.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f8b2fb8b88d1b3189fb5339a5fdd1d451541271e
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000063904_16359424.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08716a152bfd91ec537058e8227bccfbaaf7277bda823beb5c07f7a14f258fec
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000076768_19652608.pth b/checkpoint_p1/milestones/checkpoint_000076768_19652608.pth
new file mode 100644
index 0000000000000000000000000000000000000000..564cf2ddf7f41510d924871e40c646a2d65be1ba
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000076768_19652608.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b3e60fb2648aa75482da9f3dda16a6e42e0010309d43fc8f5fbc10fdf2d1b6
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000089600_22937600.pth b/checkpoint_p1/milestones/checkpoint_000089600_22937600.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1c0a0983a380be34db753e87302a259548013ec3
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000089600_22937600.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c9b10e3be704cf382079d087fd0dc57d16b1c3cf51467116bf12f6d56b6177
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000102496_26238976.pth b/checkpoint_p1/milestones/checkpoint_000102496_26238976.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c1489e61a6b6e0af7c7cf7fda24be2bbeeec5a2d
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000102496_26238976.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4aecaf50918dea1cda2dd2388874108e90179d64f3b5cb06f334b2e21a455f
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000115360_29532160.pth b/checkpoint_p1/milestones/checkpoint_000115360_29532160.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0cb9398e7352f9618ed613320e2232ff0f7a6346
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000115360_29532160.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e15a3bbd9befb3e18ddbcba3e0e1b6f62d0a8d0dffc5a6bc3bbe14e4f313786
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000128160_32808960.pth b/checkpoint_p1/milestones/checkpoint_000128160_32808960.pth
new file mode 100644
index 0000000000000000000000000000000000000000..173d724cf9bba3b3e02f489f83512616975b383b
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000128160_32808960.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f5d68cd2bf4e320791bde13908d4da38b58eb609cfd522c363e6e3bdf0749c
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000141024_36102144.pth b/checkpoint_p1/milestones/checkpoint_000141024_36102144.pth
new file mode 100644
index 0000000000000000000000000000000000000000..520582a504dad25cbb5967118b65362bccf316b1
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000141024_36102144.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a69d1e333545c3fce6411ba814c5062ee9bfc140c058bc10d5ead8aa02b8098
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000153888_39395328.pth b/checkpoint_p1/milestones/checkpoint_000153888_39395328.pth
new file mode 100644
index 0000000000000000000000000000000000000000..38cf593f4633e3a5fcc25c0f5998ad3e921596d9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000153888_39395328.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df60430d55bd88b1193becaea7ff11a570f5988f227368bbcce0a822de35a0cf
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000166752_42688512.pth b/checkpoint_p1/milestones/checkpoint_000166752_42688512.pth
new file mode 100644
index 0000000000000000000000000000000000000000..973f8f6560f611a76073e67a6cf663eeed18f5e0
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000166752_42688512.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1a07e101bad773a5dbb3e295c47858f1160d04ea55d6ab6e6a72c5ebcc35d9
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000179648_45989888.pth b/checkpoint_p1/milestones/checkpoint_000179648_45989888.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4b4a30bd9869583c5cda30288046de3534a1507c
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000179648_45989888.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ac114662de741f2149dc1b74696b8c0cb6b2bf968971829bf781ebad175fe3
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000192544_49291264.pth b/checkpoint_p1/milestones/checkpoint_000192544_49291264.pth
new file mode 100644
index 0000000000000000000000000000000000000000..df0d3ee0816de15e68fbdaca304ca5b5eab5726c
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000192544_49291264.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad221672fd3dc5ace1d8ed19bcae70f8a897588952b4202cfb630c16a67b5018
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000205408_52584448.pth b/checkpoint_p1/milestones/checkpoint_000205408_52584448.pth
new file mode 100644
index 0000000000000000000000000000000000000000..62cd737c4cc9eeb332d1e7f8d2b9e95a845da97c
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000205408_52584448.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a64ff5d27ae6150babc8282d86cdc4807ea6c51a0571a5ecfedaa9b2a6f8ad
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000218240_55869440.pth b/checkpoint_p1/milestones/checkpoint_000218240_55869440.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fd1a9a446cca77bfbf7df05cf3f3518f12f90b97
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000218240_55869440.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceebeedeb3fb3564fe8da246ec785de5f115f2bca479890ff0ab83d77bdb3d75
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000231136_59170816.pth b/checkpoint_p1/milestones/checkpoint_000231136_59170816.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f7f5ccc206393034c91a15bcd025c06b4c74e45c
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000231136_59170816.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878e374bf4dc0a56bc38bd65f709353a8a18176f97860bb9181cc066ddf4b663
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000243936_62447616.pth b/checkpoint_p1/milestones/checkpoint_000243936_62447616.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a23175d553629c7ceeb4b5961d7cab02db18c0ff
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000243936_62447616.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ab17f7bdd81c9ec935dc9ee664022158415da5925779992e8ebce335a1bfce
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000256800_65740800.pth b/checkpoint_p1/milestones/checkpoint_000256800_65740800.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e16ffe76a4955a87cffc989ccc25ec73ca9b571a
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000256800_65740800.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d8877245962dbfef2cb10fae6f3d2d86d39d7ed8d3746ecd88f8b26b955e01
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000269664_69033984.pth b/checkpoint_p1/milestones/checkpoint_000269664_69033984.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5c2add6f47dbd8793bdb677be91ecb4a635b89f9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000269664_69033984.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b7ed1262ebf80f5bafa4a9fcd199ae490406981ef50a9f2c6c401b2629f72a
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000282464_72310784.pth b/checkpoint_p1/milestones/checkpoint_000282464_72310784.pth
new file mode 100644
index 0000000000000000000000000000000000000000..98562106893aa78e95ed7c133194477f53afbcc9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000282464_72310784.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695d55e4baeb5ea93422be4d3d62d80bda37486e0c00b8d435a1ba15f433697a
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000295392_75620352.pth b/checkpoint_p1/milestones/checkpoint_000295392_75620352.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6866f596b6c0a3b058b0e3eddca7c760dfabd6dc
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000295392_75620352.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6294762c7270cb55e51836514495c24f805cc3fbea3e8e1366fc776375d5fd05
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000308256_78913536.pth b/checkpoint_p1/milestones/checkpoint_000308256_78913536.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ec16396a2e81ec9b0ed51869ba671240fb816b9b
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000308256_78913536.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8726eb2839c63767ce9b499550926f1306f8e470a659360e2434bb72678e78e4
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000321120_82206720.pth b/checkpoint_p1/milestones/checkpoint_000321120_82206720.pth
new file mode 100644
index 0000000000000000000000000000000000000000..046ca5a56ad10ad9308215efa439313a74ef6b76
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000321120_82206720.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb21f6c431732753e040d671d0950b0bec8447d18632c4bf9420e5697557138
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000334016_85508096.pth b/checkpoint_p1/milestones/checkpoint_000334016_85508096.pth
new file mode 100644
index 0000000000000000000000000000000000000000..50c86ba4479a6e3179aa8693dd91976a322048d4
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000334016_85508096.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e99cad970a9ccee48c9a2114f1d4d61c91a8a4f6dffe82997c8750ff8d4d939
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000346880_88801280.pth b/checkpoint_p1/milestones/checkpoint_000346880_88801280.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d5f4969285a10c912ffd0f9d141bfc9c95ef977
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000346880_88801280.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5bad664136d47e7495724640c7e5bf46dceb08016154bfb71855630b8090d89
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000359680_92078080.pth b/checkpoint_p1/milestones/checkpoint_000359680_92078080.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4840ce5216bd0e2ece666e482b9818958ba78110
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000359680_92078080.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc6a71f3f7c53ea7683dc156b2c7ffedd8eb88069bff325d076187d3e6ebf61
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000372608_95387648.pth b/checkpoint_p1/milestones/checkpoint_000372608_95387648.pth
new file mode 100644
index 0000000000000000000000000000000000000000..50b544aea155590ad07232dee4b908da69b6c53f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000372608_95387648.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1e26ccb02a81c43222ab184410c67b46db28a2d2b9d4d6af0d99ab1d59c2db
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000385472_98680832.pth b/checkpoint_p1/milestones/checkpoint_000385472_98680832.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bf13bad5a9966e8c1e2c78209325092891115930
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000385472_98680832.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65423d5473159a8a873338d11d74665c4145aee7cccb8d075393528dbb1aac1
+size 20723091
diff --git a/checkpoint_p1/milestones/checkpoint_000398304_101965824.pth b/checkpoint_p1/milestones/checkpoint_000398304_101965824.pth
new file mode 100644
index 0000000000000000000000000000000000000000..578b0aa88fc1bb591fee45794904d61a1fd0a69f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000398304_101965824.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac554f6e1737d8f2278b2eb63e392ec3ee44deb3aab7ecb7b26b9e42648fc71
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000411136_105250816.pth b/checkpoint_p1/milestones/checkpoint_000411136_105250816.pth
new file mode 100644
index 0000000000000000000000000000000000000000..48c29c8d82c0adb65fcc7d53cc05a5a15f7ce93a
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000411136_105250816.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df86f004f7af463eb8c0a6532eecf6b06268d6d6ca80fd4d8dbf6af31a0c3df
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000423968_108535808.pth b/checkpoint_p1/milestones/checkpoint_000423968_108535808.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dbe460836ba7edcaadaed4facedfbbbab73d8f70
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000423968_108535808.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ba4c019e7f013ab78c9cd895c9a6328a0af1df7126a2d5a3b9db92c69718ff
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000436800_111820800.pth b/checkpoint_p1/milestones/checkpoint_000436800_111820800.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2645b0256025c515ab65987b7922d2b8a0acc236
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000436800_111820800.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57113c66667a27fc265d421f1996d52400f5874c0d94c5003de5bcb612ae8c0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000449664_115113984.pth b/checkpoint_p1/milestones/checkpoint_000449664_115113984.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e1e1b05fc612d662c687fd78b1b93379766c3a93
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000449664_115113984.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac59cdbd1d94279d08711fadc7a10528f6ece6a5180e5318d5852dbe8d15205
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000462496_118398976.pth b/checkpoint_p1/milestones/checkpoint_000462496_118398976.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a1bfd29b9a9327d1f697966e49c86778011eab2a
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000462496_118398976.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b990934c708570a30b1e1a1a5138e4a1124729808ad7cdaee5e01b02ff3c84d3
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000475360_121692160.pth b/checkpoint_p1/milestones/checkpoint_000475360_121692160.pth
new file mode 100644
index 0000000000000000000000000000000000000000..598e39fc0e4c2b435c7381814706da8ef24f6b31
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000475360_121692160.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf66ef5e56032952cdbdbf75f2395ee2894c9a0ea1e2677f2a0d0460844a795
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000488224_124985344.pth b/checkpoint_p1/milestones/checkpoint_000488224_124985344.pth
new file mode 100644
index 0000000000000000000000000000000000000000..aa60c9255597fc3afe129385012c9973d1f18e1c
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000488224_124985344.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d2e467f1cd7d83a1fc1aa0d43f720e247ea9018481ff2f9e27dc972b25ea3e
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000501056_128270336.pth b/checkpoint_p1/milestones/checkpoint_000501056_128270336.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a1d4c208c0904572821f1144445c3fafa6506216
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000501056_128270336.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7369abf7d9935069843e27b7f27c60db20532f94dd7f346364a55105f25757
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000513888_131555328.pth b/checkpoint_p1/milestones/checkpoint_000513888_131555328.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1cb4ea4afb4bb9a59d586c46fce447e96a00754d
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000513888_131555328.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f25583ced99de38416ee774e7221fcf97289eaa5c4cc128dbb2e9dfde8e97db
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000526752_134848512.pth b/checkpoint_p1/milestones/checkpoint_000526752_134848512.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1bb7277fb1b2071270c006f34ede45d6b9fc0f41
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000526752_134848512.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8d1c3d8582e01f90ffab35153c2e234d81606da9183c343205318c08da36c9
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000539584_138133504.pth b/checkpoint_p1/milestones/checkpoint_000539584_138133504.pth
new file mode 100644
index 0000000000000000000000000000000000000000..16477d4b29743556dedb66936bd6f58e42e8d2d1
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000539584_138133504.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db81565bcd980e4f2c3ad678fba4c4648d3aa7be6f5cf061731f2b9c9ef20a91
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000552512_141443072.pth b/checkpoint_p1/milestones/checkpoint_000552512_141443072.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d324da3000c8cd273f28ce4c18b953b8491bd68
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000552512_141443072.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1877d87e14144833309be37c97c99f845c184ebd7151ab55ee5394a3c9fb83ed
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000565312_144719872.pth b/checkpoint_p1/milestones/checkpoint_000565312_144719872.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6fc3bebbb82d34aead30c71911fb42f078bc4055
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000565312_144719872.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71fa795ab9c5b7b96e804325b71efc4004f56e9cfd1e8aa65cdb35d356f925b
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000578144_148004864.pth b/checkpoint_p1/milestones/checkpoint_000578144_148004864.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cc80ace4dec1d78fd6c7944dcad0d771e32c0157
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000578144_148004864.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953e60c8dc4dfc3ba86b0cccbb19b2e3582c84ed0ff6c2740a44c29f9817b455
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000590976_151289856.pth b/checkpoint_p1/milestones/checkpoint_000590976_151289856.pth
new file mode 100644
index 0000000000000000000000000000000000000000..94a60be8d337e530f830421903800a36919fbb11
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000590976_151289856.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57dcbfa1fec364da94c57a35b026cd4642a02822281a1397204a15ec4f500ae8
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000603808_154574848.pth b/checkpoint_p1/milestones/checkpoint_000603808_154574848.pth
new file mode 100644
index 0000000000000000000000000000000000000000..de7b391a1fc35d8ce0c156633d86d3dbfd512567
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000603808_154574848.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1cd76c644d7415538da985e832bf984c662919f34bdf99b4b187b69cdcd373
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000616640_157859840.pth b/checkpoint_p1/milestones/checkpoint_000616640_157859840.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c19992c186b45263b1ea94aba385356ccd8caf50
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000616640_157859840.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b59974d736c59e162e210f487022c9684db8984053de26aab7c66c8a6fa158
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000629472_161144832.pth b/checkpoint_p1/milestones/checkpoint_000629472_161144832.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9b1124597744a7556bef80b023e9205e950a48f2
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000629472_161144832.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cda9ecc3e357915df08e07debb2e88c50cee26a3be56f7050d93219ba28fa03
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000642368_164446208.pth b/checkpoint_p1/milestones/checkpoint_000642368_164446208.pth
new file mode 100644
index 0000000000000000000000000000000000000000..da4747d9523926c75069478e8d8b4420fdaec587
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000642368_164446208.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf900aa7dcadb9982d98eb3cd7837b0ef27c47ed8dd1a6e25458eff54e2dc220
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000655168_167723008.pth b/checkpoint_p1/milestones/checkpoint_000655168_167723008.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b777a662ea958f098715c2f5077ced84b2eb4ecd
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000655168_167723008.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6669782c8216dcdf2b2e09b5f75a70c880745c3779bd6fec352da8ca58d24555
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000668032_171016192.pth b/checkpoint_p1/milestones/checkpoint_000668032_171016192.pth
new file mode 100644
index 0000000000000000000000000000000000000000..da4396c672250799b34a751ae0624d7b037623ee
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000668032_171016192.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9501a8fe3f74caba55229ec2d56185ce5dea1c4b327617b49b25854a90943833
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000680992_174333952.pth b/checkpoint_p1/milestones/checkpoint_000680992_174333952.pth
new file mode 100644
index 0000000000000000000000000000000000000000..87273e2a1b59987b4e9f3c457a0d76dd3c2e7b3b
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000680992_174333952.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db4d15e9b49845ced504f7641d87f7f0a85eaa9996845b1ac3b95b6ff38f715
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000693856_177627136.pth b/checkpoint_p1/milestones/checkpoint_000693856_177627136.pth
new file mode 100644
index 0000000000000000000000000000000000000000..80f4637074e34773a9437dd7d6b1064a7022e604
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000693856_177627136.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252af03340a1c2d5f0325eb5666cf2a5bb1a2989199198aed41cc53194044efc
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000706688_180912128.pth b/checkpoint_p1/milestones/checkpoint_000706688_180912128.pth
new file mode 100644
index 0000000000000000000000000000000000000000..169be903fb152e32a5c6fd6f991be016edc18a4f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000706688_180912128.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed64aea54a1500a4494a25caa46145d4c559f41fa6a2554b6c903751ffaf622
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000719552_184205312.pth b/checkpoint_p1/milestones/checkpoint_000719552_184205312.pth
new file mode 100644
index 0000000000000000000000000000000000000000..67970447b7d7456d8f8a5f04dd482d296c799fd8
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000719552_184205312.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79022e50f560a5d645d9f3a4953a1f6c5c83c9134393e0d3d173a99444354f1
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000732448_187506688.pth b/checkpoint_p1/milestones/checkpoint_000732448_187506688.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a818dbf5a95e61455767431700d0d5613161e24f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000732448_187506688.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fe1d72ae238df66ef04aed66f920e898a7bdd8b3af53059fe8af2b786a219b
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000745312_190799872.pth b/checkpoint_p1/milestones/checkpoint_000745312_190799872.pth
new file mode 100644
index 0000000000000000000000000000000000000000..07bbf6e4d82ae11d12f8397a69c5af57c9889be9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000745312_190799872.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759e788dac40343a8f4739bb00eb4e7bc704403d08926c649cd34e4c0141ff26
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000758112_194076672.pth b/checkpoint_p1/milestones/checkpoint_000758112_194076672.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4da69638adb248ea724713188dc7e07eb87457a0
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000758112_194076672.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f9302e3253826b002085a44c583c3c77187af9cd2ef10b51ec75005703ff43
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000770976_197369856.pth b/checkpoint_p1/milestones/checkpoint_000770976_197369856.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8b392b47a23927138624abd3c344e446d14c0c82
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000770976_197369856.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a821358727f1d6ddcd2d7f31184f3fef2c913e53f7ac2e861df9a4c942d6ef
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000783840_200663040.pth b/checkpoint_p1/milestones/checkpoint_000783840_200663040.pth
new file mode 100644
index 0000000000000000000000000000000000000000..39d1298b38d9b7c25697d68302cc4898280f0fb0
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000783840_200663040.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af921bc3e93460bf32794d1c14e6662a3a489168cc8a28f51ae7cb2ad1c3b4c
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000796320_203857920.pth b/checkpoint_p1/milestones/checkpoint_000796320_203857920.pth
new file mode 100644
index 0000000000000000000000000000000000000000..718747f7b0e095422edc3731c949e975143230aa
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000796320_203857920.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a41e2950cdb835e76d24bbee01a8d047aa8dbe6b322ec50b0a670e595a3149
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000809152_207142912.pth b/checkpoint_p1/milestones/checkpoint_000809152_207142912.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ee64f28523e5f5503f18e50c3483232d6f855586
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000809152_207142912.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d9fb2244dd59a619a10b8d7e51db899b7a337fc8cb903cadacf0beb8629e57
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000821984_210427904.pth b/checkpoint_p1/milestones/checkpoint_000821984_210427904.pth
new file mode 100644
index 0000000000000000000000000000000000000000..afae5a79e56b7fcaefb5d0cce995aeb7315ac20e
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000821984_210427904.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9063670535c26a14db528d196a2083ef5c6487b7a22a7c04261599de3caf293
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000834880_213729280.pth b/checkpoint_p1/milestones/checkpoint_000834880_213729280.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c2c74c962a59fb07229104e37562741820295a43
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000834880_213729280.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea187a828918a3584b46e6af9a50650f57ee9597e1f2cefc48fc57f03374339
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000847712_217014272.pth b/checkpoint_p1/milestones/checkpoint_000847712_217014272.pth
new file mode 100644
index 0000000000000000000000000000000000000000..67033d4d2cf1a67d9456f42316fb06471572c365
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000847712_217014272.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08b0d0d2b4dc4b97be00305d11278ab344ca4674889b6b7ff788ece1095c77e
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000860544_220299264.pth b/checkpoint_p1/milestones/checkpoint_000860544_220299264.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f63259adde1480b4b65236539018c0c8573e1895
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000860544_220299264.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8829fbdc25abf5193b00b260de78a55ba675bd24288a2b47872f0afa99a016ef
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000873440_223600640.pth b/checkpoint_p1/milestones/checkpoint_000873440_223600640.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0b8c35caaca6e98c5813dab3f9f7b020589714c6
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000873440_223600640.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a848a2bfaea9529433fa60e3c4567529c861bbbd0e00d743bfc107937c72cbe
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000886272_226885632.pth b/checkpoint_p1/milestones/checkpoint_000886272_226885632.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3b5909642633a0547f28f6e199227521a03bffb6
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000886272_226885632.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a9f7ddf7773a29610fc1673579964b8722865782cfadc71ecf2fff1c3a503a
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000899168_230187008.pth b/checkpoint_p1/milestones/checkpoint_000899168_230187008.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3b935b51477cc3d683571da0fefdc24c051cfb2a
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000899168_230187008.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f84f7ab0b16f475dcb59406110e93c669c88a74880b3cee6c275e10c3fbd30
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000912000_233472000.pth b/checkpoint_p1/milestones/checkpoint_000912000_233472000.pth
new file mode 100644
index 0000000000000000000000000000000000000000..52f3bd9fb96a98bb9910a0dce7a230d7cc7d7cb1
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000912000_233472000.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186636121f0afb41650ccaddeadf1cc96fd9008f3718a043b35541517e0938ab
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000924960_236789760.pth b/checkpoint_p1/milestones/checkpoint_000924960_236789760.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e0834272f42f0e41fc58838274871bc4cfced268
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000924960_236789760.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975e6d9ade85341371ce8192e2e3f4c1f333ebba690d0595f4a3179f44907370
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000937856_240091136.pth b/checkpoint_p1/milestones/checkpoint_000937856_240091136.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3a4a9040cd70a70ce4bdb7849dd7c24c1dd424f5
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000937856_240091136.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a7360930c7f72460085719ba22621aee7399c0bb9f4605e5761eb049870b55
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000950720_243384320.pth b/checkpoint_p1/milestones/checkpoint_000950720_243384320.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a2abbab1434e55e8adfef1b0c4fa8bf70e94283d
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000950720_243384320.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8214ca5d36f9e49c964a1d11becdb6f96a79c6afe130a6302f8bd4c1eff896
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000963584_246677504.pth b/checkpoint_p1/milestones/checkpoint_000963584_246677504.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cbfff2987649a96ced34cca1cfa354cfe3daa1a5
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000963584_246677504.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649e28ffa7dc4d7e973dfa62e7993cfac1dd3d5c67c270c8e9235699aad2b058
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000976416_249962496.pth b/checkpoint_p1/milestones/checkpoint_000976416_249962496.pth
new file mode 100644
index 0000000000000000000000000000000000000000..83a937f3048c7434189218518f9afad970b31d03
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000976416_249962496.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39402c49fb2c248b4d1050ef61512d5b98440ece34614635b3b17584bab61697
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_000989312_253263872.pth b/checkpoint_p1/milestones/checkpoint_000989312_253263872.pth
new file mode 100644
index 0000000000000000000000000000000000000000..80ccbdcb80393515cd46202cc4dcfac49eccfbd7
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000989312_253263872.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc3a99ab3b65b52d9d77354bcfabbea8c35ec48c63bd71694202497b82cbbde
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001002208_256565248.pth b/checkpoint_p1/milestones/checkpoint_001002208_256565248.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c2520e301c180896bc96bc0de429e410c993b328
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001002208_256565248.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221646987d4ac807f241d0ec8675ebb33c48098415402de5fa8db6540a0b9162
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001015136_259874816.pth b/checkpoint_p1/milestones/checkpoint_001015136_259874816.pth
new file mode 100644
index 0000000000000000000000000000000000000000..80354756a2c03a91ae174cf1de402c006c1cd2e9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001015136_259874816.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac82ea3bf11004eb97ff037703e1fb5857e6b7a0c121492903ff4859014b29e
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001027968_263159808.pth b/checkpoint_p1/milestones/checkpoint_001027968_263159808.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f3aa7fa6002ea2dc6ed2d9b6ce83a0b42be25ed1
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001027968_263159808.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7337a82484df031986b9d22e0d3114f9f813d369769f8ac7490dae8a767869
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001040864_266461184.pth b/checkpoint_p1/milestones/checkpoint_001040864_266461184.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fc1476f5216d59557086242683aa09ed2452939b
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001040864_266461184.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6939726f4c700c2a48a1baf8a2958bdc6bdb2201c5c07bbca9bc6cb32b3be7
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001053728_269754368.pth b/checkpoint_p1/milestones/checkpoint_001053728_269754368.pth
new file mode 100644
index 0000000000000000000000000000000000000000..10275b5646726fea7486630e97c396fbc99532fb
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001053728_269754368.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4549637f5266ff7c2f19ab011ea39194ea3f9a7868c97dd6304518121aefb11
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001066624_273055744.pth b/checkpoint_p1/milestones/checkpoint_001066624_273055744.pth
new file mode 100644
index 0000000000000000000000000000000000000000..074d83cde894df65d7e847848231b4a5ddd85acd
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001066624_273055744.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61e57aa50a875d2d04720df771980466687b8c1f6e85f4459d10a852b692fd0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001079520_276357120.pth b/checkpoint_p1/milestones/checkpoint_001079520_276357120.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6e30bdd7f67c8176bacc313ae7ac66e8ab37da40
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001079520_276357120.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de322400e3db954cf4f99be61fe8edd28ec9034c0d577fc790972d1d12aef5cb
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001092416_279658496.pth b/checkpoint_p1/milestones/checkpoint_001092416_279658496.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7c2c201afc88ed75ff4b8cbb7b201dabe9d5af58
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001092416_279658496.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e52568697938e3dcf90afbb512e508bfc77f91dac3c97d624e8562acee011e
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001105344_282968064.pth b/checkpoint_p1/milestones/checkpoint_001105344_282968064.pth
new file mode 100644
index 0000000000000000000000000000000000000000..abf54cc0a52b38f049480216de8db45dad5b1c57
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001105344_282968064.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51063c94f0edb2f0720785fb8c33a5fc273caf289f3e553c0e6c097364915d87
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001118176_286253056.pth b/checkpoint_p1/milestones/checkpoint_001118176_286253056.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b7e2b4e2fca62ab629ba0851108364cc70ba2bb6
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001118176_286253056.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b8b1a6a0d66ec7e277876f034fa95d7e188de80f553e033f672976f25b0634
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001131072_289554432.pth b/checkpoint_p1/milestones/checkpoint_001131072_289554432.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1fa38090ccb73b549bfd823b6587ca1f7def5bad
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001131072_289554432.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fabbb96738897b323f8f6856bb9d0dfd4381e09c710df68a1e7a01d21b1f2f5
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001143904_292839424.pth b/checkpoint_p1/milestones/checkpoint_001143904_292839424.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ffdeaaf69cab80c25f006fc37c0575019854b680
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001143904_292839424.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf0721b75b89b63f04e9f3a1fc98773c15e697736e7fa00202c3fbe08b1c194
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001156800_296140800.pth b/checkpoint_p1/milestones/checkpoint_001156800_296140800.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9a8a8a935c3f62d369a3a2ae331600dca989b749
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001156800_296140800.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b1d98d75aa4f5d9dddd03c03a6b70ea396e1760ce1c48dfa7c1afe403aaac3
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001169760_299458560.pth b/checkpoint_p1/milestones/checkpoint_001169760_299458560.pth
new file mode 100644
index 0000000000000000000000000000000000000000..22869687299872cd2c26a5f152be9ecc03e3d190
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001169760_299458560.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b80f7463635d7f589838ff565bf70d189637f3d3847c844b7458d6089b3f156
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001182624_302751744.pth b/checkpoint_p1/milestones/checkpoint_001182624_302751744.pth
new file mode 100644
index 0000000000000000000000000000000000000000..03306ac4d4fa816929d84bcd2c1031fe404bb2c0
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001182624_302751744.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383c8ab9ecbd0062e5e460085a7b8b82ac83324825d7389be73339cd4a589a52
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001195392_306020352.pth b/checkpoint_p1/milestones/checkpoint_001195392_306020352.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bcc887e23e3d205b351b278d8274b4f1f15e95d1
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001195392_306020352.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93271c5e438d0c1d3c23cba311381d82f539fc9867d629667ea466325212832
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001208064_309264384.pth b/checkpoint_p1/milestones/checkpoint_001208064_309264384.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0fa72a8112a19ec918a6abf2b6e8660e53059fe6
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001208064_309264384.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0452887a89d0fe5833a74bcf43c12617080629bc3d1a0d5c6837f597d0d0de6
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001220672_312492032.pth b/checkpoint_p1/milestones/checkpoint_001220672_312492032.pth
new file mode 100644
index 0000000000000000000000000000000000000000..62b4605af9b3fe963d45c51a9af9c6ff7f26e554
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001220672_312492032.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c171a4bc2be4ff42b88fcb090f769effc14b6f93fcad06ac0f10a652965b9322
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001233440_315760640.pth b/checkpoint_p1/milestones/checkpoint_001233440_315760640.pth
new file mode 100644
index 0000000000000000000000000000000000000000..103d7065af09f3a0d3b0299ab2dddb27d3ee00a0
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001233440_315760640.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ed102c779961ff306994c749088c1344c79bedf7988f2cf33c83b55305ae8b
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001246240_319037440.pth b/checkpoint_p1/milestones/checkpoint_001246240_319037440.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6f3e25505fae7502f453fc1a259eac67afe44692
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001246240_319037440.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9fc0ae7e58d558d7cf9a3919681c38a941f9d8da598736115688b858e986c92
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001259008_322306048.pth b/checkpoint_p1/milestones/checkpoint_001259008_322306048.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0facefbe35b0b909df79f999ea585ac638f5c8b5
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001259008_322306048.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5324a3f881412f1cb41a229056f1306be6811262cd2de7d2800f16474327b0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001271808_325582848.pth b/checkpoint_p1/milestones/checkpoint_001271808_325582848.pth
new file mode 100644
index 0000000000000000000000000000000000000000..01ce265f4e7a003e65d5705e746e34537dc1a2c5
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001271808_325582848.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e022ec8eab99ef4fc7eddf228f8d49ed73353f4e406e19fe72d7fdd2b298ece1
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001284544_328843264.pth b/checkpoint_p1/milestones/checkpoint_001284544_328843264.pth
new file mode 100644
index 0000000000000000000000000000000000000000..44eb4c58d27ced77bdf84cf4c5da4201944b4d98
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001284544_328843264.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac6de8c402b4478ae4ab80d1e08f13341096b14184b40848dc431d25a62f2c4
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001297280_332103680.pth b/checkpoint_p1/milestones/checkpoint_001297280_332103680.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3d6c0447b7c50c31a45300632ef91cffb3ad021f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001297280_332103680.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad28d8571d906ea87d8ac342bca89aa9d478352bf35ad650bac19c0579d93f02
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001310048_335372288.pth b/checkpoint_p1/milestones/checkpoint_001310048_335372288.pth
new file mode 100644
index 0000000000000000000000000000000000000000..28cff5e65bc56dba11e2b2c3d55d43b903e87342
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001310048_335372288.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a43c05c3a80071fa182ac8594cf42e237920f2a384132dd2e05ba2d7b636d0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001322816_338640896.pth b/checkpoint_p1/milestones/checkpoint_001322816_338640896.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6b2ed4ef5cfa53c99c3c83c19715fdcb341be30f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001322816_338640896.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83262cf5264f0436dd8aa5b2708b9a1e60ca36b21a69dd0d3592be7afb5744d
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001335616_341917696.pth b/checkpoint_p1/milestones/checkpoint_001335616_341917696.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cdfbe3a5f1c52968576aeba00e36c41915780a43
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001335616_341917696.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0057f14a465341a4ec87f0085c9bcf875da9f6db7098c345d56508ce6f7f321b
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001348384_345186304.pth b/checkpoint_p1/milestones/checkpoint_001348384_345186304.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d9f0b265bdb837632b5ff60e28924f64d533e6fb
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001348384_345186304.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93090a9616e131228821b62c1568c1d8f5175cf1f98512161105850b887dc1fe
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001361088_348438528.pth b/checkpoint_p1/milestones/checkpoint_001361088_348438528.pth
new file mode 100644
index 0000000000000000000000000000000000000000..497c010c120ab7d7d860b2859245038cbbbaf423
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001361088_348438528.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344f36e18c66fabd3548148f22da43a4ec0e379dd40a5caca37bb7e313134ce0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001373856_351707136.pth b/checkpoint_p1/milestones/checkpoint_001373856_351707136.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bff0cabb076a312b016a3a68f2a540ecff19f134
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001373856_351707136.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e817acc8ed0f20fd36ac5785185c49bf4acfb202ca266b18af5ebec34b70030
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001386656_354983936.pth b/checkpoint_p1/milestones/checkpoint_001386656_354983936.pth
new file mode 100644
index 0000000000000000000000000000000000000000..505a2eacd958e64c61285faff50e2c42e71cb5e0
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001386656_354983936.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da02f96a503816f86ab84ce6db73929b3c22ba0950636c2f6f62f9e0d3c3d0b0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001399360_358236160.pth b/checkpoint_p1/milestones/checkpoint_001399360_358236160.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b244f32057cb35a16adbaa8e5b6a6e6cd90829d4
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001399360_358236160.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112bd8a8f486a5157892c145f034ff9abc5dfe8a356135432c98fdfb348f287b
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001412128_361504768.pth b/checkpoint_p1/milestones/checkpoint_001412128_361504768.pth
new file mode 100644
index 0000000000000000000000000000000000000000..be44054279daabf92d7c451425292d4efe538047
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001412128_361504768.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf711ed5b56b322e7d895f7d4abab75d1e678182bea9f54552c073c9be99534
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001424832_364756992.pth b/checkpoint_p1/milestones/checkpoint_001424832_364756992.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a00cb93b51cb5014d2c0976806ade651c63d157e
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001424832_364756992.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644a2cf0a1f7f52097ed8c2ff0ce1401f51b2612fc7cf21e0a10bbc57c2eb2da
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001437600_368025600.pth b/checkpoint_p1/milestones/checkpoint_001437600_368025600.pth
new file mode 100644
index 0000000000000000000000000000000000000000..537de5625b46b064a20a30c48d8ddd48dafd4bdd
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001437600_368025600.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bcec239f7e5680c5d849d21ee27de4e3c62b1def72d04b4c054d3396649c51c
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001450304_371277824.pth b/checkpoint_p1/milestones/checkpoint_001450304_371277824.pth
new file mode 100644
index 0000000000000000000000000000000000000000..16bd8d6bf89110d81bf21bc8a956824deec51d8a
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001450304_371277824.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe838423a8e73877cd871221ec2bcafa2407f09d7d8452f88c72407c1fd5b4a
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001462976_374521856.pth b/checkpoint_p1/milestones/checkpoint_001462976_374521856.pth
new file mode 100644
index 0000000000000000000000000000000000000000..60758b7f2a50aab562570275be3f8b440423b393
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001462976_374521856.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65bace345b182f5116f6f4c06af022fbc924d02d57a939f5a6bfb88802150dca
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001475776_377798656.pth b/checkpoint_p1/milestones/checkpoint_001475776_377798656.pth
new file mode 100644
index 0000000000000000000000000000000000000000..225de4dda22a9204993e561cc2aa3d38bf7413e3
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001475776_377798656.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d664180aeadd1d8218448b5045f65e69fa6902dcb7a3b8848e4007f29a831bc
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001488544_381067264.pth b/checkpoint_p1/milestones/checkpoint_001488544_381067264.pth
new file mode 100644
index 0000000000000000000000000000000000000000..96c3fcf4c17da2221d0e130a39cc4294a4c11747
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001488544_381067264.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ab7704ae9c31c7607029b157cd1f7bd0a79074dfdb8738d1037f0724b0d3c0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001501280_384327680.pth b/checkpoint_p1/milestones/checkpoint_001501280_384327680.pth
new file mode 100644
index 0000000000000000000000000000000000000000..25f97748ce3b8d86bd87e283914621a3aea885fe
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001501280_384327680.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3dcdd923344d0a3e0fdda08b8194951e1f434a53b5f7f090cf2169bf9a12180
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001514048_387596288.pth b/checkpoint_p1/milestones/checkpoint_001514048_387596288.pth
new file mode 100644
index 0000000000000000000000000000000000000000..749e00777b61d7f697b53be17d6bc4ba3b7584b9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001514048_387596288.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be02f12e143683475a6769690f18a4729ed29f9431bded5dfeb0ffc661d333d
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001526848_390873088.pth b/checkpoint_p1/milestones/checkpoint_001526848_390873088.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4e407d28603bad1b068ef9d9316358d06aff5b31
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001526848_390873088.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e475b367051b98b1b61bd989ee361d80dd40808c48aafa7fe9cdeb7bfeaf3edd
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001539616_394141696.pth b/checkpoint_p1/milestones/checkpoint_001539616_394141696.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4f7b0af9c657a7b12bba72ac422cba0199efbf4f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001539616_394141696.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca7f771bc0beca72c5562193ebdf72f3b9ab564f443691dca588fc94177a9a25
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001552352_397402112.pth b/checkpoint_p1/milestones/checkpoint_001552352_397402112.pth
new file mode 100644
index 0000000000000000000000000000000000000000..95222d8eab5ae68d169852cd5099b48a3ae30900
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001552352_397402112.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f784f133d18c9b892521224c3e3c088b04778f0c8a0bbec5f3ba1515e9341951
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001565088_400662528.pth b/checkpoint_p1/milestones/checkpoint_001565088_400662528.pth
new file mode 100644
index 0000000000000000000000000000000000000000..135187684f1382a6ed78de42ec195cd3dc641db1
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001565088_400662528.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3f26789a071e033d2b0cba9e258c5435c687c00201bb6f152f86a7219054b6
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001577856_403931136.pth b/checkpoint_p1/milestones/checkpoint_001577856_403931136.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c8bda4d279ffd56ffe773b967753ec2d97dbaeb8
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001577856_403931136.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6c89b5009588e4b0b4f40d901a40d4aa60bd436132aad9d2e543ef82d524e2
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001590656_407207936.pth b/checkpoint_p1/milestones/checkpoint_001590656_407207936.pth
new file mode 100644
index 0000000000000000000000000000000000000000..afc5997598d9567b048ab8ef68df182663ae149e
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001590656_407207936.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:076fafc184d9f019b3433d2913bc0acc82dbc59c64b498bda616234057668486
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001603360_410460160.pth b/checkpoint_p1/milestones/checkpoint_001603360_410460160.pth
new file mode 100644
index 0000000000000000000000000000000000000000..925af6e40dac21fbea2f3f4a80a117da1888bf20
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001603360_410460160.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90573f3fe52e1d697321755b7ec978c6fd7f1bc41132e27d8200e13aa72675c0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001616192_413745152.pth b/checkpoint_p1/milestones/checkpoint_001616192_413745152.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e787149f87640bd0df99aa57a4516225a1542dfb
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001616192_413745152.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447f33d1ff6d9daf056268d28c4eb4e1203851b7716461f3cb744cc54fd06c15
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001628992_417021952.pth b/checkpoint_p1/milestones/checkpoint_001628992_417021952.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e636b8811c364f3a5b7552e2dbe37b94d8633376
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001628992_417021952.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf99018f371131bd43af1fbeb271c98f42ee3453d72dd16026e25d048fc1d3d0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001641728_420282368.pth b/checkpoint_p1/milestones/checkpoint_001641728_420282368.pth
new file mode 100644
index 0000000000000000000000000000000000000000..be68ddc83fd3b74043ae467d407e3c9258a280da
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001641728_420282368.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da75881b366d18bc7e8609859abc93a355ba314c16a4187c6df503405a610a0c
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001654400_423526400.pth b/checkpoint_p1/milestones/checkpoint_001654400_423526400.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1aa38e02c72e59ec01e0cd8330efb60e02ebac10
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001654400_423526400.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2341fcc2bb7399bafdaa3ef0494e5a49fa3b342aaf57e92fc2faf1e5e799a853
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001667104_426778624.pth b/checkpoint_p1/milestones/checkpoint_001667104_426778624.pth
new file mode 100644
index 0000000000000000000000000000000000000000..143d13794f5829341b2d6e65fcfd433197cb7358
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001667104_426778624.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e021784bd167ec44049e826dbafd92f5100d0fe747713dec2702b4230ffa311
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001679840_430039040.pth b/checkpoint_p1/milestones/checkpoint_001679840_430039040.pth
new file mode 100644
index 0000000000000000000000000000000000000000..49348f26a478f68ec4f783c74b64eea0785a0264
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001679840_430039040.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2fe774339104c72edce66e4e2b8274268ad13ecb0af943ce475d9acd7b934dd
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001692576_433299456.pth b/checkpoint_p1/milestones/checkpoint_001692576_433299456.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ee42c8203413a6ca9c60665404ea6204b773724e
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001692576_433299456.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc81d4166e6433280e42dbbe231e9e8da145125785c850481de1806edd10bb9
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001705312_436559872.pth b/checkpoint_p1/milestones/checkpoint_001705312_436559872.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ec3ab55e23016b11122f554e23c342cbe2a663ea
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001705312_436559872.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c614c558eec73020dc74f427d66ae4505c931b33b2efe55658adfa3dc6f7303
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001717664_439721984.pth b/checkpoint_p1/milestones/checkpoint_001717664_439721984.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6ba8efdba1233e11b7c147f89d87f51df110da68
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001717664_439721984.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e62b2c8dd59146e21f36bc0f63c403d013417b3dd1a4d1ccdfee78ea17332d
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001730432_442990592.pth b/checkpoint_p1/milestones/checkpoint_001730432_442990592.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b25a1de0f81f092abcd2dbe9c581c1335dfbdca2
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001730432_442990592.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02bdb5cdd03b53948164f6e882f550d545564aabd03f77826eb31b4c0bb435b
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001743232_446267392.pth b/checkpoint_p1/milestones/checkpoint_001743232_446267392.pth
new file mode 100644
index 0000000000000000000000000000000000000000..11b4018418246ac7406288f80a18b841f1088aed
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001743232_446267392.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77f4d2c6b78a1cd213cf69ec4ea04759f911015a80030351b172479760b5985
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001756096_449560576.pth b/checkpoint_p1/milestones/checkpoint_001756096_449560576.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2c030cf780c9b77f4e664e1989aabd338b48890a
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001756096_449560576.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb9aba21cab087f57a25ccbdd0f56b2bc625d57e8ed805c4ae1894e2827c0c0
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001768928_452845568.pth b/checkpoint_p1/milestones/checkpoint_001768928_452845568.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b863bd07e131cb0e90130fecab2ad8de48cc4ca9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001768928_452845568.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3116bfa47de3e82f11a46775e4c7641260575a4a583cd9ae4813810b0c137d
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001781760_456130560.pth b/checkpoint_p1/milestones/checkpoint_001781760_456130560.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3b61c641cec2487140918499dabe6296642f8158
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001781760_456130560.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b7211030c7d792c07d7b7e308fd0f1977ebb6b64e4bcac444d4b3749ca2f110
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001794624_459423744.pth b/checkpoint_p1/milestones/checkpoint_001794624_459423744.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b7dc80904a6eecc370710f30a76bce57e6e3e94b
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001794624_459423744.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb74a80acd89e6e0c079ad1706414d7571a6dba356d9449dfabb2775c72ef51
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001807424_462700544.pth b/checkpoint_p1/milestones/checkpoint_001807424_462700544.pth
new file mode 100644
index 0000000000000000000000000000000000000000..457df6c59a1e27f79b73d96e0c27b9874497c2b0
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001807424_462700544.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1f355491ae837f97d4cfba7e9dde5c5a55511aa0f4fbde95a89f408ae47a85
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001820320_466001920.pth b/checkpoint_p1/milestones/checkpoint_001820320_466001920.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0de93e38e139e9e7e6aeb01e478aaaca1bf1ee48
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001820320_466001920.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae19d25ff298133c9154e5a4ffa2f1d6a4eb5d7a4de395a2284a0433970934ba
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001833184_469295104.pth b/checkpoint_p1/milestones/checkpoint_001833184_469295104.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9af8a07bd3bb02e96dfa230cd4f018fa527db70f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001833184_469295104.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7149c61ce2af3af7d48429f641993ef5477e233ff2fc6e44294d5f2e5886b38
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001846016_472580096.pth b/checkpoint_p1/milestones/checkpoint_001846016_472580096.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c263aac644e96f014f2017ac655bfedc63a56c60
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001846016_472580096.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b7371ad172744b6b2737bf9956153117e3021fefc467204b237a671b857fba
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001858848_475865088.pth b/checkpoint_p1/milestones/checkpoint_001858848_475865088.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b468e95c1aff28a4444007276698f03819fcf1f7
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001858848_475865088.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e33feb0e4eae74f91ffa95e66cb7d4ef8044277df3c15fd77759fdc3834ca4c
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001871680_479150080.pth b/checkpoint_p1/milestones/checkpoint_001871680_479150080.pth
new file mode 100644
index 0000000000000000000000000000000000000000..72f0be5335cffcea9feae37ae4934633c81e8d49
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001871680_479150080.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835c0973600bd853e37c1aeb942fe611eff25e4a6e9f04f75907952a090587f1
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001884544_482443264.pth b/checkpoint_p1/milestones/checkpoint_001884544_482443264.pth
new file mode 100644
index 0000000000000000000000000000000000000000..edbc16d6a434641f419899cd1ab39f052b5fb3c9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001884544_482443264.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9990b31983cdbc406510b4f5d544c6bd42c03c55ff5b6312b26632389bd6269
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001897440_485744640.pth b/checkpoint_p1/milestones/checkpoint_001897440_485744640.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c1eb1150a64e61c1c189a0699694792b8aa21c58
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001897440_485744640.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1dc5e9c2069ee26ad01529b11172a5ae2e4ba18e7ceca36e00ebbe0b2feaf34
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001910336_489046016.pth b/checkpoint_p1/milestones/checkpoint_001910336_489046016.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a5d32ecf15ddddd7257bb2d0b491c4f2b83d67a4
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001910336_489046016.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5069a238f6efbddc5eea56d5042c5a0c34a201e4461a47b7f13dcca1edd0e2a2
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001923200_492339200.pth b/checkpoint_p1/milestones/checkpoint_001923200_492339200.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e4702366ea3511d530800b6f0b65250e609931ba
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001923200_492339200.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe1aa3a738ad347857793c68c9d66975daf9ae7ecdd6e966c9690ee15c2ff15
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001936128_495648768.pth b/checkpoint_p1/milestones/checkpoint_001936128_495648768.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6119e54750d3e7bd4091445be773b3930cf86564
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001936128_495648768.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c33cc92b219934135770de74f427b014daccf4136a170fc959601177f50afd2
+size 20723147
diff --git a/checkpoint_p1/milestones/checkpoint_001948928_498925568.pth b/checkpoint_p1/milestones/checkpoint_001948928_498925568.pth
new file mode 100644
index 0000000000000000000000000000000000000000..59f2d96bd259ac5df17081c8225738dd51306cf2
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001948928_498925568.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c220458b2bc5b61ec628f0f6f9fd13de33a90fb88ff700c30d30712a5ba17440
+size 20723147
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a62179643e36786605129f8abe23a94b59ba889
--- /dev/null
+++ b/config.json
@@ -0,0 +1,164 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "atari_qbert",
+  "experiment": "atari_qbert_APPO",
+  "train_dir": "./train_atari",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": 1234,
+  "num_policies": 2,
+  "async_rl": true,
+  "serial_mode": false,
+  "batched_sampling": true,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 2,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 16,
+  "num_envs_per_worker": 8,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 4,
+  "rollout": 128,
+  "recurrence": 1,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1.0,
+  "reward_clip": 1000.0,
+  "value_bootstrap": false,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.0004677351413,
+  "value_loss_coeff": 0.5,
+  "kl_loss_coeff": 0.0,
+  "exploration_loss": "entropy",
+  "gae_lambda": 0.95,
+  "ppo_clip_ratio": 0.1,
+  "ppo_clip_value": 1.0,
+  "with_vtrace": false,
+  "vtrace_rho": 1.0,
+  "vtrace_c": 1.0,
+  "optimizer": "adam",
+  "adam_eps": 1e-05,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 0.0,
+  "learning_rate": 0.0003033891184,
+  "lr_schedule": "linear_decay",
+  "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
+  "obs_subtract_mean": 0.0,
+  "obs_scale": 255.0,
+  "normalize_input": true,
+  "normalize_input_keys": [
+    "obs"
+  ],
+  "decorrelate_experience_max_seconds": 0,
+  "decorrelate_envs_on_one_worker": true,
+  "actor_worker_gpus": [],
+  "set_workers_cpu_affinity": true,
+  "force_envs_single_thread": false,
+  "default_niceness": 0,
+  "log_to_file": true,
+  "experiment_summaries_interval": 3,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": false,
+  "heartbeat_interval": 10,
+  "heartbeat_reporting_interval": 60,
+  "train_for_env_steps": 500000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 120,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": 1200,
+  "save_best_every_sec": 5,
+  "save_best_metric": "reward",
+  "save_best_after": 100000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    512,
+    512
+  ],
+  "encoder_conv_architecture": "convnet_atari",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": false,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "relu",
+  "policy_initialization": "orthogonal",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": false,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": false,
+  "env_gpu_actions": false,
+  "env_gpu_observations": true,
+  "env_frameskip": 4,
+  "env_framestack": 4,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": true,
+  "with_wandb": true,
+  "wandb_user": "matt-stammers",
+  "wandb_project": "atari_APPO",
+  "wandb_group": "atari_qbert",
+  "wandb_job_type": "SF",
+  "wandb_tags": [
+    "atari"
+  ],
+  "with_pbt": false,
+  "pbt_mix_policies_in_one_env": true,
+  "pbt_period_env_steps": 5000000,
+  "pbt_start_mutation": 20000000,
+  "pbt_replace_fraction": 0.3,
+  "pbt_mutation_rate": 0.15,
+  "pbt_replace_reward_gap": 0.1,
+  "pbt_replace_reward_gap_absolute": 1e-06,
+  "pbt_optimize_gamma": false,
+  "pbt_target_objective": "true_objective",
+  "pbt_perturb_min": 1.1,
+  "pbt_perturb_max": 1.5,
+  "command_line": "--algo=APPO --env=atari_qbert --experiment=atari_qbert_APPO --num_policies=2 --restart_behavior=resume --train_dir=./train_atari --train_for_env_steps=500000000 --seed=1234 --num_workers=16 --num_envs_per_worker=8 --num_batches_per_epoch=8 --worker_num_splits=2 --async_rl=true --batched_sampling=true --batch_size=1024 --max_grad_norm=0 --learning_rate=0.0003033891184 --heartbeat_interval=10 --heartbeat_reporting_interval=60 --save_milestones_sec=1200 --num_epochs=4 --exploration_loss_coeff=0.0004677351413 --summaries_use_frameskip=False --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari_APPO --wandb_group=atari_qbert --wandb_job_type=SF --wandb_tags=atari",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "atari_qbert",
+    "experiment": "atari_qbert_APPO",
+    "train_dir": "./train_atari",
+    "restart_behavior": "resume",
+    "seed": 1234,
+    "num_policies": 2,
+    "async_rl": true,
+    "batched_sampling": true,
+    "worker_num_splits": 2,
+    "num_workers": 16,
+    "num_envs_per_worker": 8,
+    "batch_size": 1024,
+    "num_batches_per_epoch": 8,
+    "num_epochs": 4,
+    "exploration_loss_coeff": 0.0004677351413,
+    "max_grad_norm": 0.0,
+    "learning_rate": 0.0003033891184,
+    "summaries_use_frameskip": false,
+    "heartbeat_interval": 10,
+    "heartbeat_reporting_interval": 60,
+    "train_for_env_steps": 500000000,
+    "save_milestones_sec": 1200,
+    "with_wandb": true,
+    "wandb_user": "matt-stammers",
+    "wandb_project": "atari_APPO",
+    "wandb_group": "atari_qbert",
+    "wandb_job_type": "SF",
+    "wandb_tags": [
+      "atari"
+    ]
+  },
+  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
+  "git_repo_name": "not a git repository",
+  "wandb_unique_id": "atari_qbert_APPO_20231119_033402_869247"
+}
\ No newline at end of file
diff --git a/git.diff b/git.diff
new file mode 100644
index 0000000000000000000000000000000000000000..9cf0f6792bd54243f70657987210adf15e33d282
--- /dev/null
+++ b/git.diff
@@ -0,0 +1,3470 @@
+diff --git a/train_dir/Standup/.summary/0/events.out.tfevents.1695118333.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/0/events.out.tfevents.1695118333.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index ce9a72a..0000000
+Binary files a/train_dir/Standup/.summary/0/events.out.tfevents.1695118333.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/.summary/0/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/0/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index 85ffbb3..0000000
+Binary files a/train_dir/Standup/.summary/0/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/.summary/0/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/0/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index 6b68289..0000000
+Binary files a/train_dir/Standup/.summary/0/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/.summary/1/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/1/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index 7e65434..0000000
+Binary files a/train_dir/Standup/.summary/1/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/.summary/1/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/1/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index e2184e2..0000000
+Binary files a/train_dir/Standup/.summary/1/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/README.md b/train_dir/Standup/README.md
+index 59b4eea..2dc15b6 100644
+--- a/train_dir/Standup/README.md
++++ b/train_dir/Standup/README.md
+@@ -5,7 +5,7 @@ tags:
+ - reinforcement-learning
+ - sample-factory
+ model-index:
+-- name: APPO
++- name: ATD3
+   results:
+   - task:
+       type: reinforcement-learning
+@@ -15,12 +15,12 @@ model-index:
+       type: mujoco_standup
+     metrics:
+     - type: mean_reward
+-      value: 160842.81 +/- 49335.32
++      value: 157750.89 +/- 30990.47
+       name: mean_reward
+       verified: false
+ ---
+ 
+-A(n) **APPO** model trained on the **mujoco_standup** environment.
++A(n) **ATD3** model trained on the **mujoco_standup** environment.
+ 
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+@@ -30,7 +30,7 @@ Documentation for how to use Sample-Factory can be found at https://www.samplefa
+ 
+ After installing Sample-Factory, download the model with:
+ ```
+-python -m sample_factory.huggingface.load_from_hub -r MattStammers/appo-mujoco-Standup
++python -m sample_factory.huggingface.load_from_hub -r MattStammers/atd3-mujoco-standup
+ ```
+ 
+     
+@@ -38,7 +38,7 @@ python -m sample_factory.huggingface.load_from_hub -r MattStammers/appo-mujoco-S
+ 
+ To run the model after download, use the `enjoy` script corresponding to this environment:
+ ```
+-python -m sf_examples.mujoco.enjoy_mujoco --algo=APPO --env=mujoco_standup --train_dir=./train_dir --experiment=appo-mujoco-Standup
++python -m sf_examples.mujoco.enjoy_mujoco --algo=ATD3 --env=mujoco_standup --train_dir=./train_dir --experiment=atd3-mujoco-standup
+ ```
+ 
+ 
+@@ -49,7 +49,7 @@ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
+ 
+ To continue training with this model, use the `train` script corresponding to this environment:
+ ```
+-python -m sf_examples.mujoco.train_mujoco --algo=APPO --env=mujoco_standup --train_dir=./train_dir --experiment=appo-mujoco-Standup --restart_behavior=resume --train_for_env_steps=10000000000
++python -m sf_examples.mujoco.train_mujoco --algo=ATD3 --env=mujoco_standup --train_dir=./train_dir --experiment=atd3-mujoco-standup --restart_behavior=resume --train_for_env_steps=10000000000
+ ```
+ 
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
+diff --git a/train_dir/Standup/checkpoint_p0/best_000008160_4177920_reward_162764.036.pth b/train_dir/Standup/checkpoint_p0/best_000008160_4177920_reward_162764.036.pth
+deleted file mode 100644
+index 7b4f077..0000000
+Binary files a/train_dir/Standup/checkpoint_p0/best_000008160_4177920_reward_162764.036.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p0/checkpoint_000014336_7340032.pth b/train_dir/Standup/checkpoint_p0/checkpoint_000014336_7340032.pth
+deleted file mode 100644
+index d1f1336..0000000
+Binary files a/train_dir/Standup/checkpoint_p0/checkpoint_000014336_7340032.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth b/train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth
+deleted file mode 100644
+index f4340e0..0000000
+Binary files a/train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p1/best_000013232_6774784_reward_164168.870.pth b/train_dir/Standup/checkpoint_p1/best_000013232_6774784_reward_164168.870.pth
+deleted file mode 100644
+index af623df..0000000
+Binary files a/train_dir/Standup/checkpoint_p1/best_000013232_6774784_reward_164168.870.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p1/checkpoint_000014296_7319552.pth b/train_dir/Standup/checkpoint_p1/checkpoint_000014296_7319552.pth
+deleted file mode 100644
+index f875926..0000000
+Binary files a/train_dir/Standup/checkpoint_p1/checkpoint_000014296_7319552.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth b/train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth
+deleted file mode 100644
+index 0916341..0000000
+Binary files a/train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth and /dev/null differ
+diff --git a/train_dir/Standup/config.json b/train_dir/Standup/config.json
+index 638783d..22fa3bb 100644
+--- a/train_dir/Standup/config.json
++++ b/train_dir/Standup/config.json
+@@ -1,10 +1,10 @@
+ {
+   "help": false,
+-  "algo": "APPO",
++  "algo": "ATD3",
+   "env": "mujoco_standup",
+   "experiment": "Standup",
+   "train_dir": "./train_dir",
+-  "restart_behavior": "resume",
++  "restart_behavior": "restart",
+   "device": "gpu",
+   "seed": null,
+   "num_policies": 2,
+@@ -104,8 +104,8 @@
+   "use_record_episode_statistics": false,
+   "with_wandb": true,
+   "wandb_user": "matt-stammers",
+-  "wandb_project": "sample_factory",
+-  "wandb_group": "mujoco_standup",
++  "wandb_project": "mujoco",
++  "wandb_group": "mujoco_standup3",
+   "wandb_job_type": "SF",
+   "wandb_tags": [
+     "mujoco"
+diff --git a/train_dir/Standup/replay.mp4 b/train_dir/Standup/replay.mp4
+index 51d7026..f9ddacb 100644
+Binary files a/train_dir/Standup/replay.mp4 and b/train_dir/Standup/replay.mp4 differ
+diff --git a/train_dir/Standup/sf_log.txt b/train_dir/Standup/sf_log.txt
+index c3ddd83..0d60e70 100644
+--- a/train_dir/Standup/sf_log.txt
++++ b/train_dir/Standup/sf_log.txt
+@@ -1,46 +1,48 @@
+-[2023-09-19 11:12:17,416][35316] Saving configuration to ./train_dir/Standup/config.json...
+-[2023-09-19 11:12:17,417][35316] Rollout worker 0 uses device cpu
+-[2023-09-19 11:12:17,418][35316] Rollout worker 1 uses device cpu
+-[2023-09-19 11:12:17,418][35316] Rollout worker 2 uses device cpu
+-[2023-09-19 11:12:17,418][35316] Rollout worker 3 uses device cpu
+-[2023-09-19 11:12:17,418][35316] Rollout worker 4 uses device cpu
+-[2023-09-19 11:12:17,419][35316] Rollout worker 5 uses device cpu
+-[2023-09-19 11:12:17,419][35316] Rollout worker 6 uses device cpu
+-[2023-09-19 11:12:17,419][35316] Rollout worker 7 uses device cpu
+-[2023-09-19 11:12:17,419][35316] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
+-[2023-09-19 11:12:17,463][35316] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:17,463][35316] InferenceWorker_p0-w0: min num requests: 2
+-[2023-09-19 11:12:17,487][35316] Starting all processes...
+-[2023-09-19 11:12:17,488][35316] Starting process learner_proc0
+-[2023-09-19 11:12:17,492][35316] Starting all processes...
+-[2023-09-19 11:12:17,504][35316] Starting process inference_proc0-0
+-[2023-09-19 11:12:17,504][35316] Starting process rollout_proc0
+-[2023-09-19 11:12:17,505][35316] Starting process rollout_proc1
+-[2023-09-19 11:12:17,505][35316] Starting process rollout_proc2
+-[2023-09-19 11:12:17,507][35316] Starting process rollout_proc3
+-[2023-09-19 11:12:17,507][35316] Starting process rollout_proc4
+-[2023-09-19 11:12:17,508][35316] Starting process rollout_proc5
+-[2023-09-19 11:12:17,508][35316] Starting process rollout_proc6
+-[2023-09-19 11:12:17,508][35316] Starting process rollout_proc7
+-[2023-09-19 11:12:19,355][36026] Worker 6 uses CPU cores [24, 25, 26, 27]
+-[2023-09-19 11:12:19,356][36006] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:19,356][36006] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+-[2023-09-19 11:12:19,370][36022] Worker 0 uses CPU cores [0, 1, 2, 3]
+-[2023-09-19 11:12:19,373][36023] Worker 5 uses CPU cores [20, 21, 22, 23]
+-[2023-09-19 11:12:19,378][36006] Num visible devices: 1
+-[2023-09-19 11:12:19,396][36020] Worker 1 uses CPU cores [4, 5, 6, 7]
+-[2023-09-19 11:12:19,404][36021] Worker 2 uses CPU cores [8, 9, 10, 11]
+-[2023-09-19 11:12:19,410][36027] Worker 4 uses CPU cores [16, 17, 18, 19]
+-[2023-09-19 11:12:19,436][36025] Worker 7 uses CPU cores [28, 29, 30, 31]
+-[2023-09-19 11:12:19,436][36006] Starting seed is not provided
+-[2023-09-19 11:12:19,436][36006] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:19,436][36006] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:12:19,437][36006] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:12:19,437][36006] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:12:19,528][36019] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:19,529][36019] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+-[2023-09-19 11:12:19,530][36006] Created Actor Critic model with architecture:
+-[2023-09-19 11:12:19,530][36006] ActorCriticSharedWeights(
++[2023-09-21 15:10:43,177][99566] Saving configuration to ./train_dir/Standup/config.json...
++[2023-09-21 15:10:43,343][99566] Rollout worker 0 uses device cpu
++[2023-09-21 15:10:43,344][99566] Rollout worker 1 uses device cpu
++[2023-09-21 15:10:43,345][99566] Rollout worker 2 uses device cpu
++[2023-09-21 15:10:43,345][99566] Rollout worker 3 uses device cpu
++[2023-09-21 15:10:43,346][99566] Rollout worker 4 uses device cpu
++[2023-09-21 15:10:43,346][99566] Rollout worker 5 uses device cpu
++[2023-09-21 15:10:43,346][99566] Rollout worker 6 uses device cpu
++[2023-09-21 15:10:43,347][99566] Rollout worker 7 uses device cpu
++[2023-09-21 15:10:43,347][99566] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
++[2023-09-21 15:10:43,408][99566] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:43,408][99566] InferenceWorker_p0-w0: min num requests: 1
++[2023-09-21 15:10:43,411][99566] Using GPUs [1] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:43,412][99566] InferenceWorker_p1-w0: min num requests: 1
++[2023-09-21 15:10:43,436][99566] Starting all processes...
++[2023-09-21 15:10:43,437][99566] Starting process learner_proc0
++[2023-09-21 15:10:43,439][99566] Starting process learner_proc1
++[2023-09-21 15:10:43,486][99566] Starting all processes...
++[2023-09-21 15:10:43,493][99566] Starting process inference_proc0-0
++[2023-09-21 15:10:43,493][99566] Starting process inference_proc1-0
++[2023-09-21 15:10:43,494][99566] Starting process rollout_proc0
++[2023-09-21 15:10:43,494][99566] Starting process rollout_proc1
++[2023-09-21 15:10:43,494][99566] Starting process rollout_proc2
++[2023-09-21 15:10:43,495][99566] Starting process rollout_proc3
++[2023-09-21 15:10:43,495][99566] Starting process rollout_proc4
++[2023-09-21 15:10:43,505][99566] Starting process rollout_proc5
++[2023-09-21 15:10:43,508][99566] Starting process rollout_proc6
++[2023-09-21 15:10:43,514][99566] Starting process rollout_proc7
++[2023-09-21 15:10:45,312][101035] Using GPUs [1] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:45,312][101035] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1
++[2023-09-21 15:10:45,328][101117] Using GPUs [1] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:45,328][101117] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1
++[2023-09-21 15:10:45,330][101035] Num visible devices: 1
++[2023-09-21 15:10:45,346][101117] Num visible devices: 1
++[2023-09-21 15:10:45,369][101035] Starting seed is not provided
++[2023-09-21 15:10:45,370][101035] Using GPUs [0] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:45,370][101035] Initializing actor-critic model on device cuda:0
++[2023-09-21 15:10:45,370][101035] RunningMeanStd input shape: (376,)
++[2023-09-21 15:10:45,371][101035] RunningMeanStd input shape: (1,)
++[2023-09-21 15:10:45,373][101122] Worker 4 uses CPU cores [16, 17, 18, 19]
++[2023-09-21 15:10:45,392][101119] Worker 2 uses CPU cores [8, 9, 10, 11]
++[2023-09-21 15:10:45,415][101120] Worker 3 uses CPU cores [12, 13, 14, 15]
++[2023-09-21 15:10:45,415][101121] Worker 5 uses CPU cores [20, 21, 22, 23]
++[2023-09-21 15:10:45,421][101035] Created Actor Critic model with architecture:
++[2023-09-21 15:10:45,421][101035] ActorCriticSharedWeights(
+   (obs_normalizer): ObservationNormalizer(
+     (running_mean_std): RunningMeanStdDictInPlace(
+       (running_mean_std): ModuleDict(
+@@ -71,167 +73,21 @@
+     (distribution_linear): Linear(in_features=64, out_features=17, bias=True)
+   )
+ )
+-[2023-09-19 11:12:19,571][36019] Num visible devices: 1
+-[2023-09-19 11:12:19,598][36024] Worker 3 uses CPU cores [12, 13, 14, 15]
+-[2023-09-19 11:12:20,100][36006] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:12:20,101][36006] No checkpoints found
+-[2023-09-19 11:12:20,101][36006] Did not load from checkpoint, starting from scratch!
+-[2023-09-19 11:12:20,101][36006] Initialized policy 0 weights for model version 0
+-[2023-09-19 11:12:20,103][36006] LearnerWorker_p0 finished initialization!
+-[2023-09-19 11:12:20,103][36006] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:20,715][36019] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:12:20,716][36019] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:12:20,748][35316] Inference worker 0-0 is ready!
+-[2023-09-19 11:12:20,749][35316] All inference workers are ready! Signal rollout workers to start!
+-[2023-09-19 11:12:20,854][36024] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,855][36024] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,857][36025] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,858][36025] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,858][36026] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,858][36021] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,859][36026] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,859][36021] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,872][36027] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,873][36027] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,881][36022] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,882][36022] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,899][36020] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,899][36023] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,900][36023] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,900][36020] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,908][36024] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,910][36026] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,913][36025] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,915][36021] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,926][36027] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,938][36022] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,984][36023] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,986][36020] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:21,016][36026] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,017][36024] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,018][36021] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,021][36025] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,033][36027] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,055][36022] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,144][36023] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,150][36020] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,191][36021] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,191][36024] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,198][36025] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,200][36026] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,204][36027] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,236][36022] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,312][36023] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,320][36020] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,387][36021] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,402][36024] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,408][36027] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,411][36025] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,449][36026] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,456][36022] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,516][36023] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,526][36020] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,639][36021] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,667][36024] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,672][36027] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,679][36025] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,690][36026] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,727][36022] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,766][36020] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,777][36023] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,966][36021] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:21,974][36027] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:21,978][36024] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:21,991][36025] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:22,000][36026] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:22,066][36022] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:22,100][36020] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:22,150][36023] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:23,541][35316] 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)
+-[2023-09-19 11:12:28,541][35316] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 16384. Throughput: 0: 2365.6. Samples: 11828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:12:28,544][36006] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000032_16384.pth...
+-[2023-09-19 11:12:29,287][35316] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 35316], exiting...
+-[2023-09-19 11:12:29,288][35316] Runner profile tree view:
+-main_loop: 11.8008
+-[2023-09-19 11:12:29,288][35316] Collected {0: 20480}, FPS: 1735.5
+-[2023-09-19 11:12:29,288][36006] Stopping Batcher_0...
+-[2023-09-19 11:12:29,289][36026] Stopping RolloutWorker_w6...
+-[2023-09-19 11:12:29,290][36026] Loop rollout_proc6_evt_loop terminating...
+-[2023-09-19 11:12:29,289][36006] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:12:29,290][36027] Stopping RolloutWorker_w4...
+-[2023-09-19 11:12:29,290][36027] Loop rollout_proc4_evt_loop terminating...
+-[2023-09-19 11:12:29,290][36020] Stopping RolloutWorker_w1...
+-[2023-09-19 11:12:29,290][36023] Stopping RolloutWorker_w5...
+-[2023-09-19 11:12:29,290][36020] Loop rollout_proc1_evt_loop terminating...
+-[2023-09-19 11:12:29,290][36023] Loop rollout_proc5_evt_loop terminating...
+-[2023-09-19 11:12:29,290][36006] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000040_20480.pth...
+-[2023-09-19 11:12:29,291][36022] Stopping RolloutWorker_w0...
+-[2023-09-19 11:12:29,291][36022] Loop rollout_proc0_evt_loop terminating...
+-[2023-09-19 11:12:29,291][36024] Stopping RolloutWorker_w3...
+-[2023-09-19 11:12:29,292][36024] Loop rollout_proc3_evt_loop terminating...
+-[2023-09-19 11:12:29,292][36021] Stopping RolloutWorker_w2...
+-[2023-09-19 11:12:29,292][36021] Loop rollout_proc2_evt_loop terminating...
+-[2023-09-19 11:12:29,294][36025] Stopping RolloutWorker_w7...
+-[2023-09-19 11:12:29,295][36025] Loop rollout_proc7_evt_loop terminating...
+-[2023-09-19 11:12:29,299][36006] Stopping LearnerWorker_p0...
+-[2023-09-19 11:12:29,300][36006] Loop learner_proc0_evt_loop terminating...
+-[2023-09-19 11:12:29,303][36019] Weights refcount: 2 0
+-[2023-09-19 11:12:29,304][36019] Stopping InferenceWorker_p0-w0...
+-[2023-09-19 11:12:29,304][36019] Loop inference_proc0-0_evt_loop terminating...
+-[2023-09-19 11:13:18,923][40303] Saving configuration to ./train_dir/Standup/config.json...
+-[2023-09-19 11:13:18,925][40303] Rollout worker 0 uses device cpu
+-[2023-09-19 11:13:18,926][40303] Rollout worker 1 uses device cpu
+-[2023-09-19 11:13:18,926][40303] Rollout worker 2 uses device cpu
+-[2023-09-19 11:13:18,927][40303] Rollout worker 3 uses device cpu
+-[2023-09-19 11:13:18,928][40303] Rollout worker 4 uses device cpu
+-[2023-09-19 11:13:18,928][40303] Rollout worker 5 uses device cpu
+-[2023-09-19 11:13:18,929][40303] Rollout worker 6 uses device cpu
+-[2023-09-19 11:13:18,929][40303] Rollout worker 7 uses device cpu
+-[2023-09-19 11:13:18,930][40303] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
+-[2023-09-19 11:13:18,986][40303] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:18,986][40303] InferenceWorker_p0-w0: min num requests: 1
+-[2023-09-19 11:13:18,990][40303] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:18,990][40303] InferenceWorker_p1-w0: min num requests: 1
+-[2023-09-19 11:13:19,015][40303] Starting all processes...
+-[2023-09-19 11:13:19,015][40303] Starting process learner_proc0
+-[2023-09-19 11:13:19,018][40303] Starting process learner_proc1
+-[2023-09-19 11:13:19,065][40303] Starting all processes...
+-[2023-09-19 11:13:19,071][40303] Starting process inference_proc0-0
+-[2023-09-19 11:13:19,071][40303] Starting process inference_proc1-0
+-[2023-09-19 11:13:19,071][40303] Starting process rollout_proc0
+-[2023-09-19 11:13:19,071][40303] Starting process rollout_proc1
+-[2023-09-19 11:13:19,072][40303] Starting process rollout_proc2
+-[2023-09-19 11:13:19,072][40303] Starting process rollout_proc3
+-[2023-09-19 11:13:19,073][40303] Starting process rollout_proc4
+-[2023-09-19 11:13:19,074][40303] Starting process rollout_proc5
+-[2023-09-19 11:13:19,080][40303] Starting process rollout_proc6
+-[2023-09-19 11:13:19,081][40303] Starting process rollout_proc7
+-[2023-09-19 11:13:21,055][41278] Worker 2 uses CPU cores [8, 9, 10, 11]
+-[2023-09-19 11:13:21,063][41246] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:21,063][41246] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+-[2023-09-19 11:13:21,068][41284] Worker 3 uses CPU cores [12, 13, 14, 15]
+-[2023-09-19 11:13:21,080][41271] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:21,080][41271] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1
+-[2023-09-19 11:13:21,083][41246] Num visible devices: 1
+-[2023-09-19 11:13:21,088][41292] Worker 5 uses CPU cores [20, 21, 22, 23]
+-[2023-09-19 11:13:21,100][41271] Num visible devices: 1
+-[2023-09-19 11:13:21,157][41272] Worker 0 uses CPU cores [0, 1, 2, 3]
+-[2023-09-19 11:13:21,187][41276] Worker 1 uses CPU cores [4, 5, 6, 7]
+-[2023-09-19 11:13:21,291][41291] Worker 7 uses CPU cores [28, 29, 30, 31]
+-[2023-09-19 11:13:21,319][41290] Worker 6 uses CPU cores [24, 25, 26, 27]
+-[2023-09-19 11:13:21,326][41287] Worker 4 uses CPU cores [16, 17, 18, 19]
+-[2023-09-19 11:13:21,373][41187] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:21,373][41187] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+-[2023-09-19 11:13:21,391][41187] Num visible devices: 1
+-[2023-09-19 11:13:21,412][41187] Starting seed is not provided
+-[2023-09-19 11:13:21,412][41187] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:21,412][41187] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:13:21,413][41187] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:13:21,413][41187] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:13:21,450][41188] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:21,450][41188] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1
+-[2023-09-19 11:13:21,461][41187] Created Actor Critic model with architecture:
+-[2023-09-19 11:13:21,462][41187] ActorCriticSharedWeights(
++[2023-09-21 15:10:45,459][101034] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:45,459][101034] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
++[2023-09-21 15:10:45,470][101124] Worker 7 uses CPU cores [28, 29, 30, 31]
++[2023-09-21 15:10:45,484][101123] Worker 6 uses CPU cores [24, 25, 26, 27]
++[2023-09-21 15:10:45,490][101034] Num visible devices: 1
++[2023-09-21 15:10:45,528][101034] Starting seed is not provided
++[2023-09-21 15:10:45,528][101034] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:45,528][101034] Initializing actor-critic model on device cuda:0
++[2023-09-21 15:10:45,529][101034] RunningMeanStd input shape: (376,)
++[2023-09-21 15:10:45,530][101034] RunningMeanStd input shape: (1,)
++[2023-09-21 15:10:45,552][101115] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:45,552][101115] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
++[2023-09-21 15:10:45,570][101115] Num visible devices: 1
++[2023-09-21 15:10:45,580][101034] Created Actor Critic model with architecture:
++[2023-09-21 15:10:45,581][101034] ActorCriticSharedWeights(
+   (obs_normalizer): ObservationNormalizer(
+     (running_mean_std): RunningMeanStdDictInPlace(
+       (running_mean_std): ModuleDict(
+@@ -262,2573 +118,537 @@ main_loop: 11.8008
+     (distribution_linear): Linear(in_features=64, out_features=17, bias=True)
+   )
+ )
+-[2023-09-19 11:13:21,478][41188] Num visible devices: 1
+-[2023-09-19 11:13:21,500][41188] Starting seed is not provided
+-[2023-09-19 11:13:21,500][41188] Using GPUs [0] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:21,500][41188] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:13:21,501][41188] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:13:21,501][41188] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:13:21,548][41188] Created Actor Critic model with architecture:
+-[2023-09-19 11:13:21,548][41188] 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=17, bias=True)
+-  )
+-)
+-[2023-09-19 11:13:22,080][41187] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:13:22,081][41187] Loading state from checkpoint ./train_dir/Standup/checkpoint_p0/checkpoint_000000040_20480.pth...
+-[2023-09-19 11:13:22,087][41187] Loading model from checkpoint
+-[2023-09-19 11:13:22,089][41187] Loaded experiment state at self.train_step=40, self.env_steps=20480
+-[2023-09-19 11:13:22,090][41187] Initialized policy 0 weights for model version 40
+-[2023-09-19 11:13:22,091][41187] LearnerWorker_p0 finished initialization!
+-[2023-09-19 11:13:22,092][41187] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:22,122][41188] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:13:22,123][41188] No checkpoints found
+-[2023-09-19 11:13:22,123][41188] Did not load from checkpoint, starting from scratch!
+-[2023-09-19 11:13:22,124][41188] Initialized policy 1 weights for model version 0
+-[2023-09-19 11:13:22,142][41188] LearnerWorker_p1 finished initialization!
+-[2023-09-19 11:13:22,142][41188] Using GPUs [0] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:22,704][41246] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:13:22,705][41246] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:13:22,718][41271] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:13:22,718][41271] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:13:22,737][40303] Inference worker 0-0 is ready!
+-[2023-09-19 11:13:22,750][40303] Inference worker 1-0 is ready!
+-[2023-09-19 11:13:22,751][40303] All inference workers are ready! Signal rollout workers to start!
+-[2023-09-19 11:13:22,845][41278] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,846][41278] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,852][41290] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,853][41290] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,872][41287] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,873][41287] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,886][41276] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,885][41272] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,886][41276] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,886][41272] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,893][41292] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,894][41292] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,899][41278] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,905][41291] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,905][41284] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,907][41284] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,907][41291] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,907][41290] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,939][41276] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,944][41287] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,957][41292] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,974][41272] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,990][41291] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:23,000][41284] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:23,003][41278] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,051][41290] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,056][41287] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,057][41292] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,102][41276] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,147][41272] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,170][41291] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,177][41278] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,180][41284] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,229][41292] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,230][41287] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,248][41290] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,374][41276] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,378][41278] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,426][41287] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,428][41272] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,429][41292] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,433][41291] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,434][41284] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,481][41290] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,626][41291] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,675][41278] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,680][41284] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,685][41292] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,686][41287] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,711][41276] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,748][41272] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,770][41290] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,868][41291] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,948][41284] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,986][41278] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:23,993][41292] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:23,995][41287] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,071][41290] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,113][41276] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:24,140][41272] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:24,170][41291] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,250][41284] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,433][41276] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,471][41272] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:25,197][40303] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 20480. Throughput: 0: nan, 1: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+-[2023-09-19 11:13:30,198][40303] Fps is (10 sec: 3276.7, 60 sec: 3276.7, 300 sec: 3276.7). Total num frames: 36864. Throughput: 0: 1638.4, 1: 1638.4. Samples: 16384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:13:30,200][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000056_28672.pth...
+-[2023-09-19 11:13:30,201][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000016_8192.pth...
+-[2023-09-19 11:13:30,211][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000032_16384.pth
+-[2023-09-19 11:13:35,197][40303] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 4915.2). Total num frames: 69632. Throughput: 0: 2621.6, 1: 2627.4. Samples: 52490. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:13:35,198][40303] Avg episode reward: [(0, '31454.083'), (1, '27038.960')]
+-[2023-09-19 11:13:38,652][41271] Updated weights for policy 1, policy_version 80 (0.0016)
+-[2023-09-19 11:13:38,652][41246] Updated weights for policy 0, policy_version 120 (0.0015)
+-[2023-09-19 11:13:38,973][40303] Heartbeat connected on Batcher_0
+-[2023-09-19 11:13:38,976][40303] Heartbeat connected on LearnerWorker_p0
+-[2023-09-19 11:13:38,979][40303] Heartbeat connected on Batcher_1
+-[2023-09-19 11:13:38,982][40303] Heartbeat connected on LearnerWorker_p1
+-[2023-09-19 11:13:38,989][40303] Heartbeat connected on InferenceWorker_p0-w0
+-[2023-09-19 11:13:38,992][40303] Heartbeat connected on InferenceWorker_p1-w0
+-[2023-09-19 11:13:38,998][40303] Heartbeat connected on RolloutWorker_w0
+-[2023-09-19 11:13:39,001][40303] Heartbeat connected on RolloutWorker_w1
+-[2023-09-19 11:13:39,004][40303] Heartbeat connected on RolloutWorker_w2
+-[2023-09-19 11:13:39,006][40303] Heartbeat connected on RolloutWorker_w3
+-[2023-09-19 11:13:39,008][40303] Heartbeat connected on RolloutWorker_w4
+-[2023-09-19 11:13:39,014][40303] Heartbeat connected on RolloutWorker_w5
+-[2023-09-19 11:13:39,018][40303] Heartbeat connected on RolloutWorker_w7
+-[2023-09-19 11:13:39,018][40303] Heartbeat connected on RolloutWorker_w6
+-[2023-09-19 11:13:40,198][40303] Fps is (10 sec: 7372.8, 60 sec: 6007.4, 300 sec: 6007.4). Total num frames: 110592. Throughput: 0: 2508.5, 1: 2511.7. Samples: 75304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:13:40,199][40303] Avg episode reward: [(0, '34634.079'), (1, '30037.595')]
+-[2023-09-19 11:13:45,197][40303] Fps is (10 sec: 7372.8, 60 sec: 6144.0, 300 sec: 6144.0). Total num frames: 143360. Throughput: 0: 2989.8, 1: 2992.6. Samples: 119648. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:13:45,198][40303] Avg episode reward: [(0, '43292.280'), (1, '42584.158')]
+-[2023-09-19 11:13:45,201][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000160_81920.pth...
+-[2023-09-19 11:13:45,201][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000120_61440.pth...
+-[2023-09-19 11:13:45,207][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000040_20480.pth
+-[2023-09-19 11:13:49,800][41271] Updated weights for policy 1, policy_version 160 (0.0015)
+-[2023-09-19 11:13:49,801][41246] Updated weights for policy 0, policy_version 200 (0.0014)
+-[2023-09-19 11:13:50,198][40303] Fps is (10 sec: 7372.8, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 184320. Throughput: 0: 3276.9, 1: 3276.9. Samples: 163844. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:13:50,199][40303] Avg episode reward: [(0, '43292.280'), (1, '44801.351')]
+-[2023-09-19 11:13:50,200][41187] Saving new best policy, reward=43292.280!
+-[2023-09-19 11:13:55,197][40303] Fps is (10 sec: 7372.8, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 217088. Throughput: 0: 3089.5, 1: 3091.3. Samples: 185422. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:13:55,198][40303] Avg episode reward: [(0, '50284.168'), (1, '51051.259')]
+-[2023-09-19 11:13:55,199][41187] Saving new best policy, reward=50284.168!
+-[2023-09-19 11:14:00,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 249856. Throughput: 0: 3196.1, 1: 3197.6. Samples: 223782. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:14:00,199][40303] Avg episode reward: [(0, '53046.991'), (1, '53883.351')]
+-[2023-09-19 11:14:00,208][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000264_135168.pth...
+-[2023-09-19 11:14:00,208][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000224_114688.pth...
+-[2023-09-19 11:14:00,217][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000016_8192.pth
+-[2023-09-19 11:14:00,217][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000056_28672.pth
+-[2023-09-19 11:14:00,218][41188] Saving new best policy, reward=53883.351!
+-[2023-09-19 11:14:00,218][41187] Saving new best policy, reward=53046.991!
+-[2023-09-19 11:14:01,592][41271] Updated weights for policy 1, policy_version 240 (0.0012)
+-[2023-09-19 11:14:01,592][41246] Updated weights for policy 0, policy_version 280 (0.0013)
+-[2023-09-19 11:14:05,198][40303] Fps is (10 sec: 7372.7, 60 sec: 6758.4, 300 sec: 6758.4). Total num frames: 290816. Throughput: 0: 3357.1, 1: 3358.6. Samples: 268630. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:14:05,199][40303] Avg episode reward: [(0, '62279.408'), (1, '63904.672')]
+-[2023-09-19 11:14:05,200][41187] Saving new best policy, reward=62279.408!
+-[2023-09-19 11:14:05,200][41188] Saving new best policy, reward=63904.672!
+-[2023-09-19 11:14:10,197][40303] Fps is (10 sec: 7372.9, 60 sec: 6735.6, 300 sec: 6735.6). Total num frames: 323584. Throughput: 0: 3232.0, 1: 3233.1. Samples: 290930. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:10,198][40303] Avg episode reward: [(0, '66478.184'), (1, '70755.397')]
+-[2023-09-19 11:14:10,199][41188] Saving new best policy, reward=70755.397!
+-[2023-09-19 11:14:10,199][41187] Saving new best policy, reward=66478.184!
+-[2023-09-19 11:14:12,751][41271] Updated weights for policy 1, policy_version 320 (0.0010)
+-[2023-09-19 11:14:12,752][41246] Updated weights for policy 0, policy_version 360 (0.0015)
+-[2023-09-19 11:14:15,197][40303] Fps is (10 sec: 7372.9, 60 sec: 6881.3, 300 sec: 6881.3). Total num frames: 364544. Throughput: 0: 3545.5, 1: 3546.1. Samples: 335508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:15,198][40303] Avg episode reward: [(0, '69427.017'), (1, '72462.244')]
+-[2023-09-19 11:14:15,204][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000376_192512.pth...
+-[2023-09-19 11:14:15,204][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000336_172032.pth...
+-[2023-09-19 11:14:15,208][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000160_81920.pth
+-[2023-09-19 11:14:15,209][41187] Saving new best policy, reward=69427.017!
+-[2023-09-19 11:14:15,211][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000120_61440.pth
+-[2023-09-19 11:14:15,211][41188] Saving new best policy, reward=72462.244!
+-[2023-09-19 11:14:20,197][40303] Fps is (10 sec: 7372.9, 60 sec: 6851.5, 300 sec: 6851.5). Total num frames: 397312. Throughput: 0: 3635.0, 1: 3635.0. Samples: 379638. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:20,198][40303] Avg episode reward: [(0, '73711.169'), (1, '77171.232')]
+-[2023-09-19 11:14:20,199][41187] Saving new best policy, reward=73711.169!
+-[2023-09-19 11:14:20,199][41188] Saving new best policy, reward=77171.232!
+-[2023-09-19 11:14:23,933][41246] Updated weights for policy 0, policy_version 440 (0.0013)
+-[2023-09-19 11:14:23,934][41271] Updated weights for policy 1, policy_version 400 (0.0011)
+-[2023-09-19 11:14:25,197][40303] Fps is (10 sec: 6553.6, 60 sec: 6826.7, 300 sec: 6826.7). Total num frames: 430080. Throughput: 0: 3632.2, 1: 3632.4. Samples: 402210. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:25,198][40303] Avg episode reward: [(0, '73688.883'), (1, '77171.232')]
+-[2023-09-19 11:14:30,198][40303] Fps is (10 sec: 7372.7, 60 sec: 7236.3, 300 sec: 6931.7). Total num frames: 471040. Throughput: 0: 3606.1, 1: 3606.2. Samples: 444202. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:30,198][40303] Avg episode reward: [(0, '76128.666'), (1, '83391.647')]
+-[2023-09-19 11:14:30,204][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000480_245760.pth...
+-[2023-09-19 11:14:30,205][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000440_225280.pth...
+-[2023-09-19 11:14:30,211][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000264_135168.pth
+-[2023-09-19 11:14:30,212][41187] Saving new best policy, reward=76128.666!
+-[2023-09-19 11:14:30,213][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000224_114688.pth
+-[2023-09-19 11:14:30,214][41188] Saving new best policy, reward=83391.647!
+-[2023-09-19 11:14:35,005][41271] Updated weights for policy 1, policy_version 480 (0.0015)
+-[2023-09-19 11:14:35,006][41246] Updated weights for policy 0, policy_version 520 (0.0013)
+-[2023-09-19 11:14:35,198][40303] Fps is (10 sec: 8191.9, 60 sec: 7372.8, 300 sec: 7021.7). Total num frames: 512000. Throughput: 0: 3626.8, 1: 3628.0. Samples: 490312. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:14:35,199][40303] Avg episode reward: [(0, '76490.813'), (1, '86333.937')]
+-[2023-09-19 11:14:35,200][41187] Saving new best policy, reward=76490.813!
+-[2023-09-19 11:14:35,200][41188] Saving new best policy, reward=86333.937!
+-[2023-09-19 11:14:40,198][40303] Fps is (10 sec: 7372.6, 60 sec: 7236.2, 300 sec: 6990.5). Total num frames: 544768. Throughput: 0: 3630.3, 1: 3630.3. Samples: 512152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:40,199][40303] Avg episode reward: [(0, '78215.963'), (1, '88825.825')]
+-[2023-09-19 11:14:40,201][41187] Saving new best policy, reward=78215.963!
+-[2023-09-19 11:14:40,201][41188] Saving new best policy, reward=88825.825!
+-[2023-09-19 11:14:45,197][40303] Fps is (10 sec: 7372.9, 60 sec: 7372.8, 300 sec: 7065.6). Total num frames: 585728. Throughput: 0: 3707.3, 1: 3707.2. Samples: 557434. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:14:45,198][40303] Avg episode reward: [(0, '80179.767'), (1, '93784.048')]
+-[2023-09-19 11:14:45,208][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000552_282624.pth...
+-[2023-09-19 11:14:45,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000592_303104.pth...
+-[2023-09-19 11:14:45,216][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000336_172032.pth
+-[2023-09-19 11:14:45,216][41188] Saving new best policy, reward=93784.048!
+-[2023-09-19 11:14:45,219][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000376_192512.pth
+-[2023-09-19 11:14:45,220][41187] Saving new best policy, reward=80179.767!
+-[2023-09-19 11:14:46,154][41271] Updated weights for policy 1, policy_version 560 (0.0013)
+-[2023-09-19 11:14:46,154][41246] Updated weights for policy 0, policy_version 600 (0.0015)
+-[2023-09-19 11:14:50,198][40303] Fps is (10 sec: 7372.9, 60 sec: 7236.3, 300 sec: 7035.5). Total num frames: 618496. Throughput: 0: 3695.9, 1: 3695.8. Samples: 601256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:50,199][40303] Avg episode reward: [(0, '81224.789'), (1, '95410.430')]
+-[2023-09-19 11:14:50,200][41187] Saving new best policy, reward=81224.789!
+-[2023-09-19 11:14:50,200][41188] Saving new best policy, reward=95410.430!
+-[2023-09-19 11:14:55,215][40303] Fps is (10 sec: 7359.6, 60 sec: 7370.6, 300 sec: 7098.3). Total num frames: 659456. Throughput: 0: 3656.8, 1: 3656.9. Samples: 620178. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:14:55,218][40303] Avg episode reward: [(0, '81804.261'), (1, '100729.706')]
+-[2023-09-19 11:14:55,219][41187] Saving new best policy, reward=81804.261!
+-[2023-09-19 11:14:55,219][41188] Saving new best policy, reward=100729.706!
+-[2023-09-19 11:14:57,288][41246] Updated weights for policy 0, policy_version 680 (0.0016)
+-[2023-09-19 11:14:57,288][41271] Updated weights for policy 1, policy_version 640 (0.0013)
+-[2023-09-19 11:15:00,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7071.0). Total num frames: 692224. Throughput: 0: 3672.5, 1: 3673.2. Samples: 666064. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:15:00,198][40303] Avg episode reward: [(0, '81842.550'), (1, '102461.265')]
+-[2023-09-19 11:15:00,204][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000656_335872.pth...
+-[2023-09-19 11:15:00,204][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000696_356352.pth...
+-[2023-09-19 11:15:00,208][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000440_225280.pth
+-[2023-09-19 11:15:00,208][41188] Saving new best policy, reward=102461.265!
+-[2023-09-19 11:15:00,211][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000480_245760.pth
+-[2023-09-19 11:15:00,211][41187] Saving new best policy, reward=81842.550!
+-[2023-09-19 11:15:05,198][40303] Fps is (10 sec: 5744.7, 60 sec: 7099.7, 300 sec: 6963.2). Total num frames: 716800. Throughput: 0: 3578.5, 1: 3578.2. Samples: 701690. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:05,199][40303] Avg episode reward: [(0, '82742.948'), (1, '108945.356')]
+-[2023-09-19 11:15:05,200][41187] Saving new best policy, reward=82742.948!
+-[2023-09-19 11:15:05,200][41188] Saving new best policy, reward=108945.356!
+-[2023-09-19 11:15:09,873][41271] Updated weights for policy 1, policy_version 720 (0.0015)
+-[2023-09-19 11:15:09,873][41246] Updated weights for policy 0, policy_version 760 (0.0015)
+-[2023-09-19 11:15:10,198][40303] Fps is (10 sec: 6553.6, 60 sec: 7236.3, 300 sec: 7021.7). Total num frames: 757760. Throughput: 0: 3542.3, 1: 3541.1. Samples: 720964. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:15:10,199][40303] Avg episode reward: [(0, '83013.951'), (1, '110482.262')]
+-[2023-09-19 11:15:10,200][41187] Saving new best policy, reward=83013.951!
+-[2023-09-19 11:15:10,200][41188] Saving new best policy, reward=110482.262!
+-[2023-09-19 11:15:15,198][40303] Fps is (10 sec: 7372.7, 60 sec: 7099.7, 300 sec: 7000.4). Total num frames: 790528. Throughput: 0: 3537.8, 1: 3537.8. Samples: 762602. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:15:15,199][40303] Avg episode reward: [(0, '84790.627'), (1, '117040.476')]
+-[2023-09-19 11:15:15,208][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000792_405504.pth...
+-[2023-09-19 11:15:15,209][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000752_385024.pth...
+-[2023-09-19 11:15:15,215][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000552_282624.pth
+-[2023-09-19 11:15:15,216][41188] Saving new best policy, reward=117040.476!
+-[2023-09-19 11:15:15,218][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000592_303104.pth
+-[2023-09-19 11:15:15,219][41187] Saving new best policy, reward=84790.627!
+-[2023-09-19 11:15:20,197][40303] Fps is (10 sec: 6553.7, 60 sec: 7099.7, 300 sec: 6981.0). Total num frames: 823296. Throughput: 0: 3525.8, 1: 3526.0. Samples: 807640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:20,198][40303] Avg episode reward: [(0, '86690.838'), (1, '119342.411')]
+-[2023-09-19 11:15:20,199][41188] Saving new best policy, reward=119342.411!
+-[2023-09-19 11:15:20,199][41187] Saving new best policy, reward=86690.838!
+-[2023-09-19 11:15:21,652][41271] Updated weights for policy 1, policy_version 800 (0.0011)
+-[2023-09-19 11:15:21,653][41246] Updated weights for policy 0, policy_version 840 (0.0015)
+-[2023-09-19 11:15:25,198][40303] Fps is (10 sec: 7372.9, 60 sec: 7236.2, 300 sec: 7031.5). Total num frames: 864256. Throughput: 0: 3502.0, 1: 3501.0. Samples: 827284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:25,199][40303] Avg episode reward: [(0, '90539.601'), (1, '125734.908')]
+-[2023-09-19 11:15:25,200][41187] Saving new best policy, reward=90539.601!
+-[2023-09-19 11:15:25,200][41188] Saving new best policy, reward=125734.908!
+-[2023-09-19 11:15:30,198][40303] Fps is (10 sec: 8191.9, 60 sec: 7236.3, 300 sec: 7077.9). Total num frames: 905216. Throughput: 0: 3517.5, 1: 3518.0. Samples: 874032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:30,198][40303] Avg episode reward: [(0, '92852.762'), (1, '132358.210')]
+-[2023-09-19 11:15:30,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000904_462848.pth...
+-[2023-09-19 11:15:30,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000864_442368.pth...
+-[2023-09-19 11:15:30,213][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000656_335872.pth
+-[2023-09-19 11:15:30,214][41188] Saving new best policy, reward=132358.210!
+-[2023-09-19 11:15:30,216][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000696_356352.pth
+-[2023-09-19 11:15:30,217][41187] Saving new best policy, reward=92852.762!
+-[2023-09-19 11:15:32,850][41271] Updated weights for policy 1, policy_version 880 (0.0013)
+-[2023-09-19 11:15:32,851][41246] Updated weights for policy 0, policy_version 920 (0.0013)
+-[2023-09-19 11:15:35,197][40303] Fps is (10 sec: 7372.9, 60 sec: 7099.7, 300 sec: 7057.7). Total num frames: 937984. Throughput: 0: 3497.4, 1: 3497.6. Samples: 916030. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:35,198][40303] Avg episode reward: [(0, '96297.528'), (1, '134666.372')]
+-[2023-09-19 11:15:35,199][41187] Saving new best policy, reward=96297.528!
+-[2023-09-19 11:15:35,200][41188] Saving new best policy, reward=134666.372!
+-[2023-09-19 11:15:40,198][40303] Fps is (10 sec: 6553.5, 60 sec: 7099.7, 300 sec: 7039.0). Total num frames: 970752. Throughput: 0: 3537.6, 1: 3537.8. Samples: 938444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:40,199][40303] Avg episode reward: [(0, '101172.898'), (1, '137965.048')]
+-[2023-09-19 11:15:40,200][41187] Saving new best policy, reward=101172.898!
+-[2023-09-19 11:15:40,200][41188] Saving new best policy, reward=137965.048!
+-[2023-09-19 11:15:44,038][41246] Updated weights for policy 0, policy_version 1000 (0.0014)
+-[2023-09-19 11:15:44,038][41271] Updated weights for policy 1, policy_version 960 (0.0014)
+-[2023-09-19 11:15:45,197][40303] Fps is (10 sec: 6553.7, 60 sec: 6963.2, 300 sec: 7021.7). Total num frames: 1003520. Throughput: 0: 3519.5, 1: 3518.3. Samples: 982764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:45,198][40303] Avg episode reward: [(0, '103392.205'), (1, '137965.048')]
+-[2023-09-19 11:15:45,205][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000968_495616.pth...
+-[2023-09-19 11:15:45,208][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000752_385024.pth
+-[2023-09-19 11:15:45,213][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001008_516096.pth...
+-[2023-09-19 11:15:45,217][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000792_405504.pth
+-[2023-09-19 11:15:45,218][41187] Saving new best policy, reward=103392.205!
+-[2023-09-19 11:15:50,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7062.1). Total num frames: 1044480. Throughput: 0: 3604.8, 1: 3604.9. Samples: 1026124. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:15:50,199][40303] Avg episode reward: [(0, '112090.239'), (1, '141479.122')]
+-[2023-09-19 11:15:50,200][41187] Saving new best policy, reward=112090.239!
+-[2023-09-19 11:15:50,200][41188] Saving new best policy, reward=141479.122!
+-[2023-09-19 11:15:55,198][40303] Fps is (10 sec: 7372.6, 60 sec: 6965.3, 300 sec: 7045.1). Total num frames: 1077248. Throughput: 0: 3640.0, 1: 3640.1. Samples: 1048568. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:15:55,199][40303] Avg episode reward: [(0, '115037.292'), (1, '141360.147')]
+-[2023-09-19 11:15:55,200][41187] Saving new best policy, reward=115037.292!
+-[2023-09-19 11:15:55,356][41271] Updated weights for policy 1, policy_version 1040 (0.0016)
+-[2023-09-19 11:15:55,356][41246] Updated weights for policy 0, policy_version 1080 (0.0011)
+-[2023-09-19 11:16:00,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7082.1). Total num frames: 1118208. Throughput: 0: 3634.6, 1: 3634.6. Samples: 1089716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:16:00,199][40303] Avg episode reward: [(0, '121696.345'), (1, '143516.477')]
+-[2023-09-19 11:16:00,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001112_569344.pth...
+-[2023-09-19 11:16:00,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001072_548864.pth...
+-[2023-09-19 11:16:00,213][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000904_462848.pth
+-[2023-09-19 11:16:00,214][41187] Saving new best policy, reward=121696.345!
+-[2023-09-19 11:16:00,218][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000864_442368.pth
+-[2023-09-19 11:16:00,218][41188] Saving new best policy, reward=143516.477!
+-[2023-09-19 11:16:05,198][40303] Fps is (10 sec: 8192.0, 60 sec: 7372.8, 300 sec: 7116.8). Total num frames: 1159168. Throughput: 0: 3656.8, 1: 3657.0. Samples: 1136764. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:16:05,199][40303] Avg episode reward: [(0, '126501.030'), (1, '144413.674')]
+-[2023-09-19 11:16:05,200][41187] Saving new best policy, reward=126501.030!
+-[2023-09-19 11:16:05,200][41188] Saving new best policy, reward=144413.674!
+-[2023-09-19 11:16:06,100][41271] Updated weights for policy 1, policy_version 1120 (0.0013)
+-[2023-09-19 11:16:06,100][41246] Updated weights for policy 0, policy_version 1160 (0.0016)
+-[2023-09-19 11:16:10,197][40303] Fps is (10 sec: 7372.9, 60 sec: 7236.3, 300 sec: 7099.7). Total num frames: 1191936. Throughput: 0: 3691.9, 1: 3692.5. Samples: 1159578. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:16:10,198][40303] Avg episode reward: [(0, '132111.068'), (1, '146024.408')]
+-[2023-09-19 11:16:10,199][41187] Saving new best policy, reward=132111.068!
+-[2023-09-19 11:16:10,200][41188] Saving new best policy, reward=146024.408!
+-[2023-09-19 11:16:15,198][40303] Fps is (10 sec: 5734.4, 60 sec: 7099.7, 300 sec: 7035.5). Total num frames: 1216512. Throughput: 0: 3566.4, 1: 3565.5. Samples: 1194970. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:16:15,198][40303] Avg episode reward: [(0, '135452.407'), (1, '145133.020')]
+-[2023-09-19 11:16:15,205][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001208_618496.pth...
+-[2023-09-19 11:16:15,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001168_598016.pth...
+-[2023-09-19 11:16:15,217][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000968_495616.pth
+-[2023-09-19 11:16:15,218][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001008_516096.pth
+-[2023-09-19 11:16:15,218][41187] Saving new best policy, reward=135452.407!
+-[2023-09-19 11:16:19,680][41271] Updated weights for policy 1, policy_version 1200 (0.0013)
+-[2023-09-19 11:16:19,680][41246] Updated weights for policy 0, policy_version 1240 (0.0011)
+-[2023-09-19 11:16:20,198][40303] Fps is (10 sec: 5734.3, 60 sec: 7099.7, 300 sec: 7021.7). Total num frames: 1249280. Throughput: 0: 3480.7, 1: 3480.4. Samples: 1229280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:16:20,199][40303] Avg episode reward: [(0, '138970.413'), (1, '144367.334')]
+-[2023-09-19 11:16:20,200][41187] Saving new best policy, reward=138970.413!
+-[2023-09-19 11:16:25,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7054.2). Total num frames: 1290240. Throughput: 0: 3490.3, 1: 3490.3. Samples: 1252572. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:16:25,199][40303] Avg episode reward: [(0, '138954.797'), (1, '143024.613')]
+-[2023-09-19 11:16:30,198][40303] Fps is (10 sec: 7372.7, 60 sec: 6963.2, 300 sec: 7040.7). Total num frames: 1323008. Throughput: 0: 3514.6, 1: 3515.8. Samples: 1299130. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:16:30,199][40303] Avg episode reward: [(0, '138602.655'), (1, '141826.181')]
+-[2023-09-19 11:16:30,206][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001312_671744.pth...
+-[2023-09-19 11:16:30,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001272_651264.pth...
+-[2023-09-19 11:16:30,216][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001112_569344.pth
+-[2023-09-19 11:16:30,216][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001072_548864.pth
+-[2023-09-19 11:16:30,719][41246] Updated weights for policy 0, policy_version 1320 (0.0010)
+-[2023-09-19 11:16:30,720][41271] Updated weights for policy 1, policy_version 1280 (0.0015)
+-[2023-09-19 11:16:35,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6963.2, 300 sec: 7027.9). Total num frames: 1355776. Throughput: 0: 3463.6, 1: 3463.8. Samples: 1337854. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:16:35,199][40303] Avg episode reward: [(0, '139704.889'), (1, '143172.712')]
+-[2023-09-19 11:16:35,200][41187] Saving new best policy, reward=139704.889!
+-[2023-09-19 11:16:40,197][40303] Fps is (10 sec: 6553.8, 60 sec: 6963.2, 300 sec: 7015.7). Total num frames: 1388544. Throughput: 0: 3470.0, 1: 3470.8. Samples: 1360900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:16:40,198][40303] Avg episode reward: [(0, '140044.752'), (1, '143172.712')]
+-[2023-09-19 11:16:40,199][41187] Saving new best policy, reward=140044.752!
+-[2023-09-19 11:16:42,534][41246] Updated weights for policy 0, policy_version 1400 (0.0015)
+-[2023-09-19 11:16:42,534][41271] Updated weights for policy 1, policy_version 1360 (0.0013)
+-[2023-09-19 11:16:45,198][40303] Fps is (10 sec: 7372.7, 60 sec: 7099.7, 300 sec: 7045.1). Total num frames: 1429504. Throughput: 0: 3467.3, 1: 3466.8. Samples: 1401752. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:16:45,199][40303] Avg episode reward: [(0, '142593.411'), (1, '143339.303')]
+-[2023-09-19 11:16:45,209][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001416_724992.pth...
+-[2023-09-19 11:16:45,211][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001376_704512.pth...
+-[2023-09-19 11:16:45,219][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001208_618496.pth
+-[2023-09-19 11:16:45,220][41187] Saving new best policy, reward=142593.411!
+-[2023-09-19 11:16:45,221][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001168_598016.pth
+-[2023-09-19 11:16:50,198][40303] Fps is (10 sec: 7372.6, 60 sec: 6963.2, 300 sec: 7033.1). Total num frames: 1462272. Throughput: 0: 3406.2, 1: 3406.0. Samples: 1443310. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:16:50,199][40303] Avg episode reward: [(0, '142593.411'), (1, '143931.524')]
+-[2023-09-19 11:16:53,925][41271] Updated weights for policy 1, policy_version 1440 (0.0013)
+-[2023-09-19 11:16:53,925][41246] Updated weights for policy 0, policy_version 1480 (0.0014)
+-[2023-09-19 11:16:55,197][40303] Fps is (10 sec: 6553.8, 60 sec: 6963.2, 300 sec: 7021.7). Total num frames: 1495040. Throughput: 0: 3409.2, 1: 3408.4. Samples: 1466370. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:16:55,198][40303] Avg episode reward: [(0, '149470.139'), (1, '145636.804')]
+-[2023-09-19 11:16:55,217][41187] Saving new best policy, reward=149470.139!
+-[2023-09-19 11:17:00,198][40303] Fps is (10 sec: 7372.9, 60 sec: 6963.2, 300 sec: 7048.9). Total num frames: 1536000. Throughput: 0: 3492.7, 1: 3493.2. Samples: 1509334. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:00,198][40303] Avg episode reward: [(0, '153538.121'), (1, '146540.869')]
+-[2023-09-19 11:17:00,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001520_778240.pth...
+-[2023-09-19 11:17:00,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001480_757760.pth...
+-[2023-09-19 11:17:00,214][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001272_651264.pth
+-[2023-09-19 11:17:00,215][41188] Saving new best policy, reward=146540.869!
+-[2023-09-19 11:17:00,215][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001312_671744.pth
+-[2023-09-19 11:17:00,216][41187] Saving new best policy, reward=153538.121!
+-[2023-09-19 11:17:05,198][40303] Fps is (10 sec: 7372.6, 60 sec: 6826.7, 300 sec: 7037.7). Total num frames: 1568768. Throughput: 0: 3593.8, 1: 3594.0. Samples: 1552730. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:05,199][40303] Avg episode reward: [(0, '153219.886'), (1, '146009.885')]
+-[2023-09-19 11:17:05,296][41271] Updated weights for policy 1, policy_version 1520 (0.0013)
+-[2023-09-19 11:17:05,298][41246] Updated weights for policy 0, policy_version 1560 (0.0011)
+-[2023-09-19 11:17:10,197][40303] Fps is (10 sec: 7372.9, 60 sec: 6963.2, 300 sec: 7063.3). Total num frames: 1609728. Throughput: 0: 3560.3, 1: 3559.7. Samples: 1572972. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:17:10,198][40303] Avg episode reward: [(0, '152679.736'), (1, '148353.321')]
+-[2023-09-19 11:17:10,199][41188] Saving new best policy, reward=148353.321!
+-[2023-09-19 11:17:15,197][40303] Fps is (10 sec: 7372.9, 60 sec: 7099.7, 300 sec: 7052.2). Total num frames: 1642496. Throughput: 0: 3533.3, 1: 3532.9. Samples: 1617104. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:17:15,198][40303] Avg episode reward: [(0, '152608.632'), (1, '147785.111')]
+-[2023-09-19 11:17:15,204][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001624_831488.pth...
+-[2023-09-19 11:17:15,204][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001584_811008.pth...
+-[2023-09-19 11:17:15,211][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001376_704512.pth
+-[2023-09-19 11:17:15,212][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001416_724992.pth
+-[2023-09-19 11:17:17,037][41271] Updated weights for policy 1, policy_version 1600 (0.0014)
+-[2023-09-19 11:17:17,037][41246] Updated weights for policy 0, policy_version 1640 (0.0013)
+-[2023-09-19 11:17:20,198][40303] Fps is (10 sec: 6553.5, 60 sec: 7099.7, 300 sec: 7041.6). Total num frames: 1675264. Throughput: 0: 3521.5, 1: 3520.4. Samples: 1654740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:20,199][40303] Avg episode reward: [(0, '153339.116'), (1, '146902.121')]
+-[2023-09-19 11:17:25,198][40303] Fps is (10 sec: 5734.3, 60 sec: 6826.7, 300 sec: 6997.3). Total num frames: 1699840. Throughput: 0: 3454.4, 1: 3454.3. Samples: 1671790. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:25,199][40303] Avg episode reward: [(0, '153197.923'), (1, '148121.368')]
+-[2023-09-19 11:17:29,838][41246] Updated weights for policy 0, policy_version 1720 (0.0013)
+-[2023-09-19 11:17:29,839][41271] Updated weights for policy 1, policy_version 1680 (0.0014)
+-[2023-09-19 11:17:30,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6963.2, 300 sec: 7021.7). Total num frames: 1740800. Throughput: 0: 3465.9, 1: 3466.4. Samples: 1713704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:30,199][40303] Avg episode reward: [(0, '149499.415'), (1, '148156.690')]
+-[2023-09-19 11:17:30,206][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001720_880640.pth...
+-[2023-09-19 11:17:30,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001680_860160.pth...
+-[2023-09-19 11:17:30,213][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001520_778240.pth
+-[2023-09-19 11:17:30,215][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001480_757760.pth
+-[2023-09-19 11:17:35,198][40303] Fps is (10 sec: 7372.8, 60 sec: 6963.2, 300 sec: 7012.3). Total num frames: 1773568. Throughput: 0: 3480.4, 1: 3480.4. Samples: 1756542. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:17:35,199][40303] Avg episode reward: [(0, '148300.205'), (1, '148607.536')]
+-[2023-09-19 11:17:35,200][41188] Saving new best policy, reward=148607.536!
+-[2023-09-19 11:17:40,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7035.5). Total num frames: 1814528. Throughput: 0: 3459.8, 1: 3460.8. Samples: 1777800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:40,199][40303] Avg episode reward: [(0, '148265.013'), (1, '149557.427')]
+-[2023-09-19 11:17:40,201][41188] Saving new best policy, reward=149557.427!
+-[2023-09-19 11:17:41,639][41271] Updated weights for policy 1, policy_version 1760 (0.0011)
+-[2023-09-19 11:17:41,639][41246] Updated weights for policy 0, policy_version 1800 (0.0015)
+-[2023-09-19 11:17:45,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6826.7, 300 sec: 6994.7). Total num frames: 1839104. Throughput: 0: 3421.1, 1: 3421.1. Samples: 1817234. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:17:45,199][40303] Avg episode reward: [(0, '148265.013'), (1, '149557.427')]
+-[2023-09-19 11:17:45,233][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001784_913408.pth...
+-[2023-09-19 11:17:45,236][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001584_811008.pth
+-[2023-09-19 11:17:45,238][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001824_933888.pth...
+-[2023-09-19 11:17:45,242][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001624_831488.pth
+-[2023-09-19 11:17:50,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6963.2, 300 sec: 7017.3). Total num frames: 1880064. Throughput: 0: 3389.4, 1: 3389.2. Samples: 1857766. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:17:50,199][40303] Avg episode reward: [(0, '148074.607'), (1, '152409.695')]
+-[2023-09-19 11:17:50,201][41188] Saving new best policy, reward=152409.695!
+-[2023-09-19 11:17:53,620][41246] Updated weights for policy 0, policy_version 1880 (0.0014)
+-[2023-09-19 11:17:53,621][41271] Updated weights for policy 1, policy_version 1840 (0.0015)
+-[2023-09-19 11:17:55,198][40303] Fps is (10 sec: 7372.9, 60 sec: 6963.2, 300 sec: 7008.7). Total num frames: 1912832. Throughput: 0: 3389.5, 1: 3390.0. Samples: 1878050. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:17:55,199][40303] Avg episode reward: [(0, '148074.607'), (1, '152273.875')]
+-[2023-09-19 11:18:00,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6826.7, 300 sec: 7000.4). Total num frames: 1945600. Throughput: 0: 3345.4, 1: 3345.7. Samples: 1918202. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:00,198][40303] Avg episode reward: [(0, '153050.644'), (1, '152274.335')]
+-[2023-09-19 11:18:00,206][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001880_962560.pth...
+-[2023-09-19 11:18:00,206][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001920_983040.pth...
+-[2023-09-19 11:18:00,212][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001680_860160.pth
+-[2023-09-19 11:18:00,216][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001720_880640.pth
+-[2023-09-19 11:18:05,198][40303] Fps is (10 sec: 6553.7, 60 sec: 6826.7, 300 sec: 6992.5). Total num frames: 1978368. Throughput: 0: 3388.8, 1: 3389.7. Samples: 1959770. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:05,199][40303] Avg episode reward: [(0, '154101.029'), (1, '152166.485')]
+-[2023-09-19 11:18:05,200][41187] Saving new best policy, reward=154101.029!
+-[2023-09-19 11:18:05,611][41246] Updated weights for policy 0, policy_version 1960 (0.0016)
+-[2023-09-19 11:18:05,611][41271] Updated weights for policy 1, policy_version 1920 (0.0015)
+-[2023-09-19 11:18:10,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6690.1, 300 sec: 6984.8). Total num frames: 2011136. Throughput: 0: 3449.6, 1: 3449.8. Samples: 1982264. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:18:10,199][40303] Avg episode reward: [(0, '156034.676'), (1, '151366.137')]
+-[2023-09-19 11:18:10,200][41187] Saving new best policy, reward=156034.676!
+-[2023-09-19 11:18:15,198][40303] Fps is (10 sec: 6553.4, 60 sec: 6690.1, 300 sec: 6977.3). Total num frames: 2043904. Throughput: 0: 3381.2, 1: 3381.2. Samples: 2018014. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:15,199][40303] Avg episode reward: [(0, '155164.894'), (1, '150838.954')]
+-[2023-09-19 11:18:15,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002016_1032192.pth...
+-[2023-09-19 11:18:15,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001976_1011712.pth...
+-[2023-09-19 11:18:15,217][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001824_933888.pth
+-[2023-09-19 11:18:15,217][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001784_913408.pth
+-[2023-09-19 11:18:18,102][41246] Updated weights for policy 0, policy_version 2040 (0.0012)
+-[2023-09-19 11:18:18,102][41271] Updated weights for policy 1, policy_version 2000 (0.0012)
+-[2023-09-19 11:18:20,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6970.1). Total num frames: 2076672. Throughput: 0: 3371.1, 1: 3370.6. Samples: 2059918. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:18:20,199][40303] Avg episode reward: [(0, '155231.770'), (1, '150958.366')]
+-[2023-09-19 11:18:25,198][40303] Fps is (10 sec: 5734.5, 60 sec: 6690.1, 300 sec: 6997.9). Total num frames: 2101248. Throughput: 0: 3299.0, 1: 3299.1. Samples: 2074716. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:18:25,199][40303] Avg episode reward: [(0, '154273.430'), (1, '151002.496')]
+-[2023-09-19 11:18:30,198][40303] Fps is (10 sec: 5734.4, 60 sec: 6553.6, 300 sec: 6997.9). Total num frames: 2134016. Throughput: 0: 3270.6, 1: 3270.6. Samples: 2111590. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:30,198][40303] Avg episode reward: [(0, '155007.997'), (1, '150084.194')]
+-[2023-09-19 11:18:30,205][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002064_1056768.pth...
+-[2023-09-19 11:18:30,205][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002104_1077248.pth...
+-[2023-09-19 11:18:30,211][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001880_962560.pth
+-[2023-09-19 11:18:30,214][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001920_983040.pth
+-[2023-09-19 11:18:32,089][41271] Updated weights for policy 1, policy_version 2080 (0.0011)
+-[2023-09-19 11:18:32,090][41246] Updated weights for policy 0, policy_version 2120 (0.0012)
+-[2023-09-19 11:18:35,197][40303] Fps is (10 sec: 6553.7, 60 sec: 6553.6, 300 sec: 6970.1). Total num frames: 2166784. Throughput: 0: 3205.9, 1: 3205.1. Samples: 2146258. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:35,198][40303] Avg episode reward: [(0, '155007.997'), (1, '150624.279')]
+-[2023-09-19 11:18:40,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6970.1). Total num frames: 2199552. Throughput: 0: 3184.1, 1: 3184.0. Samples: 2164612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:40,199][40303] Avg episode reward: [(0, '145580.524'), (1, '151090.148')]
+-[2023-09-19 11:18:44,767][41271] Updated weights for policy 1, policy_version 2160 (0.0013)
+-[2023-09-19 11:18:44,768][41246] Updated weights for policy 0, policy_version 2200 (0.0014)
+-[2023-09-19 11:18:45,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6553.6, 300 sec: 6942.4). Total num frames: 2232320. Throughput: 0: 3191.7, 1: 3191.8. Samples: 2205460. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:18:45,199][40303] Avg episode reward: [(0, '145607.879'), (1, '152391.555')]
+-[2023-09-19 11:18:45,208][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002200_1126400.pth...
+-[2023-09-19 11:18:45,208][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002160_1105920.pth...
+-[2023-09-19 11:18:45,214][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001976_1011712.pth
+-[2023-09-19 11:18:45,217][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002016_1032192.pth
+-[2023-09-19 11:18:50,197][40303] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6942.4). Total num frames: 2265088. Throughput: 0: 3173.6, 1: 3173.4. Samples: 2245384. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:18:50,198][40303] Avg episode reward: [(0, '141531.277'), (1, '153070.074')]
+-[2023-09-19 11:18:50,199][41188] Saving new best policy, reward=153070.074!
+-[2023-09-19 11:18:55,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6942.4). Total num frames: 2297856. Throughput: 0: 3144.3, 1: 3144.4. Samples: 2265256. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:18:55,199][40303] Avg episode reward: [(0, '141531.277'), (1, '153134.366')]
+-[2023-09-19 11:18:55,200][41188] Saving new best policy, reward=153134.366!
+-[2023-09-19 11:18:57,266][41271] Updated weights for policy 1, policy_version 2240 (0.0014)
+-[2023-09-19 11:18:57,267][41246] Updated weights for policy 0, policy_version 2280 (0.0013)
+-[2023-09-19 11:19:00,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6914.6). Total num frames: 2330624. Throughput: 0: 3181.9, 1: 3181.2. Samples: 2304352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:00,198][40303] Avg episode reward: [(0, '140084.973'), (1, '153499.154')]
+-[2023-09-19 11:19:00,205][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002296_1175552.pth...
+-[2023-09-19 11:19:00,206][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002256_1155072.pth...
+-[2023-09-19 11:19:00,213][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002064_1056768.pth
+-[2023-09-19 11:19:00,213][41188] Saving new best policy, reward=153499.154!
+-[2023-09-19 11:19:00,214][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002104_1077248.pth
+-[2023-09-19 11:19:05,197][40303] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6914.6). Total num frames: 2363392. Throughput: 0: 3174.0, 1: 3174.3. Samples: 2345590. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:05,198][40303] Avg episode reward: [(0, '140163.997'), (1, '154850.945')]
+-[2023-09-19 11:19:05,199][41188] Saving new best policy, reward=154850.945!
+-[2023-09-19 11:19:09,431][41271] Updated weights for policy 1, policy_version 2320 (0.0012)
+-[2023-09-19 11:19:09,432][41246] Updated weights for policy 0, policy_version 2360 (0.0015)
+-[2023-09-19 11:19:10,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6886.8). Total num frames: 2396160. Throughput: 0: 3226.4, 1: 3226.4. Samples: 2365092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:10,199][40303] Avg episode reward: [(0, '146252.432'), (1, '155854.149')]
+-[2023-09-19 11:19:10,200][41188] Saving new best policy, reward=155854.149!
+-[2023-09-19 11:19:15,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6886.8). Total num frames: 2428928. Throughput: 0: 3251.3, 1: 3251.4. Samples: 2404212. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:19:15,198][40303] Avg episode reward: [(0, '146450.850'), (1, '155450.882')]
+-[2023-09-19 11:19:15,205][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002392_1224704.pth...
+-[2023-09-19 11:19:15,206][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002352_1204224.pth...
+-[2023-09-19 11:19:15,216][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002200_1126400.pth
+-[2023-09-19 11:19:15,217][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002160_1105920.pth
+-[2023-09-19 11:19:16,564][40303] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 40303], exiting...
+-[2023-09-19 11:19:16,565][40303] Runner profile tree view:
+-main_loop: 357.5508
+-[2023-09-19 11:19:16,566][41187] Stopping Batcher_0...
+-[2023-09-19 11:19:16,566][41187] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:19:16,566][40303] Collected {0: 1228800, 1: 1208320}, FPS: 6758.9
+-[2023-09-19 11:19:16,566][41188] Stopping Batcher_1...
+-[2023-09-19 11:19:16,566][41188] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:19:16,567][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002360_1208320.pth...
+-[2023-09-19 11:19:16,567][41287] Stopping RolloutWorker_w4...
+-[2023-09-19 11:19:16,567][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002400_1228800.pth...
+-[2023-09-19 11:19:16,567][41287] Loop rollout_proc4_evt_loop terminating...
+-[2023-09-19 11:19:16,569][41278] Stopping RolloutWorker_w2...
+-[2023-09-19 11:19:16,569][41276] Stopping RolloutWorker_w1...
+-[2023-09-19 11:19:16,569][41278] Loop rollout_proc2_evt_loop terminating...
+-[2023-09-19 11:19:16,569][41276] Loop rollout_proc1_evt_loop terminating...
+-[2023-09-19 11:19:16,570][41291] Stopping RolloutWorker_w7...
+-[2023-09-19 11:19:16,570][41291] Loop rollout_proc7_evt_loop terminating...
+-[2023-09-19 11:19:16,570][41272] Stopping RolloutWorker_w0...
+-[2023-09-19 11:19:16,570][41272] Loop rollout_proc0_evt_loop terminating...
+-[2023-09-19 11:19:16,571][41290] Stopping RolloutWorker_w6...
+-[2023-09-19 11:19:16,571][41290] Loop rollout_proc6_evt_loop terminating...
+-[2023-09-19 11:19:16,571][41284] Stopping RolloutWorker_w3...
+-[2023-09-19 11:19:16,571][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002256_1155072.pth
+-[2023-09-19 11:19:16,571][41284] Loop rollout_proc3_evt_loop terminating...
+-[2023-09-19 11:19:16,571][41292] Stopping RolloutWorker_w5...
+-[2023-09-19 11:19:16,572][41188] Stopping LearnerWorker_p1...
+-[2023-09-19 11:19:16,572][41292] Loop rollout_proc5_evt_loop terminating...
+-[2023-09-19 11:19:16,572][41188] Loop learner_proc1_evt_loop terminating...
+-[2023-09-19 11:19:16,575][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002296_1175552.pth
+-[2023-09-19 11:19:16,576][41187] Stopping LearnerWorker_p0...
+-[2023-09-19 11:19:16,576][41187] Loop learner_proc0_evt_loop terminating...
+-[2023-09-19 11:19:16,580][41246] Weights refcount: 2 0
+-[2023-09-19 11:19:16,581][41246] Stopping InferenceWorker_p0-w0...
+-[2023-09-19 11:19:16,581][41246] Loop inference_proc0-0_evt_loop terminating...
+-[2023-09-19 11:19:16,583][41271] Weights refcount: 2 0
+-[2023-09-19 11:19:16,584][41271] Stopping InferenceWorker_p1-w0...
+-[2023-09-19 11:19:16,584][41271] Loop inference_proc1-0_evt_loop terminating...
+-[2023-09-19 11:19:40,691][72530] Saving configuration to ./train_dir/Standup/config.json...
+-[2023-09-19 11:19:40,693][72530] Rollout worker 0 uses device cpu
+-[2023-09-19 11:19:40,694][72530] Rollout worker 1 uses device cpu
+-[2023-09-19 11:19:40,694][72530] Rollout worker 2 uses device cpu
+-[2023-09-19 11:19:40,695][72530] Rollout worker 3 uses device cpu
+-[2023-09-19 11:19:40,695][72530] Rollout worker 4 uses device cpu
+-[2023-09-19 11:19:40,695][72530] Rollout worker 5 uses device cpu
+-[2023-09-19 11:19:40,696][72530] Rollout worker 6 uses device cpu
+-[2023-09-19 11:19:40,696][72530] Rollout worker 7 uses device cpu
+-[2023-09-19 11:19:40,696][72530] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
+-[2023-09-19 11:19:40,753][72530] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:40,753][72530] InferenceWorker_p0-w0: min num requests: 1
+-[2023-09-19 11:19:40,757][72530] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:40,757][72530] InferenceWorker_p1-w0: min num requests: 1
+-[2023-09-19 11:19:40,783][72530] Starting all processes...
+-[2023-09-19 11:19:40,783][72530] Starting process learner_proc0
+-[2023-09-19 11:19:40,786][72530] Starting process learner_proc1
+-[2023-09-19 11:19:40,832][72530] Starting all processes...
+-[2023-09-19 11:19:40,838][72530] Starting process inference_proc0-0
+-[2023-09-19 11:19:40,838][72530] Starting process inference_proc1-0
+-[2023-09-19 11:19:40,838][72530] Starting process rollout_proc0
+-[2023-09-19 11:19:40,839][72530] Starting process rollout_proc1
+-[2023-09-19 11:19:40,839][72530] Starting process rollout_proc2
+-[2023-09-19 11:19:40,839][72530] Starting process rollout_proc3
+-[2023-09-19 11:19:40,840][72530] Starting process rollout_proc4
+-[2023-09-19 11:19:40,843][72530] Starting process rollout_proc5
+-[2023-09-19 11:19:40,843][72530] Starting process rollout_proc6
+-[2023-09-19 11:19:40,844][72530] Starting process rollout_proc7
+-[2023-09-19 11:19:42,632][73131] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:42,632][73131] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1
+-[2023-09-19 11:19:42,651][73131] Num visible devices: 1
+-[2023-09-19 11:19:42,668][73131] Starting seed is not provided
+-[2023-09-19 11:19:42,669][73131] Using GPUs [0] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:42,669][73131] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:19:42,670][73131] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:19:42,670][73131] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:19:42,680][73130] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:42,681][73130] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+-[2023-09-19 11:19:42,683][73226] Worker 7 uses CPU cores [28, 29, 30, 31]
+-[2023-09-19 11:19:42,694][73220] Worker 2 uses CPU cores [8, 9, 10, 11]
+-[2023-09-19 11:19:42,701][73130] Num visible devices: 1
+-[2023-09-19 11:19:42,723][73222] Worker 6 uses CPU cores [24, 25, 26, 27]
+-[2023-09-19 11:19:42,725][73130] Starting seed is not provided
+-[2023-09-19 11:19:42,725][73130] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:42,725][73130] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:19:42,725][73130] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:19:42,726][73130] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:19:42,731][73224] Worker 4 uses CPU cores [16, 17, 18, 19]
+-[2023-09-19 11:19:42,733][73131] Created Actor Critic model with architecture:
+-[2023-09-19 11:19:42,734][73131] 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=17, bias=True)
+-  )
+-)
+-[2023-09-19 11:19:42,740][73219] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:42,740][73219] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1
+-[2023-09-19 11:19:42,756][73145] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:42,756][73145] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+-[2023-09-19 11:19:42,787][73145] Num visible devices: 1
+-[2023-09-19 11:19:42,787][73219] Num visible devices: 1
+-[2023-09-19 11:19:42,797][73130] Created Actor Critic model with architecture:
+-[2023-09-19 11:19:42,797][73130] 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=17, bias=True)
+-  )
+-)
+-[2023-09-19 11:19:42,798][73221] Worker 1 uses CPU cores [4, 5, 6, 7]
+-[2023-09-19 11:19:42,939][73223] Worker 3 uses CPU cores [12, 13, 14, 15]
+-[2023-09-19 11:19:43,116][73229] Worker 5 uses CPU cores [20, 21, 22, 23]
+-[2023-09-19 11:19:43,205][73218] Worker 0 uses CPU cores [0, 1, 2, 3]
+-[2023-09-19 11:19:43,373][73131] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:19:43,373][73131] Loading state from checkpoint ./train_dir/Standup/checkpoint_p1/checkpoint_000002360_1208320.pth...
+-[2023-09-19 11:19:43,379][73131] Loading model from checkpoint
+-[2023-09-19 11:19:43,381][73131] Loaded experiment state at self.train_step=2360, self.env_steps=1208320
+-[2023-09-19 11:19:43,382][73131] Initialized policy 1 weights for model version 2360
+-[2023-09-19 11:19:43,383][73131] LearnerWorker_p1 finished initialization!
+-[2023-09-19 11:19:43,383][73131] Using GPUs [0] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:43,409][73130] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:19:43,410][73130] Loading state from checkpoint ./train_dir/Standup/checkpoint_p0/checkpoint_000002400_1228800.pth...
+-[2023-09-19 11:19:43,416][73130] Loading model from checkpoint
+-[2023-09-19 11:19:43,419][73130] Loaded experiment state at self.train_step=2400, self.env_steps=1228800
+-[2023-09-19 11:19:43,419][73130] Initialized policy 0 weights for model version 2400
+-[2023-09-19 11:19:43,427][73130] LearnerWorker_p0 finished initialization!
+-[2023-09-19 11:19:43,427][73130] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:43,971][73219] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:19:43,971][73219] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:19:43,987][73145] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:19:43,987][73145] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:19:44,004][72530] Inference worker 1-0 is ready!
+-[2023-09-19 11:19:44,021][72530] Inference worker 0-0 is ready!
+-[2023-09-19 11:19:44,022][72530] All inference workers are ready! Signal rollout workers to start!
+-[2023-09-19 11:19:44,118][73223] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,119][73223] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,120][73229] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,121][73229] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,122][73221] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,123][73221] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,128][73226] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,128][73226] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,132][73220] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,133][73220] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,141][73222] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,142][73222] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,157][73224] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,158][73224] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,161][73218] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,162][73218] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,168][73223] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,171][73229] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,175][73221] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,181][73226] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,199][73220] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,200][73222] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,222][73224] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,243][73218] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,273][73223] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,277][73229] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,281][73221] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,284][73226] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,299][73222] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,304][73220] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,319][73224] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,368][73218] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,444][73223] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,447][73229] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,457][73226] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,462][73221] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,476][73222] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,492][73220] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,499][73224] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,575][73218] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,651][73223] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,657][73229] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,666][73226] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,681][73221] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,689][73222] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,707][73220] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,714][73224] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,803][73218] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,907][73223] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,915][73229] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,916][73226] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,933][73221] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,939][73222] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,969][73224] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:45,006][73220] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:45,067][73218] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:45,209][73223] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,221][73226] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,227][73229] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,253][73222] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,261][73221] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,302][73224] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,325][73220] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,392][73218] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:47,043][72530] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 2437120. Throughput: 0: nan, 1: nan. Samples: 5818. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+-[2023-09-19 11:19:52,043][72530] Fps is (10 sec: 3276.7, 60 sec: 3276.7, 300 sec: 3276.7). Total num frames: 2453504. Throughput: 0: 1049.2, 1: 1064.0. Samples: 16384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:52,340][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002424_1241088.pth...
+-[2023-09-19 11:19:52,343][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002384_1220608.pth...
+-[2023-09-19 11:19:52,345][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002392_1224704.pth
+-[2023-09-19 11:19:52,348][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002352_1204224.pth
+-[2023-09-19 11:19:57,043][72530] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 2478080. Throughput: 0: 1910.2, 1: 1911.2. Samples: 44032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:57,045][72530] Avg episode reward: [(0, '67743.941'), (1, '43579.059')]
+-[2023-09-19 11:20:00,740][72530] Heartbeat connected on Batcher_0
+-[2023-09-19 11:20:00,743][72530] Heartbeat connected on LearnerWorker_p0
+-[2023-09-19 11:20:00,746][72530] Heartbeat connected on Batcher_1
+-[2023-09-19 11:20:00,749][72530] Heartbeat connected on LearnerWorker_p1
+-[2023-09-19 11:20:00,755][72530] Heartbeat connected on InferenceWorker_p0-w0
+-[2023-09-19 11:20:00,760][72530] Heartbeat connected on InferenceWorker_p1-w0
+-[2023-09-19 11:20:00,761][72530] Heartbeat connected on RolloutWorker_w0
+-[2023-09-19 11:20:00,767][72530] Heartbeat connected on RolloutWorker_w2
+-[2023-09-19 11:20:00,769][72530] Heartbeat connected on RolloutWorker_w3
+-[2023-09-19 11:20:00,771][72530] Heartbeat connected on RolloutWorker_w1
+-[2023-09-19 11:20:00,772][72530] Heartbeat connected on RolloutWorker_w4
+-[2023-09-19 11:20:00,779][72530] Heartbeat connected on RolloutWorker_w6
+-[2023-09-19 11:20:00,782][72530] Heartbeat connected on RolloutWorker_w7
+-[2023-09-19 11:20:00,783][72530] Heartbeat connected on RolloutWorker_w5
+-[2023-09-19 11:20:02,043][72530] Fps is (10 sec: 6144.1, 60 sec: 5188.3, 300 sec: 5188.3). Total num frames: 2514944. Throughput: 0: 1864.9, 1: 1865.5. Samples: 61774. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:02,043][72530] Avg episode reward: [(0, '99962.574'), (1, '74154.644')]
+-[2023-09-19 11:20:02,049][73145] Updated weights for policy 0, policy_version 2480 (0.0015)
+-[2023-09-19 11:20:02,049][73219] Updated weights for policy 1, policy_version 2440 (0.0013)
+-[2023-09-19 11:20:07,043][72530] Fps is (10 sec: 7372.7, 60 sec: 5734.3, 300 sec: 5734.3). Total num frames: 2551808. Throughput: 0: 2437.4, 1: 2437.7. Samples: 103320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:07,045][72530] Avg episode reward: [(0, '117948.527'), (1, '103367.832')]
+-[2023-09-19 11:20:07,048][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002512_1286144.pth...
+-[2023-09-19 11:20:07,048][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002472_1265664.pth...
+-[2023-09-19 11:20:07,055][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002400_1228800.pth
+-[2023-09-19 11:20:07,057][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002360_1208320.pth
+-[2023-09-19 11:20:12,043][72530] Fps is (10 sec: 6963.0, 60 sec: 5898.2, 300 sec: 5898.2). Total num frames: 2584576. Throughput: 0: 2806.0, 1: 2806.1. Samples: 146122. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:20:12,045][72530] Avg episode reward: [(0, '124390.108'), (1, '110149.801')]
+-[2023-09-19 11:20:13,613][73219] Updated weights for policy 1, policy_version 2520 (0.0012)
+-[2023-09-19 11:20:13,613][73145] Updated weights for policy 0, policy_version 2560 (0.0014)
+-[2023-09-19 11:20:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6007.5, 300 sec: 6007.5). Total num frames: 2617344. Throughput: 0: 3030.0, 1: 3030.3. Samples: 187626. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:20:17,047][72530] Avg episode reward: [(0, '133247.381'), (1, '124425.608')]
+-[2023-09-19 11:20:22,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6085.4, 300 sec: 6085.4). Total num frames: 2650112. Throughput: 0: 2890.3, 1: 2890.4. Samples: 208144. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:20:22,044][72530] Avg episode reward: [(0, '134256.432'), (1, '126597.151')]
+-[2023-09-19 11:20:22,047][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002568_1314816.pth...
+-[2023-09-19 11:20:22,049][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002608_1335296.pth...
+-[2023-09-19 11:20:22,056][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002384_1220608.pth
+-[2023-09-19 11:20:22,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002424_1241088.pth
+-[2023-09-19 11:20:26,328][73219] Updated weights for policy 1, policy_version 2600 (0.0014)
+-[2023-09-19 11:20:26,329][73145] Updated weights for policy 0, policy_version 2640 (0.0014)
+-[2023-09-19 11:20:27,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6144.0). Total num frames: 2682880. Throughput: 0: 2979.6, 1: 2979.8. Samples: 244194. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:27,044][72530] Avg episode reward: [(0, '152920.116'), (1, '149441.210')]
+-[2023-09-19 11:20:32,043][72530] Fps is (10 sec: 6553.8, 60 sec: 6189.5, 300 sec: 6189.5). Total num frames: 2715648. Throughput: 0: 3119.2, 1: 3119.5. Samples: 286558. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:20:32,044][72530] Avg episode reward: [(0, '154007.595'), (1, '152818.612')]
+-[2023-09-19 11:20:37,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6225.9, 300 sec: 6225.9). Total num frames: 2748416. Throughput: 0: 3203.5, 1: 3202.2. Samples: 304640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:37,044][72530] Avg episode reward: [(0, '152855.520'), (1, '157930.094')]
+-[2023-09-19 11:20:37,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002664_1363968.pth...
+-[2023-09-19 11:20:37,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002704_1384448.pth...
+-[2023-09-19 11:20:37,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002472_1265664.pth
+-[2023-09-19 11:20:37,059][73131] Saving new best policy, reward=157930.094!
+-[2023-09-19 11:20:37,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002512_1286144.pth
+-[2023-09-19 11:20:39,045][73219] Updated weights for policy 1, policy_version 2680 (0.0013)
+-[2023-09-19 11:20:39,046][73145] Updated weights for policy 0, policy_version 2720 (0.0015)
+-[2023-09-19 11:20:42,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6255.7, 300 sec: 6255.7). Total num frames: 2781184. Throughput: 0: 3306.8, 1: 3306.8. Samples: 341646. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:42,044][72530] Avg episode reward: [(0, '151664.402'), (1, '158564.220')]
+-[2023-09-19 11:20:42,045][73131] Saving new best policy, reward=158564.220!
+-[2023-09-19 11:20:47,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6280.5). Total num frames: 2813952. Throughput: 0: 3562.3, 1: 3562.2. Samples: 382380. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:20:47,044][72530] Avg episode reward: [(0, '145105.303'), (1, '155856.908')]
+-[2023-09-19 11:20:51,525][73145] Updated weights for policy 0, policy_version 2800 (0.0016)
+-[2023-09-19 11:20:51,526][73219] Updated weights for policy 1, policy_version 2760 (0.0014)
+-[2023-09-19 11:20:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6301.5). Total num frames: 2846720. Throughput: 0: 3312.4, 1: 3313.6. Samples: 401490. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:20:52,044][72530] Avg episode reward: [(0, '144121.200'), (1, '155856.908')]
+-[2023-09-19 11:20:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002800_1433600.pth...
+-[2023-09-19 11:20:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002760_1413120.pth...
+-[2023-09-19 11:20:52,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002608_1335296.pth
+-[2023-09-19 11:20:52,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002568_1314816.pth
+-[2023-09-19 11:20:57,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6319.5). Total num frames: 2879488. Throughput: 0: 3240.4, 1: 3240.4. Samples: 437758. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:20:57,044][72530] Avg episode reward: [(0, '142988.097'), (1, '155707.131')]
+-[2023-09-19 11:21:02,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6621.8, 300 sec: 6335.1). Total num frames: 2912256. Throughput: 0: 3233.5, 1: 3233.3. Samples: 478634. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:02,045][72530] Avg episode reward: [(0, '144052.838'), (1, '155707.131')]
+-[2023-09-19 11:21:04,172][73219] Updated weights for policy 1, policy_version 2840 (0.0013)
+-[2023-09-19 11:21:04,172][73145] Updated weights for policy 0, policy_version 2880 (0.0010)
+-[2023-09-19 11:21:07,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6348.8). Total num frames: 2945024. Throughput: 0: 3220.4, 1: 3220.5. Samples: 497982. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:21:07,044][72530] Avg episode reward: [(0, '145667.627'), (1, '156028.379')]
+-[2023-09-19 11:21:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002856_1462272.pth...
+-[2023-09-19 11:21:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002896_1482752.pth...
+-[2023-09-19 11:21:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002664_1363968.pth
+-[2023-09-19 11:21:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002704_1384448.pth
+-[2023-09-19 11:21:12,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6360.8). Total num frames: 2977792. Throughput: 0: 3292.6, 1: 3293.6. Samples: 540574. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:21:12,045][72530] Avg episode reward: [(0, '147376.857'), (1, '156100.448')]
+-[2023-09-19 11:21:16,935][73219] Updated weights for policy 1, policy_version 2920 (0.0012)
+-[2023-09-19 11:21:16,935][73145] Updated weights for policy 0, policy_version 2960 (0.0013)
+-[2023-09-19 11:21:17,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6371.5). Total num frames: 3010560. Throughput: 0: 3192.5, 1: 3192.8. Samples: 573896. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:21:17,044][72530] Avg episode reward: [(0, '153646.249'), (1, '157825.450')]
+-[2023-09-19 11:21:22,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6417.1, 300 sec: 6294.9). Total num frames: 3035136. Throughput: 0: 3218.0, 1: 3217.9. Samples: 594256. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:21:22,044][72530] Avg episode reward: [(0, '156927.936'), (1, '157825.450')]
+-[2023-09-19 11:21:22,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002944_1507328.pth...
+-[2023-09-19 11:21:22,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002984_1527808.pth...
+-[2023-09-19 11:21:22,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002800_1433600.pth
+-[2023-09-19 11:21:22,060][73130] Saving new best policy, reward=156927.936!
+-[2023-09-19 11:21:22,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002760_1413120.pth
+-[2023-09-19 11:21:27,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6417.1, 300 sec: 6307.8). Total num frames: 3067904. Throughput: 0: 3210.2, 1: 3210.0. Samples: 630558. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:21:27,045][72530] Avg episode reward: [(0, '158809.152'), (1, '159261.146')]
+-[2023-09-19 11:21:27,046][73130] Saving new best policy, reward=158809.152!
+-[2023-09-19 11:21:27,046][73131] Saving new best policy, reward=159261.146!
+-[2023-09-19 11:21:29,937][73145] Updated weights for policy 0, policy_version 3040 (0.0014)
+-[2023-09-19 11:21:29,937][73219] Updated weights for policy 1, policy_version 3000 (0.0015)
+-[2023-09-19 11:21:32,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.0, 300 sec: 6319.5). Total num frames: 3100672. Throughput: 0: 3202.6, 1: 3202.7. Samples: 670618. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:32,044][72530] Avg episode reward: [(0, '158669.703'), (1, '159261.146')]
+-[2023-09-19 11:21:37,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6330.2). Total num frames: 3133440. Throughput: 0: 3194.8, 1: 3193.6. Samples: 688972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:37,044][72530] Avg episode reward: [(0, '160207.000'), (1, '158900.446')]
+-[2023-09-19 11:21:37,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003040_1556480.pth...
+-[2023-09-19 11:21:37,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003080_1576960.pth...
+-[2023-09-19 11:21:37,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002856_1462272.pth
+-[2023-09-19 11:21:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002896_1482752.pth
+-[2023-09-19 11:21:37,063][73130] Saving new best policy, reward=160207.000!
+-[2023-09-19 11:21:42,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6339.9). Total num frames: 3166208. Throughput: 0: 3201.6, 1: 3201.7. Samples: 725908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:42,044][72530] Avg episode reward: [(0, '160167.920'), (1, '158900.446')]
+-[2023-09-19 11:21:43,450][73219] Updated weights for policy 1, policy_version 3080 (0.0013)
+-[2023-09-19 11:21:43,451][73145] Updated weights for policy 0, policy_version 3120 (0.0018)
+-[2023-09-19 11:21:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6280.5). Total num frames: 3190784. Throughput: 0: 3112.9, 1: 3113.1. Samples: 758804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:47,045][72530] Avg episode reward: [(0, '160649.680'), (1, '159123.148')]
+-[2023-09-19 11:21:47,046][73130] Saving new best policy, reward=160649.680!
+-[2023-09-19 11:21:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6291.4). Total num frames: 3223552. Throughput: 0: 3114.0, 1: 3115.4. Samples: 778308. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:21:52,044][72530] Avg episode reward: [(0, '159415.266'), (1, '160065.227')]
+-[2023-09-19 11:21:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003168_1622016.pth...
+-[2023-09-19 11:21:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003128_1601536.pth...
+-[2023-09-19 11:21:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002944_1507328.pth
+-[2023-09-19 11:21:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002984_1527808.pth
+-[2023-09-19 11:21:52,062][73131] Saving new best policy, reward=160065.227!
+-[2023-09-19 11:21:56,561][73145] Updated weights for policy 0, policy_version 3200 (0.0015)
+-[2023-09-19 11:21:56,561][73219] Updated weights for policy 1, policy_version 3160 (0.0015)
+-[2023-09-19 11:21:57,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6301.5). Total num frames: 3256320. Throughput: 0: 3061.8, 1: 3060.8. Samples: 816090. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:21:57,044][72530] Avg episode reward: [(0, '159883.769'), (1, '159603.128')]
+-[2023-09-19 11:22:02,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6310.9). Total num frames: 3289088. Throughput: 0: 3110.9, 1: 3110.3. Samples: 853850. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:22:02,044][72530] Avg episode reward: [(0, '160168.162'), (1, '158805.251')]
+-[2023-09-19 11:22:07,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6319.5). Total num frames: 3321856. Throughput: 0: 3100.6, 1: 3100.8. Samples: 873320. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:22:07,044][72530] Avg episode reward: [(0, '159368.135'), (1, '158166.073')]
+-[2023-09-19 11:22:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003224_1650688.pth...
+-[2023-09-19 11:22:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003264_1671168.pth...
+-[2023-09-19 11:22:07,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003040_1556480.pth
+-[2023-09-19 11:22:07,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003080_1576960.pth
+-[2023-09-19 11:22:09,339][73145] Updated weights for policy 0, policy_version 3280 (0.0016)
+-[2023-09-19 11:22:09,339][73219] Updated weights for policy 1, policy_version 3240 (0.0013)
+-[2023-09-19 11:22:12,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6327.6). Total num frames: 3354624. Throughput: 0: 3134.1, 1: 3134.3. Samples: 912634. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:12,044][72530] Avg episode reward: [(0, '154750.825'), (1, '157929.657')]
+-[2023-09-19 11:22:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6280.5). Total num frames: 3379200. Throughput: 0: 3098.0, 1: 3098.2. Samples: 949448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:17,045][72530] Avg episode reward: [(0, '152601.903'), (1, '153832.123')]
+-[2023-09-19 11:22:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6289.3). Total num frames: 3411968. Throughput: 0: 3112.9, 1: 3113.0. Samples: 969138. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:22:22,044][72530] Avg episode reward: [(0, '152992.401'), (1, '152373.243')]
+-[2023-09-19 11:22:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003312_1695744.pth...
+-[2023-09-19 11:22:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003352_1716224.pth...
+-[2023-09-19 11:22:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003128_1601536.pth
+-[2023-09-19 11:22:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003168_1622016.pth
+-[2023-09-19 11:22:22,748][73219] Updated weights for policy 1, policy_version 3320 (0.0013)
+-[2023-09-19 11:22:22,749][73145] Updated weights for policy 0, policy_version 3360 (0.0014)
+-[2023-09-19 11:22:27,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6297.6). Total num frames: 3444736. Throughput: 0: 3104.4, 1: 3104.3. Samples: 1005296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:27,044][72530] Avg episode reward: [(0, '152409.297'), (1, '152400.063')]
+-[2023-09-19 11:22:32,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6305.4). Total num frames: 3477504. Throughput: 0: 3183.3, 1: 3183.3. Samples: 1045302. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:22:32,044][72530] Avg episode reward: [(0, '150571.798'), (1, '152330.295')]
+-[2023-09-19 11:22:35,267][73145] Updated weights for policy 0, policy_version 3440 (0.0013)
+-[2023-09-19 11:22:35,268][73219] Updated weights for policy 1, policy_version 3400 (0.0014)
+-[2023-09-19 11:22:37,043][72530] Fps is (10 sec: 6553.4, 60 sec: 6280.5, 300 sec: 6312.6). Total num frames: 3510272. Throughput: 0: 3180.8, 1: 3180.2. Samples: 1064554. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:37,044][72530] Avg episode reward: [(0, '150024.495'), (1, '153833.309')]
+-[2023-09-19 11:22:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003408_1744896.pth...
+-[2023-09-19 11:22:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003448_1765376.pth...
+-[2023-09-19 11:22:37,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003264_1671168.pth
+-[2023-09-19 11:22:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003224_1650688.pth
+-[2023-09-19 11:22:42,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6319.5). Total num frames: 3543040. Throughput: 0: 3161.4, 1: 3161.5. Samples: 1100622. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:42,044][72530] Avg episode reward: [(0, '153738.816'), (1, '154391.331')]
+-[2023-09-19 11:22:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6280.5, 300 sec: 6280.5). Total num frames: 3567616. Throughput: 0: 3163.8, 1: 3165.1. Samples: 1138652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:47,044][72530] Avg episode reward: [(0, '154735.807'), (1, '155587.330')]
+-[2023-09-19 11:22:48,507][73145] Updated weights for policy 0, policy_version 3520 (0.0012)
+-[2023-09-19 11:22:48,508][73219] Updated weights for policy 1, policy_version 3480 (0.0013)
+-[2023-09-19 11:22:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6287.9). Total num frames: 3600384. Throughput: 0: 3151.2, 1: 3151.2. Samples: 1156926. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:22:52,044][72530] Avg episode reward: [(0, '155558.003'), (1, '158444.382')]
+-[2023-09-19 11:22:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003496_1789952.pth...
+-[2023-09-19 11:22:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003536_1810432.pth...
+-[2023-09-19 11:22:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003312_1695744.pth
+-[2023-09-19 11:22:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003352_1716224.pth
+-[2023-09-19 11:22:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6251.8). Total num frames: 3624960. Throughput: 0: 3076.0, 1: 3076.3. Samples: 1189490. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:57,044][72530] Avg episode reward: [(0, '156213.048'), (1, '159905.417')]
+-[2023-09-19 11:23:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6259.5). Total num frames: 3657728. Throughput: 0: 3051.2, 1: 3051.2. Samples: 1224052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:02,044][72530] Avg episode reward: [(0, '154952.583'), (1, '160034.837')]
+-[2023-09-19 11:23:03,139][73219] Updated weights for policy 1, policy_version 3560 (0.0011)
+-[2023-09-19 11:23:03,140][73145] Updated weights for policy 0, policy_version 3600 (0.0014)
+-[2023-09-19 11:23:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6225.9). Total num frames: 3682304. Throughput: 0: 3014.6, 1: 3014.8. Samples: 1240462. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:23:07,045][72530] Avg episode reward: [(0, '154952.583'), (1, '160050.141')]
+-[2023-09-19 11:23:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003576_1830912.pth...
+-[2023-09-19 11:23:07,057][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003616_1851392.pth...
+-[2023-09-19 11:23:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003448_1765376.pth
+-[2023-09-19 11:23:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003408_1744896.pth
+-[2023-09-19 11:23:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6233.9). Total num frames: 3715072. Throughput: 0: 3031.9, 1: 3032.3. Samples: 1278182. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:12,045][72530] Avg episode reward: [(0, '151313.141'), (1, '159602.087')]
+-[2023-09-19 11:23:16,373][73219] Updated weights for policy 1, policy_version 3640 (0.0012)
+-[2023-09-19 11:23:16,374][73145] Updated weights for policy 0, policy_version 3680 (0.0011)
+-[2023-09-19 11:23:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6241.5). Total num frames: 3747840. Throughput: 0: 2998.0, 1: 2998.0. Samples: 1315120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:17,044][72530] Avg episode reward: [(0, '151313.141'), (1, '159523.019')]
+-[2023-09-19 11:23:22,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6248.8). Total num frames: 3780608. Throughput: 0: 3006.6, 1: 3007.0. Samples: 1335164. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:23:22,044][72530] Avg episode reward: [(0, '152570.175'), (1, '158236.314')]
+-[2023-09-19 11:23:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003712_1900544.pth...
+-[2023-09-19 11:23:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003672_1880064.pth...
+-[2023-09-19 11:23:22,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003536_1810432.pth
+-[2023-09-19 11:23:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003496_1789952.pth
+-[2023-09-19 11:23:27,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6255.7). Total num frames: 3813376. Throughput: 0: 2986.7, 1: 2986.5. Samples: 1369418. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:27,045][72530] Avg episode reward: [(0, '152570.175'), (1, '158236.314')]
+-[2023-09-19 11:23:29,330][73219] Updated weights for policy 1, policy_version 3720 (0.0013)
+-[2023-09-19 11:23:29,331][73145] Updated weights for policy 0, policy_version 3760 (0.0014)
+-[2023-09-19 11:23:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6225.9). Total num frames: 3837952. Throughput: 0: 2803.1, 1: 2802.0. Samples: 1390884. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:23:32,044][72530] Avg episode reward: [(0, '152939.553'), (1, '157598.636')]
+-[2023-09-19 11:23:37,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6007.5, 300 sec: 6233.0). Total num frames: 3870720. Throughput: 0: 3009.5, 1: 3009.5. Samples: 1427778. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:23:37,044][72530] Avg episode reward: [(0, '152939.553'), (1, '157598.636')]
+-[2023-09-19 11:23:37,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003800_1945600.pth...
+-[2023-09-19 11:23:37,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003760_1925120.pth...
+-[2023-09-19 11:23:37,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003616_1851392.pth
+-[2023-09-19 11:23:37,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003576_1830912.pth
+-[2023-09-19 11:23:42,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6007.5, 300 sec: 6239.9). Total num frames: 3903488. Throughput: 0: 3062.4, 1: 3061.9. Samples: 1465082. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:42,044][72530] Avg episode reward: [(0, '155045.334'), (1, '157877.174')]
+-[2023-09-19 11:23:42,591][73219] Updated weights for policy 1, policy_version 3800 (0.0013)
+-[2023-09-19 11:23:42,592][73145] Updated weights for policy 0, policy_version 3840 (0.0013)
+-[2023-09-19 11:23:47,043][72530] Fps is (10 sec: 5734.2, 60 sec: 6007.4, 300 sec: 6212.3). Total num frames: 3928064. Throughput: 0: 3055.4, 1: 3056.6. Samples: 1499094. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:47,044][72530] Avg episode reward: [(0, '155518.647'), (1, '157877.174')]
+-[2023-09-19 11:23:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6219.2). Total num frames: 3960832. Throughput: 0: 3090.5, 1: 3090.4. Samples: 1518604. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:23:52,044][72530] Avg episode reward: [(0, '156419.731'), (1, '159794.628')]
+-[2023-09-19 11:23:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003848_1970176.pth...
+-[2023-09-19 11:23:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003888_1990656.pth...
+-[2023-09-19 11:23:52,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003672_1880064.pth
+-[2023-09-19 11:23:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003712_1900544.pth
+-[2023-09-19 11:23:56,865][73219] Updated weights for policy 1, policy_version 3880 (0.0012)
+-[2023-09-19 11:23:56,866][73145] Updated weights for policy 0, policy_version 3920 (0.0014)
+-[2023-09-19 11:23:57,043][72530] Fps is (10 sec: 6553.8, 60 sec: 6144.0, 300 sec: 6225.9). Total num frames: 3993600. Throughput: 0: 3037.8, 1: 3037.7. Samples: 1551576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:57,044][72530] Avg episode reward: [(0, '155910.674'), (1, '159794.628')]
+-[2023-09-19 11:24:02,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.4, 300 sec: 6200.2). Total num frames: 4018176. Throughput: 0: 2986.6, 1: 2986.6. Samples: 1583914. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:02,045][72530] Avg episode reward: [(0, '155254.236'), (1, '160650.698')]
+-[2023-09-19 11:24:02,046][73131] Saving new best policy, reward=160650.698!
+-[2023-09-19 11:24:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6207.0). Total num frames: 4050944. Throughput: 0: 2980.8, 1: 2979.8. Samples: 1603390. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:07,044][72530] Avg episode reward: [(0, '155932.263'), (1, '160981.958')]
+-[2023-09-19 11:24:07,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003936_2015232.pth...
+-[2023-09-19 11:24:07,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003976_2035712.pth...
+-[2023-09-19 11:24:07,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003800_1945600.pth
+-[2023-09-19 11:24:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003760_1925120.pth
+-[2023-09-19 11:24:07,062][73131] Saving new best policy, reward=160981.958!
+-[2023-09-19 11:24:10,788][73145] Updated weights for policy 0, policy_version 4000 (0.0014)
+-[2023-09-19 11:24:10,788][73219] Updated weights for policy 1, policy_version 3960 (0.0013)
+-[2023-09-19 11:24:12,043][72530] Fps is (10 sec: 5734.6, 60 sec: 6007.5, 300 sec: 6182.6). Total num frames: 4075520. Throughput: 0: 3006.8, 1: 3006.8. Samples: 1640028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:12,044][72530] Avg episode reward: [(0, '156741.192'), (1, '161232.794')]
+-[2023-09-19 11:24:12,051][73131] Saving new best policy, reward=161232.794!
+-[2023-09-19 11:24:17,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6219.9). Total num frames: 4116480. Throughput: 0: 3213.3, 1: 3213.3. Samples: 1680080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:17,044][72530] Avg episode reward: [(0, '158187.015'), (1, '161349.690')]
+-[2023-09-19 11:24:17,045][73131] Saving new best policy, reward=161349.690!
+-[2023-09-19 11:24:22,043][72530] Fps is (10 sec: 7372.6, 60 sec: 6144.0, 300 sec: 6225.9). Total num frames: 4149248. Throughput: 0: 3037.6, 1: 3037.4. Samples: 1701154. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:22,044][72530] Avg episode reward: [(0, '158725.033'), (1, '161643.895')]
+-[2023-09-19 11:24:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004032_2064384.pth...
+-[2023-09-19 11:24:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004072_2084864.pth...
+-[2023-09-19 11:24:22,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003848_1970176.pth
+-[2023-09-19 11:24:22,061][73131] Saving new best policy, reward=161643.895!
+-[2023-09-19 11:24:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003888_1990656.pth
+-[2023-09-19 11:24:23,177][73219] Updated weights for policy 1, policy_version 4040 (0.0014)
+-[2023-09-19 11:24:23,178][73145] Updated weights for policy 0, policy_version 4080 (0.0016)
+-[2023-09-19 11:24:27,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6202.5). Total num frames: 4173824. Throughput: 0: 3023.4, 1: 3023.4. Samples: 1737188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:27,044][72530] Avg episode reward: [(0, '155903.476'), (1, '161815.854')]
+-[2023-09-19 11:24:27,045][73131] Saving new best policy, reward=161815.854!
+-[2023-09-19 11:24:32,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6237.4). Total num frames: 4214784. Throughput: 0: 3098.6, 1: 3097.1. Samples: 1777900. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:24:32,044][72530] Avg episode reward: [(0, '154152.668'), (1, '161862.881')]
+-[2023-09-19 11:24:32,045][73131] Saving new best policy, reward=161862.881!
+-[2023-09-19 11:24:36,067][73145] Updated weights for policy 0, policy_version 4160 (0.0013)
+-[2023-09-19 11:24:36,069][73219] Updated weights for policy 1, policy_version 4120 (0.0014)
+-[2023-09-19 11:24:37,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6214.6). Total num frames: 4239360. Throughput: 0: 3068.9, 1: 3068.7. Samples: 1794800. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:24:37,044][72530] Avg episode reward: [(0, '151755.204'), (1, '161941.149')]
+-[2023-09-19 11:24:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004160_2129920.pth...
+-[2023-09-19 11:24:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004120_2109440.pth...
+-[2023-09-19 11:24:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003976_2035712.pth
+-[2023-09-19 11:24:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003936_2015232.pth
+-[2023-09-19 11:24:37,065][73131] Saving new best policy, reward=161941.149!
+-[2023-09-19 11:24:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6220.4). Total num frames: 4272128. Throughput: 0: 3155.4, 1: 3155.3. Samples: 1835558. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:24:42,044][72530] Avg episode reward: [(0, '150680.731'), (1, '161901.771')]
+-[2023-09-19 11:24:47,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.6, 300 sec: 6275.9). Total num frames: 4304896. Throughput: 0: 3207.8, 1: 3207.7. Samples: 1872614. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:47,044][72530] Avg episode reward: [(0, '148141.874'), (1, '161823.095')]
+-[2023-09-19 11:24:48,828][73219] Updated weights for policy 1, policy_version 4200 (0.0010)
+-[2023-09-19 11:24:48,829][73145] Updated weights for policy 0, policy_version 4240 (0.0014)
+-[2023-09-19 11:24:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6303.7). Total num frames: 4337664. Throughput: 0: 3210.0, 1: 3211.3. Samples: 1892352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:52,044][72530] Avg episode reward: [(0, '144621.889'), (1, '160527.319')]
+-[2023-09-19 11:24:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004216_2158592.pth...
+-[2023-09-19 11:24:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004256_2179072.pth...
+-[2023-09-19 11:24:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004032_2064384.pth
+-[2023-09-19 11:24:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004072_2084864.pth
+-[2023-09-19 11:24:57,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6289.8). Total num frames: 4370432. Throughput: 0: 3240.7, 1: 3240.7. Samples: 1931690. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:57,044][72530] Avg episode reward: [(0, '144800.686'), (1, '160295.845')]
+-[2023-09-19 11:25:01,923][73219] Updated weights for policy 1, policy_version 4280 (0.0013)
+-[2023-09-19 11:25:01,923][73145] Updated weights for policy 0, policy_version 4320 (0.0013)
+-[2023-09-19 11:25:02,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6275.9). Total num frames: 4403200. Throughput: 0: 3184.6, 1: 3184.7. Samples: 1966700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:02,044][72530] Avg episode reward: [(0, '145084.319'), (1, '160219.957')]
+-[2023-09-19 11:25:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 4427776. Throughput: 0: 3125.7, 1: 3127.1. Samples: 1982528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:07,045][72530] Avg episode reward: [(0, '144470.225'), (1, '159962.850')]
+-[2023-09-19 11:25:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004304_2203648.pth...
+-[2023-09-19 11:25:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004344_2224128.pth...
+-[2023-09-19 11:25:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004120_2109440.pth
+-[2023-09-19 11:25:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004160_2129920.pth
+-[2023-09-19 11:25:12,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4460544. Throughput: 0: 3189.5, 1: 3189.4. Samples: 2024240. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:25:12,044][72530] Avg episode reward: [(0, '144911.603'), (1, '159940.569')]
+-[2023-09-19 11:25:14,575][73145] Updated weights for policy 0, policy_version 4400 (0.0013)
+-[2023-09-19 11:25:14,577][73219] Updated weights for policy 1, policy_version 4360 (0.0014)
+-[2023-09-19 11:25:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 4493312. Throughput: 0: 3180.8, 1: 3181.4. Samples: 2064198. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:17,044][72530] Avg episode reward: [(0, '140838.640'), (1, '160023.760')]
+-[2023-09-19 11:25:22,043][72530] Fps is (10 sec: 7372.7, 60 sec: 6417.1, 300 sec: 6275.9). Total num frames: 4534272. Throughput: 0: 3210.7, 1: 3210.9. Samples: 2083770. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:22,044][72530] Avg episode reward: [(0, '145736.624'), (1, '161193.551')]
+-[2023-09-19 11:25:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004408_2256896.pth...
+-[2023-09-19 11:25:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004448_2277376.pth...
+-[2023-09-19 11:25:22,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004256_2179072.pth
+-[2023-09-19 11:25:22,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004216_2158592.pth
+-[2023-09-19 11:25:27,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4558848. Throughput: 0: 3177.1, 1: 3178.3. Samples: 2121554. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:27,044][72530] Avg episode reward: [(0, '146210.154'), (1, '161328.801')]
+-[2023-09-19 11:25:27,759][73219] Updated weights for policy 1, policy_version 4440 (0.0013)
+-[2023-09-19 11:25:27,759][73145] Updated weights for policy 0, policy_version 4480 (0.0013)
+-[2023-09-19 11:25:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 4591616. Throughput: 0: 3156.1, 1: 3156.0. Samples: 2156656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:32,044][72530] Avg episode reward: [(0, '148003.467'), (1, '161381.807')]
+-[2023-09-19 11:25:37,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4624384. Throughput: 0: 3173.7, 1: 3172.3. Samples: 2177924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:37,044][72530] Avg episode reward: [(0, '152496.039'), (1, '161644.736')]
+-[2023-09-19 11:25:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004496_2301952.pth...
+-[2023-09-19 11:25:37,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004536_2322432.pth...
+-[2023-09-19 11:25:37,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004304_2203648.pth
+-[2023-09-19 11:25:37,071][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004344_2224128.pth
+-[2023-09-19 11:25:40,045][73219] Updated weights for policy 1, policy_version 4520 (0.0014)
+-[2023-09-19 11:25:40,045][73145] Updated weights for policy 0, policy_version 4560 (0.0014)
+-[2023-09-19 11:25:42,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4657152. Throughput: 0: 3196.5, 1: 3196.4. Samples: 2219366. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:25:42,044][72530] Avg episode reward: [(0, '151440.031'), (1, '161613.003')]
+-[2023-09-19 11:25:47,043][72530] Fps is (10 sec: 6553.8, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4689920. Throughput: 0: 3225.5, 1: 3225.4. Samples: 2256988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:47,044][72530] Avg episode reward: [(0, '155863.155'), (1, '161674.332')]
+-[2023-09-19 11:25:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4722688. Throughput: 0: 3263.8, 1: 3262.1. Samples: 2276194. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:52,044][72530] Avg episode reward: [(0, '154315.726'), (1, '161202.405')]
+-[2023-09-19 11:25:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004592_2351104.pth...
+-[2023-09-19 11:25:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004632_2371584.pth...
+-[2023-09-19 11:25:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004408_2256896.pth
+-[2023-09-19 11:25:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004448_2277376.pth
+-[2023-09-19 11:25:52,782][73219] Updated weights for policy 1, policy_version 4600 (0.0014)
+-[2023-09-19 11:25:52,782][73145] Updated weights for policy 0, policy_version 4640 (0.0014)
+-[2023-09-19 11:25:57,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4755456. Throughput: 0: 3211.2, 1: 3211.4. Samples: 2313256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:57,044][72530] Avg episode reward: [(0, '150010.060'), (1, '160917.790')]
+-[2023-09-19 11:26:02,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4788224. Throughput: 0: 3193.2, 1: 3192.7. Samples: 2351560. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:26:02,045][72530] Avg episode reward: [(0, '150263.831'), (1, '161029.917')]
+-[2023-09-19 11:26:05,903][73219] Updated weights for policy 1, policy_version 4680 (0.0013)
+-[2023-09-19 11:26:05,903][73145] Updated weights for policy 0, policy_version 4720 (0.0012)
+-[2023-09-19 11:26:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6417.1, 300 sec: 6220.4). Total num frames: 4812800. Throughput: 0: 3179.7, 1: 3179.7. Samples: 2369942. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:07,044][72530] Avg episode reward: [(0, '146564.474'), (1, '161044.989')]
+-[2023-09-19 11:26:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004680_2396160.pth...
+-[2023-09-19 11:26:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004720_2416640.pth...
+-[2023-09-19 11:26:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004536_2322432.pth
+-[2023-09-19 11:26:07,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004496_2301952.pth
+-[2023-09-19 11:26:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6417.0, 300 sec: 6220.4). Total num frames: 4845568. Throughput: 0: 3166.9, 1: 3166.1. Samples: 2406540. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:26:12,045][72530] Avg episode reward: [(0, '146583.424'), (1, '161100.378')]
+-[2023-09-19 11:26:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 4870144. Throughput: 0: 3143.0, 1: 3143.1. Samples: 2439528. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:26:17,044][72530] Avg episode reward: [(0, '141842.532'), (1, '161215.328')]
+-[2023-09-19 11:26:19,884][73219] Updated weights for policy 1, policy_version 4760 (0.0016)
+-[2023-09-19 11:26:19,884][73145] Updated weights for policy 0, policy_version 4800 (0.0015)
+-[2023-09-19 11:26:22,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6220.4). Total num frames: 4902912. Throughput: 0: 3118.8, 1: 3118.8. Samples: 2458616. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:26:22,044][72530] Avg episode reward: [(0, '142452.610'), (1, '161748.126')]
+-[2023-09-19 11:26:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004768_2441216.pth...
+-[2023-09-19 11:26:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004808_2461696.pth...
+-[2023-09-19 11:26:22,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004592_2351104.pth
+-[2023-09-19 11:26:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004632_2371584.pth
+-[2023-09-19 11:26:27,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 4935680. Throughput: 0: 3120.4, 1: 3120.6. Samples: 2500210. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:26:27,044][72530] Avg episode reward: [(0, '137895.579'), (1, '162103.130')]
+-[2023-09-19 11:26:27,045][73131] Saving new best policy, reward=162103.130!
+-[2023-09-19 11:26:32,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 4968448. Throughput: 0: 3138.1, 1: 3139.4. Samples: 2539476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:32,044][72530] Avg episode reward: [(0, '135551.322'), (1, '162133.015')]
+-[2023-09-19 11:26:32,045][73131] Saving new best policy, reward=162133.015!
+-[2023-09-19 11:26:32,157][73219] Updated weights for policy 1, policy_version 4840 (0.0010)
+-[2023-09-19 11:26:32,158][73145] Updated weights for policy 0, policy_version 4880 (0.0012)
+-[2023-09-19 11:26:37,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 5001216. Throughput: 0: 3107.1, 1: 3108.5. Samples: 2555894. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:26:37,044][72530] Avg episode reward: [(0, '131208.771'), (1, '162213.080')]
+-[2023-09-19 11:26:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004904_2510848.pth...
+-[2023-09-19 11:26:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004864_2490368.pth...
+-[2023-09-19 11:26:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004680_2396160.pth
+-[2023-09-19 11:26:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004720_2416640.pth
+-[2023-09-19 11:26:37,065][73131] Saving new best policy, reward=162213.080!
+-[2023-09-19 11:26:42,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5033984. Throughput: 0: 3145.9, 1: 3145.9. Samples: 2596386. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:42,044][72530] Avg episode reward: [(0, '130942.941'), (1, '162247.080')]
+-[2023-09-19 11:26:42,045][73131] Saving new best policy, reward=162247.080!
+-[2023-09-19 11:26:44,999][73145] Updated weights for policy 0, policy_version 4960 (0.0011)
+-[2023-09-19 11:26:44,999][73219] Updated weights for policy 1, policy_version 4920 (0.0015)
+-[2023-09-19 11:26:47,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5066752. Throughput: 0: 3150.9, 1: 3150.9. Samples: 2635140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:47,044][72530] Avg episode reward: [(0, '129912.953'), (1, '162118.110')]
+-[2023-09-19 11:26:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5099520. Throughput: 0: 3158.5, 1: 3159.3. Samples: 2654242. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:52,044][72530] Avg episode reward: [(0, '128999.147'), (1, '162160.112')]
+-[2023-09-19 11:26:52,050][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005000_2560000.pth...
+-[2023-09-19 11:26:52,050][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004960_2539520.pth...
+-[2023-09-19 11:26:52,057][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004808_2461696.pth
+-[2023-09-19 11:26:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004768_2441216.pth
+-[2023-09-19 11:26:57,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5132288. Throughput: 0: 3168.7, 1: 3168.5. Samples: 2691716. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:26:57,045][72530] Avg episode reward: [(0, '133141.196'), (1, '161915.344')]
+-[2023-09-19 11:26:57,786][73219] Updated weights for policy 1, policy_version 5000 (0.0015)
+-[2023-09-19 11:26:57,787][73145] Updated weights for policy 0, policy_version 5040 (0.0011)
+-[2023-09-19 11:27:02,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5165056. Throughput: 0: 3210.7, 1: 3210.9. Samples: 2728500. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:27:02,044][72530] Avg episode reward: [(0, '134217.012'), (1, '161927.050')]
+-[2023-09-19 11:27:07,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 5189632. Throughput: 0: 3215.4, 1: 3215.5. Samples: 2748004. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:27:07,044][72530] Avg episode reward: [(0, '139484.494'), (1, '161928.042')]
+-[2023-09-19 11:27:07,058][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005056_2588672.pth...
+-[2023-09-19 11:27:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004864_2490368.pth
+-[2023-09-19 11:27:07,070][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005096_2609152.pth...
+-[2023-09-19 11:27:07,073][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004904_2510848.pth
+-[2023-09-19 11:27:10,937][73145] Updated weights for policy 0, policy_version 5120 (0.0015)
+-[2023-09-19 11:27:10,937][73219] Updated weights for policy 1, policy_version 5080 (0.0015)
+-[2023-09-19 11:27:12,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6280.6, 300 sec: 6248.1). Total num frames: 5222400. Throughput: 0: 3173.6, 1: 3173.6. Samples: 2785834. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:27:12,044][72530] Avg episode reward: [(0, '140906.115'), (1, '161939.285')]
+-[2023-09-19 11:27:17,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 5255168. Throughput: 0: 3151.1, 1: 3149.6. Samples: 2823006. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:17,045][72530] Avg episode reward: [(0, '145817.026'), (1, '161027.902')]
+-[2023-09-19 11:27:22,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 5287936. Throughput: 0: 3185.7, 1: 3185.7. Samples: 2842604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:22,044][72530] Avg episode reward: [(0, '142531.824'), (1, '161093.623')]
+-[2023-09-19 11:27:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005184_2654208.pth...
+-[2023-09-19 11:27:22,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005144_2633728.pth...
+-[2023-09-19 11:27:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005000_2560000.pth
+-[2023-09-19 11:27:22,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004960_2539520.pth
+-[2023-09-19 11:27:23,721][73145] Updated weights for policy 0, policy_version 5200 (0.0010)
+-[2023-09-19 11:27:23,721][73219] Updated weights for policy 1, policy_version 5160 (0.0013)
+-[2023-09-19 11:27:27,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 5320704. Throughput: 0: 3188.8, 1: 3189.0. Samples: 2883390. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:27:27,044][72530] Avg episode reward: [(0, '142889.954'), (1, '161067.955')]
+-[2023-09-19 11:27:32,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.0, 300 sec: 6248.1). Total num frames: 5353472. Throughput: 0: 3127.8, 1: 3128.0. Samples: 2916652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:32,044][72530] Avg episode reward: [(0, '142889.954'), (1, '161121.140')]
+-[2023-09-19 11:27:37,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 5378048. Throughput: 0: 3133.1, 1: 3132.4. Samples: 2936188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:37,045][72530] Avg episode reward: [(0, '142062.299'), (1, '159603.215')]
+-[2023-09-19 11:27:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005232_2678784.pth...
+-[2023-09-19 11:27:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005272_2699264.pth...
+-[2023-09-19 11:27:37,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005056_2588672.pth
+-[2023-09-19 11:27:37,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005096_2609152.pth
+-[2023-09-19 11:27:37,396][73145] Updated weights for policy 0, policy_version 5280 (0.0011)
+-[2023-09-19 11:27:37,396][73219] Updated weights for policy 1, policy_version 5240 (0.0014)
+-[2023-09-19 11:27:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5410816. Throughput: 0: 3131.2, 1: 3132.0. Samples: 2973558. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:42,045][72530] Avg episode reward: [(0, '142062.299'), (1, '159574.648')]
+-[2023-09-19 11:27:47,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5443584. Throughput: 0: 3132.0, 1: 3132.0. Samples: 3010382. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:27:47,045][72530] Avg episode reward: [(0, '143548.226'), (1, '160565.889')]
+-[2023-09-19 11:27:50,044][73145] Updated weights for policy 0, policy_version 5360 (0.0013)
+-[2023-09-19 11:27:50,045][73219] Updated weights for policy 1, policy_version 5320 (0.0012)
+-[2023-09-19 11:27:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 5476352. Throughput: 0: 3144.9, 1: 3145.5. Samples: 3031074. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:52,044][72530] Avg episode reward: [(0, '143548.226'), (1, '160563.875')]
+-[2023-09-19 11:27:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005368_2748416.pth...
+-[2023-09-19 11:27:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005328_2727936.pth...
+-[2023-09-19 11:27:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005184_2654208.pth
+-[2023-09-19 11:27:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005144_2633728.pth
+-[2023-09-19 11:27:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 5500928. Throughput: 0: 3089.5, 1: 3090.1. Samples: 3063918. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:57,045][72530] Avg episode reward: [(0, '146270.433'), (1, '160418.331')]
+-[2023-09-19 11:28:02,043][72530] Fps is (10 sec: 5734.6, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5533696. Throughput: 0: 3077.2, 1: 3077.4. Samples: 3099964. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:28:02,044][72530] Avg episode reward: [(0, '146167.425'), (1, '160418.331')]
+-[2023-09-19 11:28:04,104][73219] Updated weights for policy 1, policy_version 5400 (0.0013)
+-[2023-09-19 11:28:04,105][73145] Updated weights for policy 0, policy_version 5440 (0.0014)
+-[2023-09-19 11:28:07,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 5566464. Throughput: 0: 3076.4, 1: 3075.6. Samples: 3119446. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:07,044][72530] Avg episode reward: [(0, '146743.667'), (1, '161871.065')]
+-[2023-09-19 11:28:07,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005456_2793472.pth...
+-[2023-09-19 11:28:07,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005416_2772992.pth...
+-[2023-09-19 11:28:07,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005272_2699264.pth
+-[2023-09-19 11:28:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005232_2678784.pth
+-[2023-09-19 11:28:12,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 5599232. Throughput: 0: 3039.7, 1: 3039.5. Samples: 3156956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:12,044][72530] Avg episode reward: [(0, '146503.770'), (1, '161818.415')]
+-[2023-09-19 11:28:17,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 5623808. Throughput: 0: 2895.2, 1: 2895.1. Samples: 3177218. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:28:17,044][72530] Avg episode reward: [(0, '146720.459'), (1, '161769.023')]
+-[2023-09-19 11:28:17,068][73145] Updated weights for policy 0, policy_version 5520 (0.0013)
+-[2023-09-19 11:28:17,069][73219] Updated weights for policy 1, policy_version 5480 (0.0012)
+-[2023-09-19 11:28:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 5656576. Throughput: 0: 3086.3, 1: 3086.2. Samples: 3213950. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:28:22,044][72530] Avg episode reward: [(0, '147474.306'), (1, '161768.790')]
+-[2023-09-19 11:28:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005504_2818048.pth...
+-[2023-09-19 11:28:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005544_2838528.pth...
+-[2023-09-19 11:28:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005328_2727936.pth
+-[2023-09-19 11:28:22,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005368_2748416.pth
+-[2023-09-19 11:28:27,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5689344. Throughput: 0: 3045.5, 1: 3044.6. Samples: 3247612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:27,044][72530] Avg episode reward: [(0, '146171.268'), (1, '161578.478')]
+-[2023-09-19 11:28:30,639][73219] Updated weights for policy 1, policy_version 5560 (0.0007)
+-[2023-09-19 11:28:30,640][73145] Updated weights for policy 0, policy_version 5600 (0.0014)
+-[2023-09-19 11:28:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6248.1). Total num frames: 5713920. Throughput: 0: 3050.4, 1: 3051.6. Samples: 3284968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:32,044][72530] Avg episode reward: [(0, '143678.262'), (1, '161606.329')]
+-[2023-09-19 11:28:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 5746688. Throughput: 0: 3003.7, 1: 3003.7. Samples: 3301410. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:37,044][72530] Avg episode reward: [(0, '147339.327'), (1, '161677.535')]
+-[2023-09-19 11:28:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005632_2883584.pth...
+-[2023-09-19 11:28:37,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005592_2863104.pth...
+-[2023-09-19 11:28:37,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005456_2793472.pth
+-[2023-09-19 11:28:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005416_2772992.pth
+-[2023-09-19 11:28:42,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5779456. Throughput: 0: 3087.8, 1: 3087.2. Samples: 3341792. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:28:42,044][72530] Avg episode reward: [(0, '149917.742'), (1, '161865.342')]
+-[2023-09-19 11:28:43,733][73145] Updated weights for policy 0, policy_version 5680 (0.0015)
+-[2023-09-19 11:28:43,734][73219] Updated weights for policy 1, policy_version 5640 (0.0014)
+-[2023-09-19 11:28:47,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5812224. Throughput: 0: 3101.5, 1: 3101.5. Samples: 3379098. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:47,044][72530] Avg episode reward: [(0, '150038.622'), (1, '161982.019')]
+-[2023-09-19 11:28:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5844992. Throughput: 0: 3141.9, 1: 3141.4. Samples: 3402194. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:28:52,044][72530] Avg episode reward: [(0, '144197.749'), (1, '162024.019')]
+-[2023-09-19 11:28:52,065][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005696_2916352.pth...
+-[2023-09-19 11:28:52,067][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005736_2936832.pth...
+-[2023-09-19 11:28:52,069][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005504_2818048.pth
+-[2023-09-19 11:28:52,072][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005544_2838528.pth
+-[2023-09-19 11:28:56,545][73145] Updated weights for policy 0, policy_version 5760 (0.0009)
+-[2023-09-19 11:28:56,546][73219] Updated weights for policy 1, policy_version 5720 (0.0014)
+-[2023-09-19 11:28:57,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6303.7). Total num frames: 5877760. Throughput: 0: 3141.5, 1: 3142.4. Samples: 3439730. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:57,044][72530] Avg episode reward: [(0, '138885.538'), (1, '162345.734')]
+-[2023-09-19 11:28:57,045][73131] Saving new best policy, reward=162345.734!
+-[2023-09-19 11:29:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5902336. Throughput: 0: 3289.1, 1: 3289.5. Samples: 3473254. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:02,044][72530] Avg episode reward: [(0, '134517.899'), (1, '162329.045')]
+-[2023-09-19 11:29:07,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6331.4). Total num frames: 5943296. Throughput: 0: 3101.0, 1: 3100.8. Samples: 3493030. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:07,045][72530] Avg episode reward: [(0, '128642.101'), (1, '162318.341')]
+-[2023-09-19 11:29:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005784_2961408.pth...
+-[2023-09-19 11:29:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005824_2981888.pth...
+-[2023-09-19 11:29:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005592_2863104.pth
+-[2023-09-19 11:29:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005632_2883584.pth
+-[2023-09-19 11:29:09,339][73145] Updated weights for policy 0, policy_version 5840 (0.0012)
+-[2023-09-19 11:29:09,340][73219] Updated weights for policy 1, policy_version 5800 (0.0013)
+-[2023-09-19 11:29:12,043][72530] Fps is (10 sec: 7372.7, 60 sec: 6280.5, 300 sec: 6303.7). Total num frames: 5976064. Throughput: 0: 3166.1, 1: 3166.1. Samples: 3532560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:12,044][72530] Avg episode reward: [(0, '118954.396'), (1, '162291.376')]
+-[2023-09-19 11:29:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6303.7). Total num frames: 6008832. Throughput: 0: 3187.8, 1: 3186.9. Samples: 3571832. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:29:17,044][72530] Avg episode reward: [(0, '114412.470'), (1, '162295.847')]
+-[2023-09-19 11:29:21,826][73145] Updated weights for policy 0, policy_version 5920 (0.0012)
+-[2023-09-19 11:29:21,826][73219] Updated weights for policy 1, policy_version 5880 (0.0015)
+-[2023-09-19 11:29:22,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6331.4). Total num frames: 6041600. Throughput: 0: 3238.0, 1: 3237.2. Samples: 3592796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:22,044][72530] Avg episode reward: [(0, '112785.270'), (1, '162279.161')]
+-[2023-09-19 11:29:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005880_3010560.pth...
+-[2023-09-19 11:29:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005920_3031040.pth...
+-[2023-09-19 11:29:22,057][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005696_2916352.pth
+-[2023-09-19 11:29:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005736_2936832.pth
+-[2023-09-19 11:29:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 6066176. Throughput: 0: 3176.2, 1: 3176.2. Samples: 3627652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:27,044][72530] Avg episode reward: [(0, '112913.414'), (1, '161752.422')]
+-[2023-09-19 11:29:32,053][72530] Fps is (10 sec: 5728.9, 60 sec: 6416.0, 300 sec: 6303.5). Total num frames: 6098944. Throughput: 0: 3140.7, 1: 3142.2. Samples: 3661888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:32,055][72530] Avg episode reward: [(0, '114352.426'), (1, '160799.718')]
+-[2023-09-19 11:29:36,186][73145] Updated weights for policy 0, policy_version 6000 (0.0013)
+-[2023-09-19 11:29:36,187][73219] Updated weights for policy 1, policy_version 5960 (0.0013)
+-[2023-09-19 11:29:37,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 6123520. Throughput: 0: 3071.6, 1: 3072.0. Samples: 3678658. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:37,044][72530] Avg episode reward: [(0, '114436.532'), (1, '160786.962')]
+-[2023-09-19 11:29:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005960_3051520.pth...
+-[2023-09-19 11:29:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006000_3072000.pth...
+-[2023-09-19 11:29:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005784_2961408.pth
+-[2023-09-19 11:29:37,067][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005824_2981888.pth
+-[2023-09-19 11:29:42,043][72530] Fps is (10 sec: 5740.0, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 6156288. Throughput: 0: 3094.3, 1: 3094.0. Samples: 3718202. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:42,044][72530] Avg episode reward: [(0, '115826.562'), (1, '160797.026')]
+-[2023-09-19 11:29:47,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 6189056. Throughput: 0: 3107.9, 1: 3107.4. Samples: 3752942. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:29:47,044][72530] Avg episode reward: [(0, '116442.200'), (1, '160802.531')]
+-[2023-09-19 11:29:49,303][73219] Updated weights for policy 1, policy_version 6040 (0.0013)
+-[2023-09-19 11:29:49,304][73145] Updated weights for policy 0, policy_version 6080 (0.0015)
+-[2023-09-19 11:29:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 6213632. Throughput: 0: 3115.6, 1: 3116.0. Samples: 3773450. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:29:52,044][72530] Avg episode reward: [(0, '116782.945'), (1, '160812.704')]
+-[2023-09-19 11:29:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006048_3096576.pth...
+-[2023-09-19 11:29:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006088_3117056.pth...
+-[2023-09-19 11:29:52,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005880_3010560.pth
+-[2023-09-19 11:29:52,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005920_3031040.pth
+-[2023-09-19 11:29:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 6246400. Throughput: 0: 3059.6, 1: 3059.6. Samples: 3807922. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:57,044][72530] Avg episode reward: [(0, '116782.945'), (1, '160801.177')]
+-[2023-09-19 11:30:02,043][72530] Fps is (10 sec: 6144.0, 60 sec: 6212.2, 300 sec: 6262.0). Total num frames: 6275072. Throughput: 0: 2823.3, 1: 2823.1. Samples: 3825920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:02,045][72530] Avg episode reward: [(0, '113033.870'), (1, '161341.845')]
+-[2023-09-19 11:30:03,323][73145] Updated weights for policy 0, policy_version 6160 (0.0013)
+-[2023-09-19 11:30:03,323][73219] Updated weights for policy 1, policy_version 6120 (0.0015)
+-[2023-09-19 11:30:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6248.1). Total num frames: 6303744. Throughput: 0: 2978.1, 1: 2978.2. Samples: 3860830. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:07,045][72530] Avg episode reward: [(0, '113033.870'), (1, '161341.845')]
+-[2023-09-19 11:30:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006136_3141632.pth...
+-[2023-09-19 11:30:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006176_3162112.pth...
+-[2023-09-19 11:30:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006000_3072000.pth
+-[2023-09-19 11:30:07,066][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005960_3051520.pth
+-[2023-09-19 11:30:12,043][72530] Fps is (10 sec: 6144.1, 60 sec: 6007.5, 300 sec: 6248.1). Total num frames: 6336512. Throughput: 0: 3016.4, 1: 3017.1. Samples: 3899160. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:30:12,044][72530] Avg episode reward: [(0, '110251.349'), (1, '161327.497')]
+-[2023-09-19 11:30:16,823][73219] Updated weights for policy 1, policy_version 6200 (0.0013)
+-[2023-09-19 11:30:16,823][73145] Updated weights for policy 0, policy_version 6240 (0.0011)
+-[2023-09-19 11:30:17,043][72530] Fps is (10 sec: 6553.8, 60 sec: 6007.5, 300 sec: 6220.4). Total num frames: 6369280. Throughput: 0: 3019.8, 1: 3018.5. Samples: 3933552. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:30:17,044][72530] Avg episode reward: [(0, '110867.577'), (1, '161327.497')]
+-[2023-09-19 11:30:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5870.9, 300 sec: 6220.4). Total num frames: 6393856. Throughput: 0: 3036.0, 1: 3036.0. Samples: 3951900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:22,044][72530] Avg episode reward: [(0, '112712.732'), (1, '161204.256')]
+-[2023-09-19 11:30:22,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006264_3207168.pth...
+-[2023-09-19 11:30:22,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006224_3186688.pth...
+-[2023-09-19 11:30:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006088_3117056.pth
+-[2023-09-19 11:30:22,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006048_3096576.pth
+-[2023-09-19 11:30:27,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5870.9, 300 sec: 6192.6). Total num frames: 6418432. Throughput: 0: 2950.9, 1: 2950.4. Samples: 3983760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:27,044][72530] Avg episode reward: [(0, '113392.546'), (1, '161125.113')]
+-[2023-09-19 11:30:31,119][73145] Updated weights for policy 0, policy_version 6320 (0.0012)
+-[2023-09-19 11:30:31,119][73219] Updated weights for policy 1, policy_version 6280 (0.0013)
+-[2023-09-19 11:30:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5871.9, 300 sec: 6192.6). Total num frames: 6451200. Throughput: 0: 2960.9, 1: 2961.4. Samples: 4019448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:32,044][72530] Avg episode reward: [(0, '113475.235'), (1, '161107.375')]
+-[2023-09-19 11:30:37,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5870.9, 300 sec: 6164.8). Total num frames: 6475776. Throughput: 0: 2884.0, 1: 2883.7. Samples: 4032994. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:37,045][72530] Avg episode reward: [(0, '118367.276'), (1, '160625.932')]
+-[2023-09-19 11:30:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006344_3248128.pth...
+-[2023-09-19 11:30:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006304_3227648.pth...
+-[2023-09-19 11:30:37,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006176_3162112.pth
+-[2023-09-19 11:30:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006136_3141632.pth
+-[2023-09-19 11:30:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6164.8). Total num frames: 6508544. Throughput: 0: 2926.3, 1: 2927.1. Samples: 4071324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:42,044][72530] Avg episode reward: [(0, '121712.371'), (1, '160963.772')]
+-[2023-09-19 11:30:44,991][73145] Updated weights for policy 0, policy_version 6400 (0.0014)
+-[2023-09-19 11:30:44,991][73219] Updated weights for policy 1, policy_version 6360 (0.0016)
+-[2023-09-19 11:30:47,043][72530] Fps is (10 sec: 6553.7, 60 sec: 5870.9, 300 sec: 6164.8). Total num frames: 6541312. Throughput: 0: 3155.9, 1: 3155.8. Samples: 4109948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:47,044][72530] Avg episode reward: [(0, '130906.514'), (1, '160996.680')]
+-[2023-09-19 11:30:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6007.5, 300 sec: 6164.8). Total num frames: 6574080. Throughput: 0: 2977.7, 1: 2978.5. Samples: 4128860. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:30:52,044][72530] Avg episode reward: [(0, '132721.030'), (1, '160740.250')]
+-[2023-09-19 11:30:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006400_3276800.pth...
+-[2023-09-19 11:30:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006440_3297280.pth...
+-[2023-09-19 11:30:52,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006264_3207168.pth
+-[2023-09-19 11:30:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006224_3186688.pth
+-[2023-09-19 11:30:57,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6007.5, 300 sec: 6164.8). Total num frames: 6606848. Throughput: 0: 2999.1, 1: 2998.3. Samples: 4169040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:57,044][72530] Avg episode reward: [(0, '135319.795'), (1, '160381.100')]
+-[2023-09-19 11:30:57,551][73145] Updated weights for policy 0, policy_version 6480 (0.0013)
+-[2023-09-19 11:30:57,551][73219] Updated weights for policy 1, policy_version 6440 (0.0014)
+-[2023-09-19 11:31:02,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6075.8, 300 sec: 6192.6). Total num frames: 6639616. Throughput: 0: 2999.7, 1: 2999.9. Samples: 4203534. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:02,044][72530] Avg episode reward: [(0, '138147.376'), (1, '160443.505')]
+-[2023-09-19 11:31:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6164.8). Total num frames: 6664192. Throughput: 0: 2995.4, 1: 2995.4. Samples: 4221484. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:31:07,044][72530] Avg episode reward: [(0, '140607.383'), (1, '160444.041')]
+-[2023-09-19 11:31:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006488_3321856.pth...
+-[2023-09-19 11:31:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006528_3342336.pth...
+-[2023-09-19 11:31:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006304_3227648.pth
+-[2023-09-19 11:31:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006344_3248128.pth
+-[2023-09-19 11:31:11,438][73219] Updated weights for policy 1, policy_version 6520 (0.0012)
+-[2023-09-19 11:31:11,438][73145] Updated weights for policy 0, policy_version 6560 (0.0013)
+-[2023-09-19 11:31:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6192.6). Total num frames: 6696960. Throughput: 0: 3048.7, 1: 3048.4. Samples: 4258132. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:31:12,044][72530] Avg episode reward: [(0, '140794.377'), (1, '161324.369')]
+-[2023-09-19 11:31:17,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6007.4, 300 sec: 6192.6). Total num frames: 6729728. Throughput: 0: 3077.7, 1: 3077.3. Samples: 4296424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:17,045][72530] Avg episode reward: [(0, '146158.608'), (1, '161421.999')]
+-[2023-09-19 11:31:22,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6192.6). Total num frames: 6762496. Throughput: 0: 3152.2, 1: 3152.3. Samples: 4316696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:22,044][72530] Avg episode reward: [(0, '147169.785'), (1, '161725.816')]
+-[2023-09-19 11:31:22,057][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006624_3391488.pth...
+-[2023-09-19 11:31:22,057][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006584_3371008.pth...
+-[2023-09-19 11:31:22,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006400_3276800.pth
+-[2023-09-19 11:31:22,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006440_3297280.pth
+-[2023-09-19 11:31:24,435][73145] Updated weights for policy 0, policy_version 6640 (0.0016)
+-[2023-09-19 11:31:24,436][73219] Updated weights for policy 1, policy_version 6600 (0.0016)
+-[2023-09-19 11:31:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6164.8). Total num frames: 6787072. Throughput: 0: 3107.4, 1: 3106.5. Samples: 4350952. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:31:27,044][72530] Avg episode reward: [(0, '147753.216'), (1, '161687.670')]
+-[2023-09-19 11:31:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6164.8). Total num frames: 6819840. Throughput: 0: 3071.0, 1: 3071.2. Samples: 4386346. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:31:32,044][72530] Avg episode reward: [(0, '147753.216'), (1, '161687.670')]
+-[2023-09-19 11:31:37,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6164.8). Total num frames: 6852608. Throughput: 0: 3060.3, 1: 3059.2. Samples: 4404236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:37,044][72530] Avg episode reward: [(0, '155757.680'), (1, '162057.882')]
+-[2023-09-19 11:31:37,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006672_3416064.pth...
+-[2023-09-19 11:31:37,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006712_3436544.pth...
+-[2023-09-19 11:31:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006528_3342336.pth
+-[2023-09-19 11:31:37,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006488_3321856.pth
+-[2023-09-19 11:31:38,241][73145] Updated weights for policy 0, policy_version 6720 (0.0015)
+-[2023-09-19 11:31:38,242][73219] Updated weights for policy 1, policy_version 6680 (0.0014)
+-[2023-09-19 11:31:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 6877184. Throughput: 0: 3009.5, 1: 3010.6. Samples: 4439946. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:42,045][72530] Avg episode reward: [(0, '155757.680'), (1, '162057.882')]
+-[2023-09-19 11:31:47,043][72530] Fps is (10 sec: 5734.6, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 6909952. Throughput: 0: 3026.3, 1: 3026.0. Samples: 4475886. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:31:47,044][72530] Avg episode reward: [(0, '156604.047'), (1, '162030.805')]
+-[2023-09-19 11:31:51,596][73145] Updated weights for policy 0, policy_version 6800 (0.0012)
+-[2023-09-19 11:31:51,596][73219] Updated weights for policy 1, policy_version 6760 (0.0015)
+-[2023-09-19 11:31:52,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 6942720. Throughput: 0: 3052.5, 1: 3052.3. Samples: 4496200. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:31:52,044][72530] Avg episode reward: [(0, '154864.725'), (1, '162040.931')]
+-[2023-09-19 11:31:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006800_3481600.pth...
+-[2023-09-19 11:31:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006760_3461120.pth...
+-[2023-09-19 11:31:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006624_3391488.pth
+-[2023-09-19 11:31:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006584_3371008.pth
+-[2023-09-19 11:31:57,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 6975488. Throughput: 0: 3054.7, 1: 3054.8. Samples: 4533058. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:31:57,044][72530] Avg episode reward: [(0, '150963.742'), (1, '162180.754')]
+-[2023-09-19 11:32:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6137.1). Total num frames: 7000064. Throughput: 0: 3051.5, 1: 3052.9. Samples: 4571120. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:32:02,044][72530] Avg episode reward: [(0, '150392.522'), (1, '162181.685')]
+-[2023-09-19 11:32:04,785][73145] Updated weights for policy 0, policy_version 6880 (0.0009)
+-[2023-09-19 11:32:04,786][73219] Updated weights for policy 1, policy_version 6840 (0.0010)
+-[2023-09-19 11:32:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 7032832. Throughput: 0: 3026.7, 1: 3026.7. Samples: 4589098. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:32:07,044][72530] Avg episode reward: [(0, '145583.491'), (1, '162297.023')]
+-[2023-09-19 11:32:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006848_3506176.pth...
+-[2023-09-19 11:32:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006888_3526656.pth...
+-[2023-09-19 11:32:07,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006672_3416064.pth
+-[2023-09-19 11:32:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006712_3436544.pth
+-[2023-09-19 11:32:12,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 7065600. Throughput: 0: 3022.0, 1: 3022.0. Samples: 4622936. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:12,045][72530] Avg episode reward: [(0, '144862.441'), (1, '162339.817')]
+-[2023-09-19 11:32:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6109.3). Total num frames: 7090176. Throughput: 0: 3051.5, 1: 3052.3. Samples: 4661014. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:17,045][72530] Avg episode reward: [(0, '140160.091'), (1, '162747.216')]
+-[2023-09-19 11:32:17,046][73131] Saving new best policy, reward=162747.216!
+-[2023-09-19 11:32:18,733][73145] Updated weights for policy 0, policy_version 6960 (0.0013)
+-[2023-09-19 11:32:18,734][73219] Updated weights for policy 1, policy_version 6920 (0.0014)
+-[2023-09-19 11:32:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6109.3). Total num frames: 7122944. Throughput: 0: 3035.2, 1: 3036.6. Samples: 4677464. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:22,045][72530] Avg episode reward: [(0, '138598.620'), (1, '162798.619')]
+-[2023-09-19 11:32:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006936_3551232.pth...
+-[2023-09-19 11:32:22,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006976_3571712.pth...
+-[2023-09-19 11:32:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006760_3461120.pth
+-[2023-09-19 11:32:22,063][73131] Saving new best policy, reward=162798.619!
+-[2023-09-19 11:32:22,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006800_3481600.pth
+-[2023-09-19 11:32:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6081.5). Total num frames: 7147520. Throughput: 0: 3005.6, 1: 3006.0. Samples: 4710464. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:32:27,044][72530] Avg episode reward: [(0, '140889.402'), (1, '162879.076')]
+-[2023-09-19 11:32:27,046][73131] Saving new best policy, reward=162879.076!
+-[2023-09-19 11:32:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.4, 300 sec: 6109.3). Total num frames: 7180288. Throughput: 0: 3006.3, 1: 3006.6. Samples: 4746466. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:32,045][72530] Avg episode reward: [(0, '146675.404'), (1, '162955.653')]
+-[2023-09-19 11:32:32,046][73131] Saving new best policy, reward=162955.653!
+-[2023-09-19 11:32:33,165][73219] Updated weights for policy 1, policy_version 7000 (0.0013)
+-[2023-09-19 11:32:33,166][73145] Updated weights for policy 0, policy_version 7040 (0.0014)
+-[2023-09-19 11:32:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6081.5). Total num frames: 7204864. Throughput: 0: 2926.2, 1: 2927.6. Samples: 4759620. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:37,044][72530] Avg episode reward: [(0, '146675.404'), (1, '162959.948')]
+-[2023-09-19 11:32:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007016_3592192.pth...
+-[2023-09-19 11:32:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007056_3612672.pth...
+-[2023-09-19 11:32:37,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006888_3526656.pth
+-[2023-09-19 11:32:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006848_3506176.pth
+-[2023-09-19 11:32:37,061][73131] Saving new best policy, reward=162959.948!
+-[2023-09-19 11:32:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7229440. Throughput: 0: 2894.3, 1: 2894.4. Samples: 4793548. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:32:42,045][72530] Avg episode reward: [(0, '152846.566'), (1, '163027.662')]
+-[2023-09-19 11:32:42,046][73131] Saving new best policy, reward=163027.662!
+-[2023-09-19 11:32:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 6053.8). Total num frames: 7262208. Throughput: 0: 2871.0, 1: 2869.7. Samples: 4829452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:32:47,044][72530] Avg episode reward: [(0, '152846.566'), (1, '163027.662')]
+-[2023-09-19 11:32:47,786][73145] Updated weights for policy 0, policy_version 7120 (0.0013)
+-[2023-09-19 11:32:47,786][73219] Updated weights for policy 1, policy_version 7080 (0.0013)
+-[2023-09-19 11:32:52,043][72530] Fps is (10 sec: 6553.5, 60 sec: 5870.9, 300 sec: 6081.5). Total num frames: 7294976. Throughput: 0: 2870.4, 1: 2870.4. Samples: 4847430. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:32:52,044][72530] Avg episode reward: [(0, '158683.654'), (1, '163077.657')]
+-[2023-09-19 11:32:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007104_3637248.pth...
+-[2023-09-19 11:32:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007144_3657728.pth...
+-[2023-09-19 11:32:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006936_3551232.pth
+-[2023-09-19 11:32:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006976_3571712.pth
+-[2023-09-19 11:32:52,062][73131] Saving new best policy, reward=163077.657!
+-[2023-09-19 11:32:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 6053.7). Total num frames: 7319552. Throughput: 0: 2884.6, 1: 2885.0. Samples: 4882566. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:32:57,044][72530] Avg episode reward: [(0, '159312.798'), (1, '163099.001')]
+-[2023-09-19 11:32:57,046][73131] Saving new best policy, reward=163099.001!
+-[2023-09-19 11:33:01,325][73145] Updated weights for policy 0, policy_version 7200 (0.0015)
+-[2023-09-19 11:33:01,326][73219] Updated weights for policy 1, policy_version 7160 (0.0014)
+-[2023-09-19 11:33:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 6053.8). Total num frames: 7352320. Throughput: 0: 2874.4, 1: 2873.4. Samples: 4919666. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:02,044][72530] Avg episode reward: [(0, '154677.624'), (1, '162411.671')]
+-[2023-09-19 11:33:07,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7385088. Throughput: 0: 2888.5, 1: 2887.3. Samples: 4937376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:07,044][72530] Avg episode reward: [(0, '154955.709'), (1, '162052.665')]
+-[2023-09-19 11:33:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007232_3702784.pth...
+-[2023-09-19 11:33:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007192_3682304.pth...
+-[2023-09-19 11:33:07,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007056_3612672.pth
+-[2023-09-19 11:33:07,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007016_3592192.pth
+-[2023-09-19 11:33:12,043][72530] Fps is (10 sec: 6553.5, 60 sec: 5870.9, 300 sec: 6081.5). Total num frames: 7417856. Throughput: 0: 2946.5, 1: 2945.3. Samples: 4975594. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:12,044][72530] Avg episode reward: [(0, '152248.569'), (1, '160136.631')]
+-[2023-09-19 11:33:14,671][73219] Updated weights for policy 1, policy_version 7240 (0.0012)
+-[2023-09-19 11:33:14,672][73145] Updated weights for policy 0, policy_version 7280 (0.0010)
+-[2023-09-19 11:33:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7442432. Throughput: 0: 2951.6, 1: 2951.3. Samples: 5012094. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:17,044][72530] Avg episode reward: [(0, '148744.362'), (1, '160112.522')]
+-[2023-09-19 11:33:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7475200. Throughput: 0: 3001.9, 1: 3001.6. Samples: 5029778. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:22,044][72530] Avg episode reward: [(0, '143773.891'), (1, '160005.506')]
+-[2023-09-19 11:33:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007280_3727360.pth...
+-[2023-09-19 11:33:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007320_3747840.pth...
+-[2023-09-19 11:33:22,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007144_3657728.pth
+-[2023-09-19 11:33:22,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007104_3637248.pth
+-[2023-09-19 11:33:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7499776. Throughput: 0: 2989.4, 1: 2990.7. Samples: 5062652. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:33:27,045][72530] Avg episode reward: [(0, '140255.889'), (1, '159095.967')]
+-[2023-09-19 11:33:28,731][73145] Updated weights for policy 0, policy_version 7360 (0.0015)
+-[2023-09-19 11:33:28,731][73219] Updated weights for policy 1, policy_version 7320 (0.0015)
+-[2023-09-19 11:33:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 6053.8). Total num frames: 7532544. Throughput: 0: 2981.7, 1: 2982.1. Samples: 5097822. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:33:32,044][72530] Avg episode reward: [(0, '141984.249'), (1, '158018.359')]
+-[2023-09-19 11:33:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6026.0). Total num frames: 7557120. Throughput: 0: 2948.8, 1: 2948.9. Samples: 5112824. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:33:37,044][72530] Avg episode reward: [(0, '143692.297'), (1, '152337.381')]
+-[2023-09-19 11:33:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007360_3768320.pth...
+-[2023-09-19 11:33:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007400_3788800.pth...
+-[2023-09-19 11:33:37,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007192_3682304.pth
+-[2023-09-19 11:33:37,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007232_3702784.pth
+-[2023-09-19 11:33:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6026.0). Total num frames: 7589888. Throughput: 0: 2966.8, 1: 2966.4. Samples: 5149558. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:33:42,045][72530] Avg episode reward: [(0, '143692.297'), (1, '151993.886')]
+-[2023-09-19 11:33:43,226][73219] Updated weights for policy 1, policy_version 7400 (0.0014)
+-[2023-09-19 11:33:43,228][73145] Updated weights for policy 0, policy_version 7440 (0.0015)
+-[2023-09-19 11:33:47,043][72530] Fps is (10 sec: 5734.6, 60 sec: 5870.9, 300 sec: 5998.2). Total num frames: 7614464. Throughput: 0: 2915.9, 1: 2916.2. Samples: 5182110. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:33:47,044][72530] Avg episode reward: [(0, '148573.588'), (1, '147997.923')]
+-[2023-09-19 11:33:52,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5871.0, 300 sec: 5998.2). Total num frames: 7647232. Throughput: 0: 2925.6, 1: 2925.8. Samples: 5200686. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:52,044][72530] Avg episode reward: [(0, '148799.645'), (1, '147997.923')]
+-[2023-09-19 11:33:52,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007448_3813376.pth...
+-[2023-09-19 11:33:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007488_3833856.pth...
+-[2023-09-19 11:33:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007280_3727360.pth
+-[2023-09-19 11:33:52,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007320_3747840.pth
+-[2023-09-19 11:33:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5870.9, 300 sec: 5998.2). Total num frames: 7671808. Throughput: 0: 2852.0, 1: 2851.8. Samples: 5232264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:57,044][72530] Avg episode reward: [(0, '149325.137'), (1, '139943.474')]
+-[2023-09-19 11:33:57,818][73219] Updated weights for policy 1, policy_version 7480 (0.0015)
+-[2023-09-19 11:33:57,818][73145] Updated weights for policy 0, policy_version 7520 (0.0012)
+-[2023-09-19 11:34:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5970.4). Total num frames: 7704576. Throughput: 0: 2837.4, 1: 2838.8. Samples: 5267522. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:02,044][72530] Avg episode reward: [(0, '151014.673'), (1, '136184.034')]
+-[2023-09-19 11:34:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5942.7). Total num frames: 7729152. Throughput: 0: 2822.8, 1: 2822.9. Samples: 5283834. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:07,045][72530] Avg episode reward: [(0, '151810.022'), (1, '129794.580')]
+-[2023-09-19 11:34:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007528_3854336.pth...
+-[2023-09-19 11:34:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007568_3874816.pth...
+-[2023-09-19 11:34:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007400_3788800.pth
+-[2023-09-19 11:34:07,071][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007360_3768320.pth
+-[2023-09-19 11:34:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5914.9). Total num frames: 7753728. Throughput: 0: 2825.1, 1: 2824.1. Samples: 5316866. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:34:12,044][72530] Avg episode reward: [(0, '148050.631'), (1, '130670.879')]
+-[2023-09-19 11:34:12,371][73145] Updated weights for policy 0, policy_version 7600 (0.0013)
+-[2023-09-19 11:34:12,371][73219] Updated weights for policy 1, policy_version 7560 (0.0012)
+-[2023-09-19 11:34:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5914.9). Total num frames: 7786496. Throughput: 0: 2825.1, 1: 2824.7. Samples: 5352062. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:17,044][72530] Avg episode reward: [(0, '149579.084'), (1, '130319.380')]
+-[2023-09-19 11:34:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5914.9). Total num frames: 7811072. Throughput: 0: 2840.5, 1: 2840.4. Samples: 5368464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:22,044][72530] Avg episode reward: [(0, '149283.565'), (1, '126902.166')]
+-[2023-09-19 11:34:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007608_3895296.pth...
+-[2023-09-19 11:34:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007648_3915776.pth...
+-[2023-09-19 11:34:22,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007448_3813376.pth
+-[2023-09-19 11:34:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007488_3833856.pth
+-[2023-09-19 11:34:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5887.3). Total num frames: 7835648. Throughput: 0: 2775.7, 1: 2776.0. Samples: 5399384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:27,045][72530] Avg episode reward: [(0, '149283.565'), (1, '126902.166')]
+-[2023-09-19 11:34:27,264][73219] Updated weights for policy 1, policy_version 7640 (0.0012)
+-[2023-09-19 11:34:27,264][73145] Updated weights for policy 0, policy_version 7680 (0.0015)
+-[2023-09-19 11:34:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5914.9). Total num frames: 7868416. Throughput: 0: 2824.0, 1: 2824.0. Samples: 5436266. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:32,044][72530] Avg episode reward: [(0, '144232.887'), (1, '135739.316')]
+-[2023-09-19 11:34:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5887.1). Total num frames: 7892992. Throughput: 0: 2799.2, 1: 2799.5. Samples: 5452628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:37,044][72530] Avg episode reward: [(0, '144291.890'), (1, '135739.316')]
+-[2023-09-19 11:34:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007688_3936256.pth...
+-[2023-09-19 11:34:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007728_3956736.pth...
+-[2023-09-19 11:34:37,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007528_3854336.pth
+-[2023-09-19 11:34:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007568_3874816.pth
+-[2023-09-19 11:34:42,043][72530] Fps is (10 sec: 5324.8, 60 sec: 5529.6, 300 sec: 5873.3). Total num frames: 7921664. Throughput: 0: 2800.1, 1: 2800.4. Samples: 5484288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:42,044][72530] Avg episode reward: [(0, '144843.661'), (1, '143710.582')]
+-[2023-09-19 11:34:42,048][73219] Updated weights for policy 1, policy_version 7720 (0.0013)
+-[2023-09-19 11:34:42,048][73145] Updated weights for policy 0, policy_version 7760 (0.0015)
+-[2023-09-19 11:34:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5887.1). Total num frames: 7950336. Throughput: 0: 2757.9, 1: 2756.6. Samples: 5515674. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:34:47,044][72530] Avg episode reward: [(0, '143205.243'), (1, '147140.750')]
+-[2023-09-19 11:34:52,043][72530] Fps is (10 sec: 5324.6, 60 sec: 5461.3, 300 sec: 5859.4). Total num frames: 7974912. Throughput: 0: 2780.3, 1: 2779.1. Samples: 5534010. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:34:52,044][72530] Avg episode reward: [(0, '141821.454'), (1, '149043.623')]
+-[2023-09-19 11:34:52,061][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007776_3981312.pth...
+-[2023-09-19 11:34:52,063][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007816_4001792.pth...
+-[2023-09-19 11:34:52,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007608_3895296.pth
+-[2023-09-19 11:34:52,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007648_3915776.pth
+-[2023-09-19 11:34:56,255][73145] Updated weights for policy 0, policy_version 7840 (0.0012)
+-[2023-09-19 11:34:56,255][73219] Updated weights for policy 1, policy_version 7800 (0.0014)
+-[2023-09-19 11:34:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5873.2). Total num frames: 8007680. Throughput: 0: 2815.3, 1: 2815.3. Samples: 5570242. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:57,044][72530] Avg episode reward: [(0, '138372.363'), (1, '156468.221')]
+-[2023-09-19 11:35:02,043][72530] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5859.4). Total num frames: 8032256. Throughput: 0: 2781.8, 1: 2782.4. Samples: 5602448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:02,044][72530] Avg episode reward: [(0, '138372.363'), (1, '157445.674')]
+-[2023-09-19 11:35:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5859.4). Total num frames: 8065024. Throughput: 0: 2774.6, 1: 2774.7. Samples: 5618186. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:07,044][72530] Avg episode reward: [(0, '142866.072'), (1, '153809.911')]
+-[2023-09-19 11:35:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007896_4042752.pth...
+-[2023-09-19 11:35:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007856_4022272.pth...
+-[2023-09-19 11:35:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007728_3956736.pth
+-[2023-09-19 11:35:07,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007688_3936256.pth
+-[2023-09-19 11:35:11,540][73219] Updated weights for policy 1, policy_version 7880 (0.0011)
+-[2023-09-19 11:35:11,541][73145] Updated weights for policy 0, policy_version 7920 (0.0013)
+-[2023-09-19 11:35:12,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5831.6). Total num frames: 8089600. Throughput: 0: 2803.7, 1: 2803.8. Samples: 5651722. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:35:12,044][72530] Avg episode reward: [(0, '143261.806'), (1, '153809.911')]
+-[2023-09-19 11:35:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5859.4). Total num frames: 8122368. Throughput: 0: 2571.9, 1: 2571.7. Samples: 5667726. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:17,044][72530] Avg episode reward: [(0, '145757.121'), (1, '154277.285')]
+-[2023-09-19 11:35:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5859.4). Total num frames: 8146944. Throughput: 0: 2785.8, 1: 2785.5. Samples: 5703340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:22,045][72530] Avg episode reward: [(0, '147899.769'), (1, '154650.090')]
+-[2023-09-19 11:35:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007936_4063232.pth...
+-[2023-09-19 11:35:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007976_4083712.pth...
+-[2023-09-19 11:35:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007816_4001792.pth
+-[2023-09-19 11:35:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007776_3981312.pth
+-[2023-09-19 11:35:25,473][73145] Updated weights for policy 0, policy_version 8000 (0.0013)
+-[2023-09-19 11:35:25,474][73219] Updated weights for policy 1, policy_version 7960 (0.0013)
+-[2023-09-19 11:35:27,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5859.4). Total num frames: 8179712. Throughput: 0: 2814.4, 1: 2814.4. Samples: 5737588. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:35:27,044][72530] Avg episode reward: [(0, '152749.656'), (1, '154559.667')]
+-[2023-09-19 11:35:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5859.4). Total num frames: 8204288. Throughput: 0: 2811.2, 1: 2811.5. Samples: 5768692. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:35:32,044][72530] Avg episode reward: [(0, '154504.272'), (1, '154707.152')]
+-[2023-09-19 11:35:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5831.6). Total num frames: 8228864. Throughput: 0: 2771.9, 1: 2773.0. Samples: 5783532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:37,044][72530] Avg episode reward: [(0, '154504.272'), (1, '154289.118')]
+-[2023-09-19 11:35:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008056_4124672.pth...
+-[2023-09-19 11:35:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008016_4104192.pth...
+-[2023-09-19 11:35:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007896_4042752.pth
+-[2023-09-19 11:35:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007856_4022272.pth
+-[2023-09-19 11:35:41,038][73145] Updated weights for policy 0, policy_version 8080 (0.0011)
+-[2023-09-19 11:35:41,039][73219] Updated weights for policy 1, policy_version 8040 (0.0014)
+-[2023-09-19 11:35:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5529.6, 300 sec: 5803.8). Total num frames: 8253440. Throughput: 0: 2734.4, 1: 2734.8. Samples: 5816354. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:42,044][72530] Avg episode reward: [(0, '161395.630'), (1, '158048.524')]
+-[2023-09-19 11:35:42,045][73130] Saving new best policy, reward=161395.630!
+-[2023-09-19 11:35:47,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5803.8). Total num frames: 8286208. Throughput: 0: 2761.4, 1: 2761.2. Samples: 5850962. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:47,044][72530] Avg episode reward: [(0, '159754.689'), (1, '158048.524')]
+-[2023-09-19 11:35:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5776.1). Total num frames: 8310784. Throughput: 0: 2780.5, 1: 2780.5. Samples: 5868434. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:35:52,045][72530] Avg episode reward: [(0, '160738.664'), (1, '159082.738')]
+-[2023-09-19 11:35:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008096_4145152.pth...
+-[2023-09-19 11:35:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008136_4165632.pth...
+-[2023-09-19 11:35:52,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007936_4063232.pth
+-[2023-09-19 11:35:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007976_4083712.pth
+-[2023-09-19 11:35:55,537][73145] Updated weights for policy 0, policy_version 8160 (0.0015)
+-[2023-09-19 11:35:55,537][73219] Updated weights for policy 1, policy_version 8120 (0.0014)
+-[2023-09-19 11:35:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5748.3). Total num frames: 8335360. Throughput: 0: 2770.3, 1: 2770.4. Samples: 5901056. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:35:57,044][72530] Avg episode reward: [(0, '162764.036'), (1, '158805.704')]
+-[2023-09-19 11:35:57,046][73130] Saving new best policy, reward=162764.036!
+-[2023-09-19 11:36:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5776.1). Total num frames: 8368128. Throughput: 0: 2965.8, 1: 2965.9. Samples: 5934650. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:36:02,044][72530] Avg episode reward: [(0, '162349.625'), (1, '156768.108')]
+-[2023-09-19 11:36:07,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5748.3). Total num frames: 8392704. Throughput: 0: 2770.8, 1: 2770.8. Samples: 5952710. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:07,043][72530] Avg episode reward: [(0, '161456.743'), (1, '158066.203')]
+-[2023-09-19 11:36:07,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008176_4186112.pth...
+-[2023-09-19 11:36:07,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008216_4206592.pth...
+-[2023-09-19 11:36:07,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008016_4104192.pth
+-[2023-09-19 11:36:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008056_4124672.pth
+-[2023-09-19 11:36:10,148][73145] Updated weights for policy 0, policy_version 8240 (0.0015)
+-[2023-09-19 11:36:10,148][73219] Updated weights for policy 1, policy_version 8200 (0.0015)
+-[2023-09-19 11:36:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5748.3). Total num frames: 8425472. Throughput: 0: 2751.9, 1: 2751.9. Samples: 5985260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:12,044][72530] Avg episode reward: [(0, '161456.743'), (1, '157423.763')]
+-[2023-09-19 11:36:17,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5720.5). Total num frames: 8450048. Throughput: 0: 2744.1, 1: 2743.7. Samples: 6015644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:17,044][72530] Avg episode reward: [(0, '161135.132'), (1, '158376.754')]
+-[2023-09-19 11:36:22,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5720.5). Total num frames: 8474624. Throughput: 0: 2786.1, 1: 2785.0. Samples: 6034230. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:36:22,044][72530] Avg episode reward: [(0, '160598.162'), (1, '158376.754')]
+-[2023-09-19 11:36:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008256_4227072.pth...
+-[2023-09-19 11:36:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008296_4247552.pth...
+-[2023-09-19 11:36:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008136_4165632.pth
+-[2023-09-19 11:36:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008096_4145152.pth
+-[2023-09-19 11:36:25,677][73219] Updated weights for policy 1, policy_version 8280 (0.0011)
+-[2023-09-19 11:36:25,678][73145] Updated weights for policy 0, policy_version 8320 (0.0011)
+-[2023-09-19 11:36:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5692.7). Total num frames: 8499200. Throughput: 0: 2751.8, 1: 2751.2. Samples: 6063990. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:36:27,044][72530] Avg episode reward: [(0, '159747.417'), (1, '153840.543')]
+-[2023-09-19 11:36:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5692.8). Total num frames: 8531968. Throughput: 0: 2749.7, 1: 2749.3. Samples: 6098416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:32,044][72530] Avg episode reward: [(0, '154229.110'), (1, '153123.695')]
+-[2023-09-19 11:36:37,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5720.5). Total num frames: 8564736. Throughput: 0: 2758.1, 1: 2758.1. Samples: 6116658. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:36:37,044][72530] Avg episode reward: [(0, '149061.433'), (1, '154038.880')]
+-[2023-09-19 11:36:37,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008344_4272128.pth...
+-[2023-09-19 11:36:37,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008384_4292608.pth...
+-[2023-09-19 11:36:37,057][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008176_4186112.pth
+-[2023-09-19 11:36:37,057][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008216_4206592.pth
+-[2023-09-19 11:36:39,594][73219] Updated weights for policy 1, policy_version 8360 (0.0015)
+-[2023-09-19 11:36:39,594][73145] Updated weights for policy 0, policy_version 8400 (0.0016)
+-[2023-09-19 11:36:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5692.7). Total num frames: 8589312. Throughput: 0: 2789.9, 1: 2790.9. Samples: 6152192. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:36:42,044][72530] Avg episode reward: [(0, '144058.161'), (1, '154059.173')]
+-[2023-09-19 11:36:47,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5692.7). Total num frames: 8622080. Throughput: 0: 2794.4, 1: 2794.6. Samples: 6186154. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:47,044][72530] Avg episode reward: [(0, '140921.567'), (1, '153742.312')]
+-[2023-09-19 11:36:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5665.0). Total num frames: 8646656. Throughput: 0: 2793.8, 1: 2793.7. Samples: 6204150. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:36:52,044][72530] Avg episode reward: [(0, '137894.258'), (1, '154893.749')]
+-[2023-09-19 11:36:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008424_4313088.pth...
+-[2023-09-19 11:36:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008464_4333568.pth...
+-[2023-09-19 11:36:52,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008256_4227072.pth
+-[2023-09-19 11:36:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008296_4247552.pth
+-[2023-09-19 11:36:53,707][73145] Updated weights for policy 0, policy_version 8480 (0.0014)
+-[2023-09-19 11:36:53,707][73219] Updated weights for policy 1, policy_version 8440 (0.0015)
+-[2023-09-19 11:36:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5692.7). Total num frames: 8679424. Throughput: 0: 2832.6, 1: 2832.4. Samples: 6240182. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:36:57,044][72530] Avg episode reward: [(0, '137894.258'), (1, '155112.103')]
+-[2023-09-19 11:37:02,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5692.7). Total num frames: 8712192. Throughput: 0: 2894.2, 1: 2894.2. Samples: 6276120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:02,045][72530] Avg episode reward: [(0, '135885.742'), (1, '160768.230')]
+-[2023-09-19 11:37:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 8736768. Throughput: 0: 2876.4, 1: 2876.3. Samples: 6293104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:07,045][72530] Avg episode reward: [(0, '135885.742'), (1, '160768.230')]
+-[2023-09-19 11:37:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008512_4358144.pth...
+-[2023-09-19 11:37:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008552_4378624.pth...
+-[2023-09-19 11:37:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008344_4272128.pth
+-[2023-09-19 11:37:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008384_4292608.pth
+-[2023-09-19 11:37:07,529][73145] Updated weights for policy 0, policy_version 8560 (0.0012)
+-[2023-09-19 11:37:07,529][73219] Updated weights for policy 1, policy_version 8520 (0.0013)
+-[2023-09-19 11:37:12,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5692.7). Total num frames: 8769536. Throughput: 0: 2951.7, 1: 2951.7. Samples: 6329646. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:12,044][72530] Avg episode reward: [(0, '142564.431'), (1, '161744.693')]
+-[2023-09-19 11:37:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 8794112. Throughput: 0: 2942.3, 1: 2942.5. Samples: 6363234. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:37:17,044][72530] Avg episode reward: [(0, '142915.479'), (1, '161744.693')]
+-[2023-09-19 11:37:21,639][73219] Updated weights for policy 1, policy_version 8600 (0.0011)
+-[2023-09-19 11:37:21,640][73145] Updated weights for policy 0, policy_version 8640 (0.0013)
+-[2023-09-19 11:37:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5870.9, 300 sec: 5692.7). Total num frames: 8826880. Throughput: 0: 2933.3, 1: 2933.3. Samples: 6380658. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:37:22,045][72530] Avg episode reward: [(0, '143397.695'), (1, '160966.343')]
+-[2023-09-19 11:37:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008600_4403200.pth...
+-[2023-09-19 11:37:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008640_4423680.pth...
+-[2023-09-19 11:37:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008424_4313088.pth
+-[2023-09-19 11:37:22,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008464_4333568.pth
+-[2023-09-19 11:37:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5665.0). Total num frames: 8851456. Throughput: 0: 2899.7, 1: 2898.4. Samples: 6413104. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:37:27,044][72530] Avg episode reward: [(0, '144691.029'), (1, '161003.911')]
+-[2023-09-19 11:37:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 8876032. Throughput: 0: 2857.8, 1: 2857.5. Samples: 6443340. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:37:32,044][72530] Avg episode reward: [(0, '145505.352'), (1, '159886.354')]
+-[2023-09-19 11:37:37,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5597.8, 300 sec: 5665.0). Total num frames: 8900608. Throughput: 0: 2838.1, 1: 2838.1. Samples: 6459580. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:37:37,045][72530] Avg episode reward: [(0, '148461.800'), (1, '159898.604')]
+-[2023-09-19 11:37:37,054][73145] Updated weights for policy 0, policy_version 8720 (0.0016)
+-[2023-09-19 11:37:37,054][73219] Updated weights for policy 1, policy_version 8680 (0.0016)
+-[2023-09-19 11:37:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008720_4464640.pth...
+-[2023-09-19 11:37:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008680_4444160.pth...
+-[2023-09-19 11:37:37,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008512_4358144.pth
+-[2023-09-19 11:37:37,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008552_4378624.pth
+-[2023-09-19 11:37:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 8933376. Throughput: 0: 2844.0, 1: 2844.8. Samples: 6496178. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:37:42,045][72530] Avg episode reward: [(0, '148461.800'), (1, '159908.679')]
+-[2023-09-19 11:37:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 8957952. Throughput: 0: 2809.0, 1: 2810.2. Samples: 6528986. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:37:47,044][72530] Avg episode reward: [(0, '139457.708'), (1, '160880.552')]
+-[2023-09-19 11:37:52,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 8982528. Throughput: 0: 2798.8, 1: 2799.8. Samples: 6545042. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:52,045][72530] Avg episode reward: [(0, '139457.708'), (1, '160880.552')]
+-[2023-09-19 11:37:52,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008752_4481024.pth...
+-[2023-09-19 11:37:52,057][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008792_4501504.pth...
+-[2023-09-19 11:37:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008600_4403200.pth
+-[2023-09-19 11:37:52,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008640_4423680.pth
+-[2023-09-19 11:37:52,458][73219] Updated weights for policy 1, policy_version 8760 (0.0012)
+-[2023-09-19 11:37:52,459][73145] Updated weights for policy 0, policy_version 8800 (0.0011)
+-[2023-09-19 11:37:57,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 9007104. Throughput: 0: 2704.4, 1: 2704.2. Samples: 6573032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:57,044][72530] Avg episode reward: [(0, '140620.851'), (1, '160021.637')]
+-[2023-09-19 11:38:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 9039872. Throughput: 0: 2697.8, 1: 2697.6. Samples: 6606026. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:02,045][72530] Avg episode reward: [(0, '142260.932'), (1, '161163.491')]
+-[2023-09-19 11:38:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5581.7). Total num frames: 9064448. Throughput: 0: 2677.0, 1: 2676.9. Samples: 6621582. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:38:07,045][72530] Avg episode reward: [(0, '140483.928'), (1, '159989.158')]
+-[2023-09-19 11:38:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008832_4521984.pth...
+-[2023-09-19 11:38:07,057][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008872_4542464.pth...
+-[2023-09-19 11:38:07,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008680_4444160.pth
+-[2023-09-19 11:38:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008720_4464640.pth
+-[2023-09-19 11:38:07,390][73145] Updated weights for policy 0, policy_version 8880 (0.0012)
+-[2023-09-19 11:38:07,390][73219] Updated weights for policy 1, policy_version 8840 (0.0013)
+-[2023-09-19 11:38:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 9097216. Throughput: 0: 2721.5, 1: 2721.4. Samples: 6658036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:12,045][72530] Avg episode reward: [(0, '138787.732'), (1, '159982.414')]
+-[2023-09-19 11:38:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5581.7). Total num frames: 9121792. Throughput: 0: 2759.0, 1: 2758.8. Samples: 6691642. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:17,044][72530] Avg episode reward: [(0, '138787.732'), (1, '159979.750')]
+-[2023-09-19 11:38:22,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 9146368. Throughput: 0: 2732.9, 1: 2733.0. Samples: 6705544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:22,045][72530] Avg episode reward: [(0, '137723.465'), (1, '159412.068')]
+-[2023-09-19 11:38:22,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008912_4562944.pth...
+-[2023-09-19 11:38:22,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008952_4583424.pth...
+-[2023-09-19 11:38:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008752_4481024.pth
+-[2023-09-19 11:38:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008792_4501504.pth
+-[2023-09-19 11:38:22,663][73219] Updated weights for policy 1, policy_version 8920 (0.0014)
+-[2023-09-19 11:38:22,663][73145] Updated weights for policy 0, policy_version 8960 (0.0016)
+-[2023-09-19 11:38:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5553.9). Total num frames: 9170944. Throughput: 0: 2668.7, 1: 2667.9. Samples: 6736324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:27,044][72530] Avg episode reward: [(0, '137729.460'), (1, '159412.184')]
+-[2023-09-19 11:38:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5581.7). Total num frames: 9203712. Throughput: 0: 2658.7, 1: 2657.8. Samples: 6768230. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:32,044][72530] Avg episode reward: [(0, '137016.334'), (1, '160295.806')]
+-[2023-09-19 11:38:37,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5553.9). Total num frames: 9228288. Throughput: 0: 2671.2, 1: 2670.4. Samples: 6785414. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:38:37,044][72530] Avg episode reward: [(0, '135131.016'), (1, '159223.120')]
+-[2023-09-19 11:38:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009032_4624384.pth...
+-[2023-09-19 11:38:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008992_4603904.pth...
+-[2023-09-19 11:38:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008832_4521984.pth
+-[2023-09-19 11:38:37,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008872_4542464.pth
+-[2023-09-19 11:38:37,583][73145] Updated weights for policy 0, policy_version 9040 (0.0013)
+-[2023-09-19 11:38:37,583][73219] Updated weights for policy 1, policy_version 9000 (0.0014)
+-[2023-09-19 11:38:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5553.9). Total num frames: 9252864. Throughput: 0: 2718.7, 1: 2718.9. Samples: 6817726. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:38:42,044][72530] Avg episode reward: [(0, '136734.966'), (1, '159206.896')]
+-[2023-09-19 11:38:47,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9277440. Throughput: 0: 2507.6, 1: 2694.9. Samples: 6840140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:47,044][72530] Avg episode reward: [(0, '137794.300'), (1, '161324.133')]
+-[2023-09-19 11:38:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5553.9). Total num frames: 9310208. Throughput: 0: 2701.8, 1: 2702.8. Samples: 6864788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:52,044][72530] Avg episode reward: [(0, '137794.300'), (1, '161324.133')]
+-[2023-09-19 11:38:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009112_4665344.pth...
+-[2023-09-19 11:38:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009072_4644864.pth...
+-[2023-09-19 11:38:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008912_4562944.pth
+-[2023-09-19 11:38:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008952_4583424.pth
+-[2023-09-19 11:38:53,194][73219] Updated weights for policy 1, policy_version 9080 (0.0013)
+-[2023-09-19 11:38:53,194][73145] Updated weights for policy 0, policy_version 9120 (0.0011)
+-[2023-09-19 11:38:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9334784. Throughput: 0: 2646.8, 1: 2646.8. Samples: 6896248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:57,044][72530] Avg episode reward: [(0, '137042.173'), (1, '160811.317')]
+-[2023-09-19 11:39:02,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9359360. Throughput: 0: 2603.1, 1: 2603.4. Samples: 6925932. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:39:02,044][72530] Avg episode reward: [(0, '137522.213'), (1, '160783.376')]
+-[2023-09-19 11:39:07,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9383936. Throughput: 0: 2590.8, 1: 2591.2. Samples: 6938732. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:39:07,044][72530] Avg episode reward: [(0, '138050.348'), (1, '161331.845')]
+-[2023-09-19 11:39:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009184_4702208.pth...
+-[2023-09-19 11:39:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009144_4681728.pth...
+-[2023-09-19 11:39:07,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009032_4624384.pth
+-[2023-09-19 11:39:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008992_4603904.pth
+-[2023-09-19 11:39:09,053][73219] Updated weights for policy 1, policy_version 9160 (0.0013)
+-[2023-09-19 11:39:09,054][73145] Updated weights for policy 0, policy_version 9200 (0.0011)
+-[2023-09-19 11:39:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9416704. Throughput: 0: 2658.6, 1: 2658.4. Samples: 6975588. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:39:12,044][72530] Avg episode reward: [(0, '140041.122'), (1, '160346.458')]
+-[2023-09-19 11:39:17,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9441280. Throughput: 0: 2631.2, 1: 2630.8. Samples: 7005018. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:17,044][72530] Avg episode reward: [(0, '140041.122'), (1, '160346.458')]
+-[2023-09-19 11:39:22,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9465856. Throughput: 0: 2645.9, 1: 2646.0. Samples: 7023548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:22,045][72530] Avg episode reward: [(0, '141321.149'), (1, '160469.876')]
+-[2023-09-19 11:39:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009264_4743168.pth...
+-[2023-09-19 11:39:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009224_4722688.pth...
+-[2023-09-19 11:39:22,057][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009112_4665344.pth
+-[2023-09-19 11:39:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009072_4644864.pth
+-[2023-09-19 11:39:23,736][73145] Updated weights for policy 0, policy_version 9280 (0.0016)
+-[2023-09-19 11:39:23,736][73219] Updated weights for policy 1, policy_version 9240 (0.0012)
+-[2023-09-19 11:39:27,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9498624. Throughput: 0: 2682.5, 1: 2682.2. Samples: 7059138. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:27,044][72530] Avg episode reward: [(0, '143117.745'), (1, '160469.876')]
+-[2023-09-19 11:39:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9523200. Throughput: 0: 2906.0, 1: 2718.8. Samples: 7093254. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:32,044][72530] Avg episode reward: [(0, '139677.367'), (1, '160492.361')]
+-[2023-09-19 11:39:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5540.0). Total num frames: 9555968. Throughput: 0: 2725.9, 1: 2724.9. Samples: 7110074. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:39:37,044][72530] Avg episode reward: [(0, '137931.041'), (1, '160516.950')]
+-[2023-09-19 11:39:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009352_4788224.pth...
+-[2023-09-19 11:39:37,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009312_4767744.pth...
+-[2023-09-19 11:39:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009184_4702208.pth
+-[2023-09-19 11:39:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009144_4681728.pth
+-[2023-09-19 11:39:38,025][73219] Updated weights for policy 1, policy_version 9320 (0.0014)
+-[2023-09-19 11:39:38,025][73145] Updated weights for policy 0, policy_version 9360 (0.0014)
+-[2023-09-19 11:39:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9580544. Throughput: 0: 2739.1, 1: 2740.1. Samples: 7142812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:42,045][72530] Avg episode reward: [(0, '135675.016'), (1, '160545.833')]
+-[2023-09-19 11:39:47,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9605120. Throughput: 0: 2730.0, 1: 2729.9. Samples: 7171628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:47,044][72530] Avg episode reward: [(0, '134266.068'), (1, '160294.298')]
+-[2023-09-19 11:39:52,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 9629696. Throughput: 0: 2788.4, 1: 2787.8. Samples: 7189664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:52,045][72530] Avg episode reward: [(0, '134266.068'), (1, '160294.298')]
+-[2023-09-19 11:39:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009384_4804608.pth...
+-[2023-09-19 11:39:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009424_4825088.pth...
+-[2023-09-19 11:39:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009264_4743168.pth
+-[2023-09-19 11:39:52,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009224_4722688.pth
+-[2023-09-19 11:39:53,740][73145] Updated weights for policy 0, policy_version 9440 (0.0014)
+-[2023-09-19 11:39:53,740][73219] Updated weights for policy 1, policy_version 9400 (0.0011)
+-[2023-09-19 11:39:57,043][72530] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9662464. Throughput: 0: 2746.2, 1: 2746.2. Samples: 7222744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:57,045][72530] Avg episode reward: [(0, '127890.525'), (1, '162301.441')]
+-[2023-09-19 11:40:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 9687040. Throughput: 0: 2803.2, 1: 2803.9. Samples: 7257338. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:02,044][72530] Avg episode reward: [(0, '126377.631'), (1, '162308.865')]
+-[2023-09-19 11:40:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5526.1). Total num frames: 9719808. Throughput: 0: 2767.5, 1: 2767.4. Samples: 7272620. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:40:07,045][72530] Avg episode reward: [(0, '126851.345'), (1, '162306.418')]
+-[2023-09-19 11:40:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009512_4870144.pth...
+-[2023-09-19 11:40:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009472_4849664.pth...
+-[2023-09-19 11:40:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009352_4788224.pth
+-[2023-09-19 11:40:07,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009312_4767744.pth
+-[2023-09-19 11:40:08,284][73145] Updated weights for policy 0, policy_version 9520 (0.0013)
+-[2023-09-19 11:40:08,284][73219] Updated weights for policy 1, policy_version 9480 (0.0012)
+-[2023-09-19 11:40:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 9744384. Throughput: 0: 2756.3, 1: 2757.5. Samples: 7307258. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:40:12,044][72530] Avg episode reward: [(0, '124049.731'), (1, '162755.710')]
+-[2023-09-19 11:40:17,043][72530] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 9777152. Throughput: 0: 2743.8, 1: 2743.8. Samples: 7340196. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:17,044][72530] Avg episode reward: [(0, '125342.829'), (1, '162760.657')]
+-[2023-09-19 11:40:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 9801728. Throughput: 0: 2757.9, 1: 2758.1. Samples: 7358298. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:22,044][72530] Avg episode reward: [(0, '126869.413'), (1, '162774.053')]
+-[2023-09-19 11:40:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009552_4890624.pth...
+-[2023-09-19 11:40:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009592_4911104.pth...
+-[2023-09-19 11:40:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009384_4804608.pth
+-[2023-09-19 11:40:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009424_4825088.pth
+-[2023-09-19 11:40:22,807][73219] Updated weights for policy 1, policy_version 9560 (0.0014)
+-[2023-09-19 11:40:22,808][73145] Updated weights for policy 0, policy_version 9600 (0.0015)
+-[2023-09-19 11:40:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 9826304. Throughput: 0: 2762.2, 1: 2761.2. Samples: 7391364. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:40:27,044][72530] Avg episode reward: [(0, '126869.413'), (1, '163199.726')]
+-[2023-09-19 11:40:27,045][73131] Saving new best policy, reward=163199.726!
+-[2023-09-19 11:40:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 9859072. Throughput: 0: 2813.1, 1: 2813.0. Samples: 7424800. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:40:32,044][72530] Avg episode reward: [(0, '127876.969'), (1, '163246.788')]
+-[2023-09-19 11:40:32,045][73131] Saving new best policy, reward=163246.788!
+-[2023-09-19 11:40:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9883648. Throughput: 0: 2764.8, 1: 2765.1. Samples: 7438508. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:40:37,044][72530] Avg episode reward: [(0, '128261.706'), (1, '163246.788')]
+-[2023-09-19 11:40:37,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009632_4931584.pth...
+-[2023-09-19 11:40:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009672_4952064.pth...
+-[2023-09-19 11:40:37,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009472_4849664.pth
+-[2023-09-19 11:40:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009512_4870144.pth
+-[2023-09-19 11:40:37,743][73145] Updated weights for policy 0, policy_version 9680 (0.0015)
+-[2023-09-19 11:40:37,744][73219] Updated weights for policy 1, policy_version 9640 (0.0013)
+-[2023-09-19 11:40:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5498.4). Total num frames: 9908224. Throughput: 0: 2790.9, 1: 2791.1. Samples: 7473936. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:42,044][72530] Avg episode reward: [(0, '127401.924'), (1, '163340.260')]
+-[2023-09-19 11:40:42,046][73131] Saving new best policy, reward=163340.260!
+-[2023-09-19 11:40:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 9940992. Throughput: 0: 2779.8, 1: 2779.3. Samples: 7507494. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:47,044][72530] Avg episode reward: [(0, '126125.877'), (1, '163360.879')]
+-[2023-09-19 11:40:47,045][73131] Saving new best policy, reward=163360.879!
+-[2023-09-19 11:40:51,985][73219] Updated weights for policy 1, policy_version 9720 (0.0013)
+-[2023-09-19 11:40:51,986][73145] Updated weights for policy 0, policy_version 9760 (0.0013)
+-[2023-09-19 11:40:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 9973760. Throughput: 0: 2804.9, 1: 2805.1. Samples: 7525070. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:40:52,044][72530] Avg episode reward: [(0, '124501.715'), (1, '163360.926')]
+-[2023-09-19 11:40:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009720_4976640.pth...
+-[2023-09-19 11:40:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009760_4997120.pth...
+-[2023-09-19 11:40:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009552_4890624.pth
+-[2023-09-19 11:40:52,060][73131] Saving new best policy, reward=163360.926!
+-[2023-09-19 11:40:52,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009592_4911104.pth
+-[2023-09-19 11:40:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 9998336. Throughput: 0: 2820.8, 1: 2820.6. Samples: 7561120. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:40:57,044][72530] Avg episode reward: [(0, '121716.208'), (1, '162980.361')]
+-[2023-09-19 11:41:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10031104. Throughput: 0: 2839.9, 1: 2840.1. Samples: 7595796. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:41:02,044][72530] Avg episode reward: [(0, '123047.712'), (1, '162118.736')]
+-[2023-09-19 11:41:05,816][73145] Updated weights for policy 0, policy_version 9840 (0.0013)
+-[2023-09-19 11:41:05,816][73219] Updated weights for policy 1, policy_version 9800 (0.0011)
+-[2023-09-19 11:41:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 10055680. Throughput: 0: 2842.4, 1: 2842.3. Samples: 7614106. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:07,044][72530] Avg episode reward: [(0, '121775.268'), (1, '162040.085')]
+-[2023-09-19 11:41:07,093][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009808_5021696.pth...
+-[2023-09-19 11:41:07,097][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009632_4931584.pth
+-[2023-09-19 11:41:07,108][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009848_5042176.pth...
+-[2023-09-19 11:41:07,112][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009672_4952064.pth
+-[2023-09-19 11:41:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10088448. Throughput: 0: 2884.6, 1: 2885.2. Samples: 7651008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:12,044][72530] Avg episode reward: [(0, '121120.688'), (1, '162013.153')]
+-[2023-09-19 11:41:17,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5581.7). Total num frames: 10121216. Throughput: 0: 2908.3, 1: 2908.4. Samples: 7686552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:17,044][72530] Avg episode reward: [(0, '124879.108'), (1, '161974.000')]
+-[2023-09-19 11:41:19,279][73145] Updated weights for policy 0, policy_version 9920 (0.0012)
+-[2023-09-19 11:41:19,279][73219] Updated weights for policy 1, policy_version 9880 (0.0014)
+-[2023-09-19 11:41:22,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5870.9, 300 sec: 5609.4). Total num frames: 10153984. Throughput: 0: 2966.0, 1: 2965.8. Samples: 7705438. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:22,044][72530] Avg episode reward: [(0, '124879.108'), (1, '161966.557')]
+-[2023-09-19 11:41:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009936_5087232.pth...
+-[2023-09-19 11:41:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009896_5066752.pth...
+-[2023-09-19 11:41:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009720_4976640.pth
+-[2023-09-19 11:41:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009760_4997120.pth
+-[2023-09-19 11:41:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5581.7). Total num frames: 10178560. Throughput: 0: 2936.0, 1: 2936.1. Samples: 7738182. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:27,045][72530] Avg episode reward: [(0, '127104.430'), (1, '161743.941')]
+-[2023-09-19 11:41:32,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10203136. Throughput: 0: 2947.0, 1: 2947.1. Samples: 7772726. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:32,044][72530] Avg episode reward: [(0, '128493.741'), (1, '161743.941')]
+-[2023-09-19 11:41:33,872][73219] Updated weights for policy 1, policy_version 9960 (0.0008)
+-[2023-09-19 11:41:33,873][73145] Updated weights for policy 0, policy_version 10000 (0.0013)
+-[2023-09-19 11:41:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5581.7). Total num frames: 10235904. Throughput: 0: 2945.2, 1: 2945.2. Samples: 7790142. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:37,044][72530] Avg episode reward: [(0, '127668.095'), (1, '162203.421')]
+-[2023-09-19 11:41:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009976_5107712.pth...
+-[2023-09-19 11:41:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010016_5128192.pth...
+-[2023-09-19 11:41:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009808_5021696.pth
+-[2023-09-19 11:41:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009848_5042176.pth
+-[2023-09-19 11:41:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5553.9). Total num frames: 10260480. Throughput: 0: 2933.3, 1: 2932.4. Samples: 7825076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:42,044][72530] Avg episode reward: [(0, '129918.117'), (1, '162258.975')]
+-[2023-09-19 11:41:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 5581.7). Total num frames: 10293248. Throughput: 0: 2916.2, 1: 2916.0. Samples: 7858242. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:47,044][72530] Avg episode reward: [(0, '127362.808'), (1, '162303.333')]
+-[2023-09-19 11:41:47,993][73219] Updated weights for policy 1, policy_version 10040 (0.0015)
+-[2023-09-19 11:41:47,993][73145] Updated weights for policy 0, policy_version 10080 (0.0013)
+-[2023-09-19 11:41:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10317824. Throughput: 0: 2920.8, 1: 2920.8. Samples: 7876978. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:52,044][72530] Avg episode reward: [(0, '126406.406'), (1, '162333.274')]
+-[2023-09-19 11:41:52,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010096_5169152.pth...
+-[2023-09-19 11:41:52,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010056_5148672.pth...
+-[2023-09-19 11:41:52,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009936_5087232.pth
+-[2023-09-19 11:41:52,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009896_5066752.pth
+-[2023-09-19 11:41:57,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 5553.9). Total num frames: 10350592. Throughput: 0: 2853.3, 1: 2852.7. Samples: 7907776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:57,044][72530] Avg episode reward: [(0, '123833.586'), (1, '162357.732')]
+-[2023-09-19 11:42:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10375168. Throughput: 0: 2849.7, 1: 2849.6. Samples: 7943016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:02,044][72530] Avg episode reward: [(0, '119983.882'), (1, '162619.479')]
+-[2023-09-19 11:42:02,675][73219] Updated weights for policy 1, policy_version 10120 (0.0014)
+-[2023-09-19 11:42:02,676][73145] Updated weights for policy 0, policy_version 10160 (0.0015)
+-[2023-09-19 11:42:07,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5734.4, 300 sec: 5526.1). Total num frames: 10399744. Throughput: 0: 2834.9, 1: 2834.8. Samples: 7960578. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:07,045][72530] Avg episode reward: [(0, '119983.882'), (1, '162619.479')]
+-[2023-09-19 11:42:07,089][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010144_5193728.pth...
+-[2023-09-19 11:42:07,090][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010184_5214208.pth...
+-[2023-09-19 11:42:07,093][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009976_5107712.pth
+-[2023-09-19 11:42:07,096][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010016_5128192.pth
+-[2023-09-19 11:42:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10432512. Throughput: 0: 2856.8, 1: 2857.6. Samples: 7995330. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:12,044][72530] Avg episode reward: [(0, '117278.968'), (1, '162975.817')]
+-[2023-09-19 11:42:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 10457088. Throughput: 0: 2837.4, 1: 2838.5. Samples: 8028138. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:17,044][72530] Avg episode reward: [(0, '117278.968'), (1, '162975.817')]
+-[2023-09-19 11:42:17,136][73219] Updated weights for policy 1, policy_version 10200 (0.0013)
+-[2023-09-19 11:42:17,136][73145] Updated weights for policy 0, policy_version 10240 (0.0014)
+-[2023-09-19 11:42:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 10489856. Throughput: 0: 2827.2, 1: 2828.1. Samples: 8044630. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:22,044][72530] Avg episode reward: [(0, '121515.315'), (1, '162988.813')]
+-[2023-09-19 11:42:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010224_5234688.pth...
+-[2023-09-19 11:42:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010264_5255168.pth...
+-[2023-09-19 11:42:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010056_5148672.pth
+-[2023-09-19 11:42:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010096_5169152.pth
+-[2023-09-19 11:42:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 10514432. Throughput: 0: 2792.9, 1: 2792.8. Samples: 8076430. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:42:27,044][72530] Avg episode reward: [(0, '118834.382'), (1, '162994.952')]
+-[2023-09-19 11:42:31,795][73145] Updated weights for policy 0, policy_version 10320 (0.0014)
+-[2023-09-19 11:42:31,795][73219] Updated weights for policy 1, policy_version 10280 (0.0014)
+-[2023-09-19 11:42:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5581.7). Total num frames: 10547200. Throughput: 0: 2815.4, 1: 2815.5. Samples: 8111630. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:42:32,044][72530] Avg episode reward: [(0, '118369.672'), (1, '161883.949')]
+-[2023-09-19 11:42:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 10571776. Throughput: 0: 2810.9, 1: 2810.8. Samples: 8129954. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:42:37,044][72530] Avg episode reward: [(0, '121189.235'), (1, '161513.570')]
+-[2023-09-19 11:42:37,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010304_5275648.pth...
+-[2023-09-19 11:42:37,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010344_5296128.pth...
+-[2023-09-19 11:42:37,057][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010144_5193728.pth
+-[2023-09-19 11:42:37,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010184_5214208.pth
+-[2023-09-19 11:42:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5581.7). Total num frames: 10604544. Throughput: 0: 2861.8, 1: 2861.8. Samples: 8165336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:42,044][72530] Avg episode reward: [(0, '121261.492'), (1, '161513.431')]
+-[2023-09-19 11:42:45,967][73219] Updated weights for policy 1, policy_version 10360 (0.0013)
+-[2023-09-19 11:42:45,968][73145] Updated weights for policy 0, policy_version 10400 (0.0014)
+-[2023-09-19 11:42:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5581.7). Total num frames: 10629120. Throughput: 0: 2844.1, 1: 2844.1. Samples: 8198984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:47,044][72530] Avg episode reward: [(0, '118032.842'), (1, '157614.308')]
+-[2023-09-19 11:42:52,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10661888. Throughput: 0: 2843.3, 1: 2844.3. Samples: 8216516. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:42:52,044][72530] Avg episode reward: [(0, '118032.842'), (1, '156763.229')]
+-[2023-09-19 11:42:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010392_5320704.pth...
+-[2023-09-19 11:42:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010432_5341184.pth...
+-[2023-09-19 11:42:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010224_5234688.pth
+-[2023-09-19 11:42:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010264_5255168.pth
+-[2023-09-19 11:42:57,043][72530] Fps is (10 sec: 6553.7, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10694656. Throughput: 0: 2862.2, 1: 2861.2. Samples: 8252880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:57,044][72530] Avg episode reward: [(0, '113836.289'), (1, '152570.666')]
+-[2023-09-19 11:42:59,347][73219] Updated weights for policy 1, policy_version 10440 (0.0013)
+-[2023-09-19 11:42:59,348][73145] Updated weights for policy 0, policy_version 10480 (0.0014)
+-[2023-09-19 11:43:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10719232. Throughput: 0: 2911.6, 1: 2911.6. Samples: 8290182. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:02,044][72530] Avg episode reward: [(0, '113836.289'), (1, '152570.666')]
+-[2023-09-19 11:43:07,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5734.4, 300 sec: 5581.7). Total num frames: 10743808. Throughput: 0: 2894.9, 1: 2894.2. Samples: 8305140. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:43:07,045][72530] Avg episode reward: [(0, '115267.182'), (1, '149740.570')]
+-[2023-09-19 11:43:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010512_5382144.pth...
+-[2023-09-19 11:43:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010472_5361664.pth...
+-[2023-09-19 11:43:07,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010304_5275648.pth
+-[2023-09-19 11:43:07,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010344_5296128.pth
+-[2023-09-19 11:43:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10776576. Throughput: 0: 2920.7, 1: 2921.1. Samples: 8339310. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:43:12,044][72530] Avg episode reward: [(0, '112738.453'), (1, '147363.933')]
+-[2023-09-19 11:43:13,928][73145] Updated weights for policy 0, policy_version 10560 (0.0015)
+-[2023-09-19 11:43:13,928][73219] Updated weights for policy 1, policy_version 10520 (0.0013)
+-[2023-09-19 11:43:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 5870.9, 300 sec: 5637.2). Total num frames: 10809344. Throughput: 0: 2925.9, 1: 2925.9. Samples: 8374958. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:17,044][72530] Avg episode reward: [(0, '112692.445'), (1, '139212.880')]
+-[2023-09-19 11:43:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5637.2). Total num frames: 10833920. Throughput: 0: 2885.6, 1: 2885.7. Samples: 8389664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:22,044][72530] Avg episode reward: [(0, '111524.427'), (1, '138648.058')]
+-[2023-09-19 11:43:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010560_5406720.pth...
+-[2023-09-19 11:43:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010600_5427200.pth...
+-[2023-09-19 11:43:22,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010392_5320704.pth
+-[2023-09-19 11:43:22,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010432_5341184.pth
+-[2023-09-19 11:43:27,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10858496. Throughput: 0: 2801.5, 1: 2801.5. Samples: 8417468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:27,044][72530] Avg episode reward: [(0, '111524.427'), (1, '136941.524')]
+-[2023-09-19 11:43:29,536][73145] Updated weights for policy 0, policy_version 10640 (0.0016)
+-[2023-09-19 11:43:29,536][73219] Updated weights for policy 1, policy_version 10600 (0.0013)
+-[2023-09-19 11:43:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5609.4). Total num frames: 10883072. Throughput: 0: 2830.2, 1: 2830.5. Samples: 8453716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:32,044][72530] Avg episode reward: [(0, '107385.986'), (1, '135321.775')]
+-[2023-09-19 11:43:37,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5637.2). Total num frames: 10915840. Throughput: 0: 2819.7, 1: 2819.8. Samples: 8470292. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:43:37,044][72530] Avg episode reward: [(0, '107385.986'), (1, '135321.775')]
+-[2023-09-19 11:43:37,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010640_5447680.pth...
+-[2023-09-19 11:43:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010680_5468160.pth...
+-[2023-09-19 11:43:37,056][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010512_5382144.pth
+-[2023-09-19 11:43:37,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010472_5361664.pth
+-[2023-09-19 11:43:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 10940416. Throughput: 0: 2781.7, 1: 2783.1. Samples: 8503296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:42,044][72530] Avg episode reward: [(0, '100071.875'), (1, '136457.439')]
+-[2023-09-19 11:43:44,019][73219] Updated weights for policy 1, policy_version 10680 (0.0013)
+-[2023-09-19 11:43:44,019][73145] Updated weights for policy 0, policy_version 10720 (0.0016)
+-[2023-09-19 11:43:47,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5597.9, 300 sec: 5609.4). Total num frames: 10964992. Throughput: 0: 2720.2, 1: 2719.9. Samples: 8534988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:47,044][72530] Avg episode reward: [(0, '99838.586'), (1, '136457.439')]
+-[2023-09-19 11:43:52,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 10989568. Throughput: 0: 2733.8, 1: 2733.7. Samples: 8551178. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:43:52,044][72530] Avg episode reward: [(0, '96058.014'), (1, '144304.212')]
+-[2023-09-19 11:43:52,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010752_5505024.pth...
+-[2023-09-19 11:43:52,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010712_5484544.pth...
+-[2023-09-19 11:43:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010600_5427200.pth
+-[2023-09-19 11:43:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010560_5406720.pth
+-[2023-09-19 11:43:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5609.4). Total num frames: 11014144. Throughput: 0: 2672.1, 1: 2671.8. Samples: 8579786. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:43:57,044][72530] Avg episode reward: [(0, '94439.101'), (1, '146370.302')]
+-[2023-09-19 11:44:00,053][73145] Updated weights for policy 0, policy_version 10800 (0.0011)
+-[2023-09-19 11:44:00,053][73219] Updated weights for policy 1, policy_version 10760 (0.0014)
+-[2023-09-19 11:44:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11046912. Throughput: 0: 2656.6, 1: 2656.7. Samples: 8614056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:02,044][72530] Avg episode reward: [(0, '94439.101'), (1, '149966.737')]
+-[2023-09-19 11:44:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 11071488. Throughput: 0: 2659.8, 1: 2659.7. Samples: 8629044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:07,044][72530] Avg episode reward: [(0, '89650.521'), (1, '155598.656')]
+-[2023-09-19 11:44:07,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010832_5545984.pth...
+-[2023-09-19 11:44:07,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010792_5525504.pth...
+-[2023-09-19 11:44:07,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010680_5468160.pth
+-[2023-09-19 11:44:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010640_5447680.pth
+-[2023-09-19 11:44:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11104256. Throughput: 0: 2748.8, 1: 2748.7. Samples: 8664854. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:44:12,044][72530] Avg episode reward: [(0, '89650.521'), (1, '155598.656')]
+-[2023-09-19 11:44:14,562][73219] Updated weights for policy 1, policy_version 10840 (0.0014)
+-[2023-09-19 11:44:14,562][73145] Updated weights for policy 0, policy_version 10880 (0.0013)
+-[2023-09-19 11:44:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5637.2). Total num frames: 11128832. Throughput: 0: 2724.0, 1: 2723.6. Samples: 8698854. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:44:17,044][72530] Avg episode reward: [(0, '87254.510'), (1, '160076.645')]
+-[2023-09-19 11:44:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11161600. Throughput: 0: 2733.2, 1: 2733.3. Samples: 8716288. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:44:22,044][72530] Avg episode reward: [(0, '85923.521'), (1, '161617.846')]
+-[2023-09-19 11:44:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010880_5570560.pth...
+-[2023-09-19 11:44:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010920_5591040.pth...
+-[2023-09-19 11:44:22,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010712_5484544.pth
+-[2023-09-19 11:44:22,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010752_5505024.pth
+-[2023-09-19 11:44:27,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11186176. Throughput: 0: 2701.6, 1: 2700.4. Samples: 8746388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:27,044][72530] Avg episode reward: [(0, '86413.887'), (1, '161983.883')]
+-[2023-09-19 11:44:29,421][73219] Updated weights for policy 1, policy_version 10920 (0.0014)
+-[2023-09-19 11:44:29,422][73145] Updated weights for policy 0, policy_version 10960 (0.0016)
+-[2023-09-19 11:44:32,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 11210752. Throughput: 0: 2730.4, 1: 2729.5. Samples: 8780682. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:32,044][72530] Avg episode reward: [(0, '88162.418'), (1, '162739.322')]
+-[2023-09-19 11:44:37,044][72530] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11243520. Throughput: 0: 2743.6, 1: 2743.8. Samples: 8798112. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:44:37,045][72530] Avg episode reward: [(0, '89655.979'), (1, '162764.902')]
+-[2023-09-19 11:44:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010960_5611520.pth...
+-[2023-09-19 11:44:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011000_5632000.pth...
+-[2023-09-19 11:44:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010792_5525504.pth
+-[2023-09-19 11:44:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010832_5545984.pth
+-[2023-09-19 11:44:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11268096. Throughput: 0: 2814.7, 1: 2814.5. Samples: 8833096. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:44:42,044][72530] Avg episode reward: [(0, '90951.227'), (1, '163562.679')]
+-[2023-09-19 11:44:42,045][73131] Saving new best policy, reward=163562.679!
+-[2023-09-19 11:44:43,549][73145] Updated weights for policy 0, policy_version 11040 (0.0014)
+-[2023-09-19 11:44:43,549][73219] Updated weights for policy 1, policy_version 11000 (0.0012)
+-[2023-09-19 11:44:47,043][72530] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5665.0). Total num frames: 11300864. Throughput: 0: 2823.4, 1: 2823.2. Samples: 8868152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:44:47,044][72530] Avg episode reward: [(0, '90951.227'), (1, '163569.234')]
+-[2023-09-19 11:44:47,045][73131] Saving new best policy, reward=163569.234!
+-[2023-09-19 11:44:52,043][72530] Fps is (10 sec: 6553.4, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 11333632. Throughput: 0: 2853.3, 1: 2853.4. Samples: 8885846. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:44:52,044][72530] Avg episode reward: [(0, '93196.735'), (1, '163602.622')]
+-[2023-09-19 11:44:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011048_5656576.pth...
+-[2023-09-19 11:44:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011088_5677056.pth...
+-[2023-09-19 11:44:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010920_5591040.pth
+-[2023-09-19 11:44:52,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010880_5570560.pth
+-[2023-09-19 11:44:52,064][73131] Saving new best policy, reward=163602.622!
+-[2023-09-19 11:44:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 11358208. Throughput: 0: 2817.7, 1: 2817.8. Samples: 8918454. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:57,045][72530] Avg episode reward: [(0, '93196.735'), (1, '163602.622')]
+-[2023-09-19 11:44:58,430][73145] Updated weights for policy 0, policy_version 11120 (0.0014)
+-[2023-09-19 11:44:58,430][73219] Updated weights for policy 1, policy_version 11080 (0.0010)
+-[2023-09-19 11:45:02,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 11382784. Throughput: 0: 2747.1, 1: 2747.7. Samples: 8946120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:02,044][72530] Avg episode reward: [(0, '96123.404'), (1, '163617.376')]
+-[2023-09-19 11:45:02,046][73131] Saving new best policy, reward=163617.376!
+-[2023-09-19 11:45:07,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 11407360. Throughput: 0: 2726.9, 1: 2726.6. Samples: 8961696. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:45:07,044][72530] Avg episode reward: [(0, '97205.408'), (1, '163596.670')]
+-[2023-09-19 11:45:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011160_5713920.pth...
+-[2023-09-19 11:45:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011120_5693440.pth...
+-[2023-09-19 11:45:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011000_5632000.pth
+-[2023-09-19 11:45:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010960_5611520.pth
+-[2023-09-19 11:45:12,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5609.4). Total num frames: 11431936. Throughput: 0: 2703.2, 1: 2703.2. Samples: 8989676. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:45:12,043][72530] Avg episode reward: [(0, '97205.408'), (1, '163596.670')]
+-[2023-09-19 11:45:15,308][73145] Updated weights for policy 0, policy_version 11200 (0.0014)
+-[2023-09-19 11:45:15,308][73219] Updated weights for policy 1, policy_version 11160 (0.0012)
+-[2023-09-19 11:45:17,043][72530] Fps is (10 sec: 4096.1, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11448320. Throughput: 0: 2651.6, 1: 2652.6. Samples: 9019372. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:45:17,044][72530] Avg episode reward: [(0, '102260.462'), (1, '163634.922')]
+-[2023-09-19 11:45:17,045][73131] Saving new best policy, reward=163634.922!
+-[2023-09-19 11:45:22,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5609.4). Total num frames: 11481088. Throughput: 0: 2640.3, 1: 2641.3. Samples: 9035780. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:45:22,044][72530] Avg episode reward: [(0, '105256.610'), (1, '163636.135')]
+-[2023-09-19 11:45:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011192_5730304.pth...
+-[2023-09-19 11:45:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011232_5750784.pth...
+-[2023-09-19 11:45:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011088_5677056.pth
+-[2023-09-19 11:45:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011048_5656576.pth
+-[2023-09-19 11:45:22,064][73131] Saving new best policy, reward=163636.135!
+-[2023-09-19 11:45:27,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11505664. Throughput: 0: 2614.9, 1: 2616.2. Samples: 9068494. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:27,044][72530] Avg episode reward: [(0, '106969.066'), (1, '163623.728')]
+-[2023-09-19 11:45:30,281][73145] Updated weights for policy 0, policy_version 11280 (0.0010)
+-[2023-09-19 11:45:30,281][73219] Updated weights for policy 1, policy_version 11240 (0.0014)
+-[2023-09-19 11:45:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 11538432. Throughput: 0: 2590.7, 1: 2592.2. Samples: 9101380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:32,044][72530] Avg episode reward: [(0, '107549.962'), (1, '163617.201')]
+-[2023-09-19 11:45:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5609.4). Total num frames: 11563008. Throughput: 0: 2590.5, 1: 2590.6. Samples: 9118994. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:37,044][72530] Avg episode reward: [(0, '105811.432'), (1, '163639.722')]
+-[2023-09-19 11:45:37,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011272_5771264.pth...
+-[2023-09-19 11:45:37,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011312_5791744.pth...
+-[2023-09-19 11:45:37,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011120_5693440.pth
+-[2023-09-19 11:45:37,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011160_5713920.pth
+-[2023-09-19 11:45:37,061][73131] Saving new best policy, reward=163639.722!
+-[2023-09-19 11:45:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 11595776. Throughput: 0: 2606.7, 1: 2606.6. Samples: 9153050. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:42,044][72530] Avg episode reward: [(0, '107882.450'), (1, '163839.533')]
+-[2023-09-19 11:45:42,044][73131] Saving new best policy, reward=163839.533!
+-[2023-09-19 11:45:44,762][73219] Updated weights for policy 1, policy_version 11320 (0.0013)
+-[2023-09-19 11:45:44,763][73145] Updated weights for policy 0, policy_version 11360 (0.0014)
+-[2023-09-19 11:45:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11620352. Throughput: 0: 2698.0, 1: 2697.3. Samples: 9188910. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:47,044][72530] Avg episode reward: [(0, '107882.450'), (1, '163858.005')]
+-[2023-09-19 11:45:47,046][73131] Saving new best policy, reward=163858.005!
+-[2023-09-19 11:45:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5609.4). Total num frames: 11653120. Throughput: 0: 2722.0, 1: 2721.0. Samples: 9206630. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:52,044][72530] Avg episode reward: [(0, '105400.770'), (1, '163575.436')]
+-[2023-09-19 11:45:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011360_5816320.pth...
+-[2023-09-19 11:45:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011400_5836800.pth...
+-[2023-09-19 11:45:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011192_5730304.pth
+-[2023-09-19 11:45:52,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011232_5750784.pth
+-[2023-09-19 11:45:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11677696. Throughput: 0: 2764.1, 1: 2764.3. Samples: 9238454. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:57,044][72530] Avg episode reward: [(0, '105400.770'), (1, '163575.436')]
+-[2023-09-19 11:45:59,327][73219] Updated weights for policy 1, policy_version 11400 (0.0016)
+-[2023-09-19 11:45:59,327][73145] Updated weights for policy 0, policy_version 11440 (0.0016)
+-[2023-09-19 11:46:02,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11702272. Throughput: 0: 2625.6, 1: 2624.6. Samples: 9255630. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:46:02,044][72530] Avg episode reward: [(0, '104718.135'), (1, '163329.699')]
+-[2023-09-19 11:46:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5581.7). Total num frames: 11735040. Throughput: 0: 2830.1, 1: 2829.0. Samples: 9290438. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:46:07,044][72530] Avg episode reward: [(0, '104541.048'), (1, '163378.382')]
+-[2023-09-19 11:46:07,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011440_5857280.pth...
+-[2023-09-19 11:46:07,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011480_5877760.pth...
+-[2023-09-19 11:46:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011272_5771264.pth
+-[2023-09-19 11:46:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011312_5791744.pth
+-[2023-09-19 11:46:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5553.9). Total num frames: 11759616. Throughput: 0: 2839.9, 1: 2838.8. Samples: 9324034. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:46:12,044][72530] Avg episode reward: [(0, '106063.260'), (1, '163399.235')]
+-[2023-09-19 11:46:13,614][73219] Updated weights for policy 1, policy_version 11480 (0.0013)
+-[2023-09-19 11:46:13,614][73145] Updated weights for policy 0, policy_version 11520 (0.0014)
+-[2023-09-19 11:46:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 11792384. Throughput: 0: 2832.0, 1: 2830.7. Samples: 9356202. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:46:17,044][72530] Avg episode reward: [(0, '105598.661'), (1, '162236.464')]
+-[2023-09-19 11:46:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 11816960. Throughput: 0: 2812.6, 1: 2812.9. Samples: 9372142. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:46:22,044][72530] Avg episode reward: [(0, '105598.661'), (1, '158593.843')]
+-[2023-09-19 11:46:22,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011520_5898240.pth...
+-[2023-09-19 11:46:22,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011560_5918720.pth...
+-[2023-09-19 11:46:22,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011360_5816320.pth
+-[2023-09-19 11:46:22,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011400_5836800.pth
+-[2023-09-19 11:46:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 11841536. Throughput: 0: 2754.3, 1: 2754.3. Samples: 9400936. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:46:27,044][72530] Avg episode reward: [(0, '104505.657'), (1, '155073.280')]
+-[2023-09-19 11:46:30,228][73145] Updated weights for policy 0, policy_version 11600 (0.0013)
+-[2023-09-19 11:46:30,228][73219] Updated weights for policy 1, policy_version 11560 (0.0013)
+-[2023-09-19 11:46:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 11866112. Throughput: 0: 2687.7, 1: 2687.8. Samples: 9430808. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:46:32,044][72530] Avg episode reward: [(0, '105201.453'), (1, '155073.280')]
+-[2023-09-19 11:46:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 11890688. Throughput: 0: 2652.0, 1: 2653.2. Samples: 9445364. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:46:37,044][72530] Avg episode reward: [(0, '106467.037'), (1, '155392.306')]
+-[2023-09-19 11:46:37,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011592_5935104.pth...
+-[2023-09-19 11:46:37,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011632_5955584.pth...
+-[2023-09-19 11:46:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011440_5857280.pth
+-[2023-09-19 11:46:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011480_5877760.pth
+-[2023-09-19 11:46:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 11915264. Throughput: 0: 2662.8, 1: 2663.7. Samples: 9478146. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:46:42,044][72530] Avg episode reward: [(0, '108179.215'), (1, '155385.005')]
+-[2023-09-19 11:46:45,489][73145] Updated weights for policy 0, policy_version 11680 (0.0014)
+-[2023-09-19 11:46:45,490][73219] Updated weights for policy 1, policy_version 11640 (0.0014)
+-[2023-09-19 11:46:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 11948032. Throughput: 0: 2837.7, 1: 2837.9. Samples: 9511032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:46:47,044][72530] Avg episode reward: [(0, '108179.215'), (1, '155360.629')]
+-[2023-09-19 11:46:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 11972608. Throughput: 0: 2646.1, 1: 2645.9. Samples: 9528578. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:46:52,044][72530] Avg episode reward: [(0, '110744.067'), (1, '155267.645')]
+-[2023-09-19 11:46:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011712_5996544.pth...
+-[2023-09-19 11:46:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011672_5976064.pth...
+-[2023-09-19 11:46:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011560_5918720.pth
+-[2023-09-19 11:46:52,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011520_5898240.pth
+-[2023-09-19 11:46:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 11997184. Throughput: 0: 2648.3, 1: 2648.4. Samples: 9562384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:46:57,044][72530] Avg episode reward: [(0, '110744.067'), (1, '155267.645')]
+-[2023-09-19 11:46:59,831][73145] Updated weights for policy 0, policy_version 11760 (0.0013)
+-[2023-09-19 11:46:59,832][73219] Updated weights for policy 1, policy_version 11720 (0.0013)
+-[2023-09-19 11:47:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 12029952. Throughput: 0: 2681.6, 1: 2681.6. Samples: 9597548. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:47:02,044][72530] Avg episode reward: [(0, '113492.232'), (1, '163938.746')]
+-[2023-09-19 11:47:02,046][73131] Saving new best policy, reward=163938.746!
+-[2023-09-19 11:47:07,043][72530] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 12062720. Throughput: 0: 2695.1, 1: 2694.9. Samples: 9614692. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:47:07,044][72530] Avg episode reward: [(0, '114645.759'), (1, '163938.746')]
+-[2023-09-19 11:47:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011760_6021120.pth...
+-[2023-09-19 11:47:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011800_6041600.pth...
+-[2023-09-19 11:47:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011592_5935104.pth
+-[2023-09-19 11:47:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011632_5955584.pth
+-[2023-09-19 11:47:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 12087296. Throughput: 0: 2755.8, 1: 2755.8. Samples: 9648956. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:47:12,044][72530] Avg episode reward: [(0, '117620.147'), (1, '164058.186')]
+-[2023-09-19 11:47:12,046][73131] Saving new best policy, reward=164058.186!
+-[2023-09-19 11:47:15,016][73145] Updated weights for policy 0, policy_version 11840 (0.0014)
+-[2023-09-19 11:47:15,017][73219] Updated weights for policy 1, policy_version 11800 (0.0013)
+-[2023-09-19 11:47:17,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 12111872. Throughput: 0: 2736.9, 1: 2737.0. Samples: 9677132. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:47:17,044][72530] Avg episode reward: [(0, '120342.444'), (1, '164061.858')]
+-[2023-09-19 11:47:17,045][73131] Saving new best policy, reward=164061.858!
+-[2023-09-19 11:47:22,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 12136448. Throughput: 0: 2756.4, 1: 2755.3. Samples: 9693392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:47:22,045][72530] Avg episode reward: [(0, '121613.231'), (1, '164054.108')]
+-[2023-09-19 11:47:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011832_6057984.pth...
+-[2023-09-19 11:47:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011872_6078464.pth...
+-[2023-09-19 11:47:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011672_5976064.pth
+-[2023-09-19 11:47:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011712_5996544.pth
+-[2023-09-19 11:47:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12169216. Throughput: 0: 2794.7, 1: 2793.4. Samples: 9729608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:47:27,044][72530] Avg episode reward: [(0, '120341.617'), (1, '164136.092')]
+-[2023-09-19 11:47:27,045][73131] Saving new best policy, reward=164136.092!
+-[2023-09-19 11:47:29,294][73145] Updated weights for policy 0, policy_version 11920 (0.0016)
+-[2023-09-19 11:47:29,294][73219] Updated weights for policy 1, policy_version 11880 (0.0016)
+-[2023-09-19 11:47:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12193792. Throughput: 0: 2811.6, 1: 2812.1. Samples: 9764102. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:47:32,044][72530] Avg episode reward: [(0, '120341.617'), (1, '163669.701')]
+-[2023-09-19 11:47:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12226560. Throughput: 0: 2781.4, 1: 2781.4. Samples: 9778906. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:47:37,044][72530] Avg episode reward: [(0, '118487.302'), (1, '163451.635')]
+-[2023-09-19 11:47:37,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011920_6103040.pth...
+-[2023-09-19 11:47:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011960_6123520.pth...
+-[2023-09-19 11:47:37,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011800_6041600.pth
+-[2023-09-19 11:47:37,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011760_6021120.pth
+-[2023-09-19 11:47:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12251136. Throughput: 0: 2801.6, 1: 2801.3. Samples: 9814516. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:47:42,044][72530] Avg episode reward: [(0, '119270.006'), (1, '163451.635')]
+-[2023-09-19 11:47:43,762][73145] Updated weights for policy 0, policy_version 12000 (0.0016)
+-[2023-09-19 11:47:43,762][73219] Updated weights for policy 1, policy_version 11960 (0.0015)
+-[2023-09-19 11:47:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12283904. Throughput: 0: 2806.5, 1: 2806.4. Samples: 9850126. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:47:47,044][72530] Avg episode reward: [(0, '118016.428'), (1, '163248.371')]
+-[2023-09-19 11:47:52,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 12308480. Throughput: 0: 2818.1, 1: 2818.1. Samples: 9868322. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:47:52,044][72530] Avg episode reward: [(0, '115308.107'), (1, '163245.962')]
+-[2023-09-19 11:47:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012040_6164480.pth...
+-[2023-09-19 11:47:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012000_6144000.pth...
+-[2023-09-19 11:47:52,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011872_6078464.pth
+-[2023-09-19 11:47:52,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011832_6057984.pth
+-[2023-09-19 11:47:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5498.4). Total num frames: 12341248. Throughput: 0: 2811.7, 1: 2811.7. Samples: 9902008. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:47:57,044][72530] Avg episode reward: [(0, '115899.171'), (1, '163286.602')]
+-[2023-09-19 11:47:57,983][73219] Updated weights for policy 1, policy_version 12040 (0.0014)
+-[2023-09-19 11:47:57,985][73145] Updated weights for policy 0, policy_version 12080 (0.0016)
+-[2023-09-19 11:48:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12365824. Throughput: 0: 2849.0, 1: 2849.1. Samples: 9933548. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:48:02,044][72530] Avg episode reward: [(0, '117424.425'), (1, '163330.945')]
+-[2023-09-19 11:48:07,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12390400. Throughput: 0: 2815.6, 1: 2815.7. Samples: 9946798. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:48:07,044][72530] Avg episode reward: [(0, '117424.425'), (1, '163807.050')]
+-[2023-09-19 11:48:07,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012080_6184960.pth...
+-[2023-09-19 11:48:07,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012120_6205440.pth...
+-[2023-09-19 11:48:07,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011920_6103040.pth
+-[2023-09-19 11:48:07,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011960_6123520.pth
+-[2023-09-19 11:48:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12414976. Throughput: 0: 2772.0, 1: 2772.1. Samples: 9979096. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:48:12,044][72530] Avg episode reward: [(0, '116643.698'), (1, '164043.715')]
+-[2023-09-19 11:48:13,637][73145] Updated weights for policy 0, policy_version 12160 (0.0014)
+-[2023-09-19 11:48:13,637][73219] Updated weights for policy 1, policy_version 12120 (0.0013)
+-[2023-09-19 11:48:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 12447744. Throughput: 0: 2761.6, 1: 2761.6. Samples: 10012644. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:48:17,044][72530] Avg episode reward: [(0, '116643.698'), (1, '164043.715')]
+-[2023-09-19 11:48:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 12472320. Throughput: 0: 2792.3, 1: 2792.3. Samples: 10030210. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:22,044][72530] Avg episode reward: [(0, '114977.442'), (1, '164100.748')]
+-[2023-09-19 11:48:22,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012200_6246400.pth...
+-[2023-09-19 11:48:22,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012160_6225920.pth...
+-[2023-09-19 11:48:22,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012040_6164480.pth
+-[2023-09-19 11:48:22,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012000_6144000.pth
+-[2023-09-19 11:48:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12505088. Throughput: 0: 2773.0, 1: 2773.1. Samples: 10064090. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:27,044][72530] Avg episode reward: [(0, '115199.567'), (1, '164068.846')]
+-[2023-09-19 11:48:28,286][73219] Updated weights for policy 1, policy_version 12200 (0.0013)
+-[2023-09-19 11:48:28,286][73145] Updated weights for policy 0, policy_version 12240 (0.0012)
+-[2023-09-19 11:48:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 12529664. Throughput: 0: 2711.3, 1: 2711.5. Samples: 10094152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:32,044][72530] Avg episode reward: [(0, '111865.477'), (1, '163548.142')]
+-[2023-09-19 11:48:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12554240. Throughput: 0: 2682.5, 1: 2682.3. Samples: 10109738. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:37,044][72530] Avg episode reward: [(0, '107535.334'), (1, '163429.327')]
+-[2023-09-19 11:48:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012240_6266880.pth...
+-[2023-09-19 11:48:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012280_6287360.pth...
+-[2023-09-19 11:48:37,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012080_6184960.pth
+-[2023-09-19 11:48:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012120_6205440.pth
+-[2023-09-19 11:48:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12587008. Throughput: 0: 2703.6, 1: 2703.6. Samples: 10145332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:42,044][72530] Avg episode reward: [(0, '107535.334'), (1, '162298.894')]
+-[2023-09-19 11:48:43,731][73145] Updated weights for policy 0, policy_version 12320 (0.0014)
+-[2023-09-19 11:48:43,732][73219] Updated weights for policy 1, policy_version 12280 (0.0012)
+-[2023-09-19 11:48:47,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12611584. Throughput: 0: 2702.4, 1: 2702.2. Samples: 10176756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:47,044][72530] Avg episode reward: [(0, '106316.522'), (1, '161408.497')]
+-[2023-09-19 11:48:52,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12636160. Throughput: 0: 2750.1, 1: 2749.8. Samples: 10194294. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:52,044][72530] Avg episode reward: [(0, '106316.522'), (1, '161408.497')]
+-[2023-09-19 11:48:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012320_6307840.pth...
+-[2023-09-19 11:48:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012360_6328320.pth...
+-[2023-09-19 11:48:52,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012160_6225920.pth
+-[2023-09-19 11:48:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012200_6246400.pth
+-[2023-09-19 11:48:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 12660736. Throughput: 0: 2734.8, 1: 2734.8. Samples: 10225232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:57,045][72530] Avg episode reward: [(0, '104226.634'), (1, '160377.599')]
+-[2023-09-19 11:48:58,673][73145] Updated weights for policy 0, policy_version 12400 (0.0012)
+-[2023-09-19 11:48:58,673][73219] Updated weights for policy 1, policy_version 12360 (0.0015)
+-[2023-09-19 11:49:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12693504. Throughput: 0: 2747.6, 1: 2746.8. Samples: 10259896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:02,045][72530] Avg episode reward: [(0, '104136.332'), (1, '159195.252')]
+-[2023-09-19 11:49:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12718080. Throughput: 0: 2694.6, 1: 2695.7. Samples: 10272774. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:07,045][72530] Avg episode reward: [(0, '106355.574'), (1, '159230.111')]
+-[2023-09-19 11:49:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012440_6369280.pth...
+-[2023-09-19 11:49:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012400_6348800.pth...
+-[2023-09-19 11:49:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012280_6287360.pth
+-[2023-09-19 11:49:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012240_6266880.pth
+-[2023-09-19 11:49:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12742656. Throughput: 0: 2680.0, 1: 2680.4. Samples: 10305312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:12,045][72530] Avg episode reward: [(0, '110372.318'), (1, '159771.618')]
+-[2023-09-19 11:49:14,377][73145] Updated weights for policy 0, policy_version 12480 (0.0012)
+-[2023-09-19 11:49:14,378][73219] Updated weights for policy 1, policy_version 12440 (0.0012)
+-[2023-09-19 11:49:17,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 12767232. Throughput: 0: 2711.7, 1: 2712.5. Samples: 10338240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:17,044][72530] Avg episode reward: [(0, '110372.318'), (1, '159771.618')]
+-[2023-09-19 11:49:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12800000. Throughput: 0: 2729.1, 1: 2729.3. Samples: 10355370. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:22,045][72530] Avg episode reward: [(0, '110181.871'), (1, '160985.288')]
+-[2023-09-19 11:49:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012520_6410240.pth...
+-[2023-09-19 11:49:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012480_6389760.pth...
+-[2023-09-19 11:49:22,066][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012320_6307840.pth
+-[2023-09-19 11:49:22,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012360_6328320.pth
+-[2023-09-19 11:49:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 12824576. Throughput: 0: 2671.7, 1: 2671.6. Samples: 10385784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:27,044][72530] Avg episode reward: [(0, '110198.661'), (1, '160985.288')]
+-[2023-09-19 11:49:29,030][73145] Updated weights for policy 0, policy_version 12560 (0.0012)
+-[2023-09-19 11:49:29,031][73219] Updated weights for policy 1, policy_version 12520 (0.0011)
+-[2023-09-19 11:49:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12857344. Throughput: 0: 2719.7, 1: 2720.0. Samples: 10421540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:32,044][72530] Avg episode reward: [(0, '111544.611'), (1, '162823.390')]
+-[2023-09-19 11:49:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12881920. Throughput: 0: 2719.0, 1: 2719.2. Samples: 10439012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:37,044][72530] Avg episode reward: [(0, '112652.375'), (1, '162884.861')]
+-[2023-09-19 11:49:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012600_6451200.pth...
+-[2023-09-19 11:49:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012560_6430720.pth...
+-[2023-09-19 11:49:37,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012440_6369280.pth
+-[2023-09-19 11:49:37,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012400_6348800.pth
+-[2023-09-19 11:49:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 12906496. Throughput: 0: 2710.0, 1: 2711.1. Samples: 10469180. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:49:42,045][72530] Avg episode reward: [(0, '112673.657'), (1, '163872.242')]
+-[2023-09-19 11:49:44,447][73219] Updated weights for policy 1, policy_version 12600 (0.0014)
+-[2023-09-19 11:49:44,448][73145] Updated weights for policy 0, policy_version 12640 (0.0013)
+-[2023-09-19 11:49:47,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 12931072. Throughput: 0: 2683.4, 1: 2683.4. Samples: 10501404. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:49:47,044][72530] Avg episode reward: [(0, '113377.242'), (1, '163154.750')]
+-[2023-09-19 11:49:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12963840. Throughput: 0: 2727.1, 1: 2727.0. Samples: 10518208. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:49:52,045][72530] Avg episode reward: [(0, '113377.242'), (1, '163154.750')]
+-[2023-09-19 11:49:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012680_6492160.pth...
+-[2023-09-19 11:49:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012640_6471680.pth...
+-[2023-09-19 11:49:52,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012520_6410240.pth
+-[2023-09-19 11:49:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012480_6389760.pth
+-[2023-09-19 11:49:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12988416. Throughput: 0: 2708.9, 1: 2708.4. Samples: 10549088. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:49:57,044][72530] Avg episode reward: [(0, '113159.962'), (1, '161958.914')]
+-[2023-09-19 11:49:59,407][73219] Updated weights for policy 1, policy_version 12680 (0.0015)
+-[2023-09-19 11:49:59,407][73145] Updated weights for policy 0, policy_version 12720 (0.0014)
+-[2023-09-19 11:50:02,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13012992. Throughput: 0: 2709.9, 1: 2709.0. Samples: 10582090. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:50:02,044][72530] Avg episode reward: [(0, '113659.562'), (1, '161957.798')]
+-[2023-09-19 11:50:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13045760. Throughput: 0: 2706.5, 1: 2706.4. Samples: 10598952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:07,044][72530] Avg episode reward: [(0, '114392.887'), (1, '161274.669')]
+-[2023-09-19 11:50:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012720_6512640.pth...
+-[2023-09-19 11:50:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012760_6533120.pth...
+-[2023-09-19 11:50:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012560_6430720.pth
+-[2023-09-19 11:50:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012600_6451200.pth
+-[2023-09-19 11:50:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 13062144. Throughput: 0: 2697.0, 1: 2697.2. Samples: 10628524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:12,044][72530] Avg episode reward: [(0, '113293.487'), (1, '160635.441')]
+-[2023-09-19 11:50:15,160][73145] Updated weights for policy 0, policy_version 12800 (0.0014)
+-[2023-09-19 11:50:15,160][73219] Updated weights for policy 1, policy_version 12760 (0.0016)
+-[2023-09-19 11:50:17,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13094912. Throughput: 0: 2646.0, 1: 2645.9. Samples: 10659676. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:50:17,044][72530] Avg episode reward: [(0, '113293.487'), (1, '160786.247')]
+-[2023-09-19 11:50:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 13119488. Throughput: 0: 2645.4, 1: 2645.3. Samples: 10677092. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:50:22,044][72530] Avg episode reward: [(0, '113047.949'), (1, '161538.199')]
+-[2023-09-19 11:50:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012792_6549504.pth...
+-[2023-09-19 11:50:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012832_6569984.pth...
+-[2023-09-19 11:50:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012640_6471680.pth
+-[2023-09-19 11:50:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012680_6492160.pth
+-[2023-09-19 11:50:27,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13144064. Throughput: 0: 2674.3, 1: 2673.4. Samples: 10709824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:27,044][72530] Avg episode reward: [(0, '113325.734'), (1, '161538.199')]
+-[2023-09-19 11:50:30,173][73219] Updated weights for policy 1, policy_version 12840 (0.0011)
+-[2023-09-19 11:50:30,174][73145] Updated weights for policy 0, policy_version 12880 (0.0019)
+-[2023-09-19 11:50:32,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 13176832. Throughput: 0: 2678.6, 1: 2678.5. Samples: 10742474. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:32,045][72530] Avg episode reward: [(0, '110953.125'), (1, '162797.965')]
+-[2023-09-19 11:50:37,043][72530] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13201408. Throughput: 0: 2676.9, 1: 2675.9. Samples: 10759082. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:50:37,044][72530] Avg episode reward: [(0, '111513.061'), (1, '162852.658')]
+-[2023-09-19 11:50:37,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012872_6590464.pth...
+-[2023-09-19 11:50:37,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012912_6610944.pth...
+-[2023-09-19 11:50:37,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012760_6533120.pth
+-[2023-09-19 11:50:37,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012720_6512640.pth
+-[2023-09-19 11:50:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13234176. Throughput: 0: 2723.3, 1: 2723.3. Samples: 10794184. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:50:42,044][72530] Avg episode reward: [(0, '113571.621'), (1, '162934.778')]
+-[2023-09-19 11:50:44,663][73145] Updated weights for policy 0, policy_version 12960 (0.0011)
+-[2023-09-19 11:50:44,664][73219] Updated weights for policy 1, policy_version 12920 (0.0014)
+-[2023-09-19 11:50:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13258752. Throughput: 0: 2728.1, 1: 2728.3. Samples: 10827630. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:50:47,044][72530] Avg episode reward: [(0, '113123.608'), (1, '163033.885')]
+-[2023-09-19 11:50:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13291520. Throughput: 0: 2735.7, 1: 2735.9. Samples: 10845174. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:50:52,044][72530] Avg episode reward: [(0, '114036.709'), (1, '163233.390')]
+-[2023-09-19 11:50:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012960_6635520.pth...
+-[2023-09-19 11:50:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013000_6656000.pth...
+-[2023-09-19 11:50:52,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012792_6549504.pth
+-[2023-09-19 11:50:52,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012832_6569984.pth
+-[2023-09-19 11:50:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13316096. Throughput: 0: 2784.1, 1: 2784.4. Samples: 10879108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:57,044][72530] Avg episode reward: [(0, '114403.782'), (1, '162804.648')]
+-[2023-09-19 11:50:58,834][73219] Updated weights for policy 1, policy_version 13000 (0.0013)
+-[2023-09-19 11:50:58,834][73145] Updated weights for policy 0, policy_version 13040 (0.0013)
+-[2023-09-19 11:51:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 13348864. Throughput: 0: 2823.3, 1: 2823.4. Samples: 10913776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:02,045][72530] Avg episode reward: [(0, '114403.782'), (1, '162804.648')]
+-[2023-09-19 11:51:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13373440. Throughput: 0: 2802.2, 1: 2802.3. Samples: 10929298. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:07,044][72530] Avg episode reward: [(0, '115552.472'), (1, '161727.982')]
+-[2023-09-19 11:51:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013040_6676480.pth...
+-[2023-09-19 11:51:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013080_6696960.pth...
+-[2023-09-19 11:51:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012872_6590464.pth
+-[2023-09-19 11:51:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012912_6610944.pth
+-[2023-09-19 11:51:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 13398016. Throughput: 0: 2794.4, 1: 2794.4. Samples: 10961322. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:12,045][72530] Avg episode reward: [(0, '114818.267'), (1, '161727.982')]
+-[2023-09-19 11:51:14,001][73219] Updated weights for policy 1, policy_version 13080 (0.0013)
+-[2023-09-19 11:51:14,001][73145] Updated weights for policy 0, policy_version 13120 (0.0014)
+-[2023-09-19 11:51:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 13430784. Throughput: 0: 2802.5, 1: 2802.7. Samples: 10994708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:17,044][72530] Avg episode reward: [(0, '112267.470'), (1, '161652.380')]
+-[2023-09-19 11:51:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 13455360. Throughput: 0: 2816.0, 1: 2816.1. Samples: 11012526. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:22,044][72530] Avg episode reward: [(0, '113122.257'), (1, '162464.319')]
+-[2023-09-19 11:51:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013120_6717440.pth...
+-[2023-09-19 11:51:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013160_6737920.pth...
+-[2023-09-19 11:51:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013000_6656000.pth
+-[2023-09-19 11:51:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012960_6635520.pth
+-[2023-09-19 11:51:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5498.4). Total num frames: 13488128. Throughput: 0: 2804.3, 1: 2804.5. Samples: 11046580. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:51:27,044][72530] Avg episode reward: [(0, '114512.117'), (1, '162679.576')]
+-[2023-09-19 11:51:28,153][73145] Updated weights for policy 0, policy_version 13200 (0.0012)
+-[2023-09-19 11:51:28,154][73219] Updated weights for policy 1, policy_version 13160 (0.0017)
+-[2023-09-19 11:51:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13512704. Throughput: 0: 2817.9, 1: 2818.0. Samples: 11081242. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:51:32,044][72530] Avg episode reward: [(0, '115152.477'), (1, '162979.727')]
+-[2023-09-19 11:51:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13537280. Throughput: 0: 2793.9, 1: 2793.8. Samples: 11096620. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:51:37,044][72530] Avg episode reward: [(0, '115152.477'), (1, '163119.801')]
+-[2023-09-19 11:51:37,050][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013200_6758400.pth...
+-[2023-09-19 11:51:37,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013240_6778880.pth...
+-[2023-09-19 11:51:37,055][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013040_6676480.pth
+-[2023-09-19 11:51:37,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013080_6696960.pth
+-[2023-09-19 11:51:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13570048. Throughput: 0: 2789.2, 1: 2788.7. Samples: 11130112. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:51:42,045][72530] Avg episode reward: [(0, '113913.820'), (1, '164168.870')]
+-[2023-09-19 11:51:42,046][73131] Saving new best policy, reward=164168.870!
+-[2023-09-19 11:51:43,105][73219] Updated weights for policy 1, policy_version 13240 (0.0012)
+-[2023-09-19 11:51:43,105][73145] Updated weights for policy 0, policy_version 13280 (0.0013)
+-[2023-09-19 11:51:47,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13594624. Throughput: 0: 2792.0, 1: 2791.7. Samples: 11165042. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:47,045][72530] Avg episode reward: [(0, '113329.232'), (1, '164168.870')]
+-[2023-09-19 11:51:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 13627392. Throughput: 0: 2810.2, 1: 2810.3. Samples: 11182220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:52,044][72530] Avg episode reward: [(0, '115366.353'), (1, '164073.991')]
+-[2023-09-19 11:51:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013288_6803456.pth...
+-[2023-09-19 11:51:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013328_6823936.pth...
+-[2023-09-19 11:51:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013160_6737920.pth
+-[2023-09-19 11:51:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013120_6717440.pth
+-[2023-09-19 11:51:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13651968. Throughput: 0: 2834.8, 1: 2834.5. Samples: 11216442. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:57,044][72530] Avg episode reward: [(0, '112745.770'), (1, '164094.197')]
+-[2023-09-19 11:51:57,114][73145] Updated weights for policy 0, policy_version 13360 (0.0013)
+-[2023-09-19 11:51:57,114][73219] Updated weights for policy 1, policy_version 13320 (0.0014)
+-[2023-09-19 11:52:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13684736. Throughput: 0: 2842.9, 1: 2843.0. Samples: 11250572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:02,044][72530] Avg episode reward: [(0, '112085.582'), (1, '164047.200')]
+-[2023-09-19 11:52:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13709312. Throughput: 0: 2825.9, 1: 2825.9. Samples: 11266858. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:07,044][72530] Avg episode reward: [(0, '113004.087'), (1, '163717.311')]
+-[2023-09-19 11:52:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013368_6844416.pth...
+-[2023-09-19 11:52:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013408_6864896.pth...
+-[2023-09-19 11:52:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013240_6778880.pth
+-[2023-09-19 11:52:07,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013200_6758400.pth
+-[2023-09-19 11:52:11,691][73145] Updated weights for policy 0, policy_version 13440 (0.0009)
+-[2023-09-19 11:52:11,692][73219] Updated weights for policy 1, policy_version 13400 (0.0012)
+-[2023-09-19 11:52:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5526.1). Total num frames: 13742080. Throughput: 0: 2834.2, 1: 2834.1. Samples: 11301652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:12,043][72530] Avg episode reward: [(0, '113246.114'), (1, '163818.756')]
+-[2023-09-19 11:52:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 13766656. Throughput: 0: 2831.7, 1: 2831.6. Samples: 11336090. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:17,044][72530] Avg episode reward: [(0, '112684.823'), (1, '163893.278')]
+-[2023-09-19 11:52:22,043][72530] Fps is (10 sec: 5734.2, 60 sec: 5734.4, 300 sec: 5526.1). Total num frames: 13799424. Throughput: 0: 2853.1, 1: 2853.3. Samples: 11353408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:22,044][72530] Avg episode reward: [(0, '112684.823'), (1, '163936.233')]
+-[2023-09-19 11:52:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013456_6889472.pth...
+-[2023-09-19 11:52:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013496_6909952.pth...
+-[2023-09-19 11:52:22,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013288_6803456.pth
+-[2023-09-19 11:52:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013328_6823936.pth
+-[2023-09-19 11:52:26,737][73219] Updated weights for policy 1, policy_version 13480 (0.0011)
+-[2023-09-19 11:52:26,738][73145] Updated weights for policy 0, policy_version 13520 (0.0013)
+-[2023-09-19 11:52:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 13824000. Throughput: 0: 2835.0, 1: 2835.0. Samples: 11385262. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:52:27,044][72530] Avg episode reward: [(0, '110980.059'), (1, '163809.491')]
+-[2023-09-19 11:52:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13848576. Throughput: 0: 2781.7, 1: 2781.7. Samples: 11415394. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:52:32,044][72530] Avg episode reward: [(0, '110632.259'), (1, '163809.491')]
+-[2023-09-19 11:52:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13873152. Throughput: 0: 2779.5, 1: 2779.4. Samples: 11432370. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:52:37,044][72530] Avg episode reward: [(0, '110937.608'), (1, '162945.052')]
+-[2023-09-19 11:52:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013528_6926336.pth...
+-[2023-09-19 11:52:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013568_6946816.pth...
+-[2023-09-19 11:52:37,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013368_6844416.pth
+-[2023-09-19 11:52:37,070][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013408_6864896.pth
+-[2023-09-19 11:52:41,868][73145] Updated weights for policy 0, policy_version 13600 (0.0011)
+-[2023-09-19 11:52:41,868][73219] Updated weights for policy 1, policy_version 13560 (0.0013)
+-[2023-09-19 11:52:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13905920. Throughput: 0: 2761.7, 1: 2761.8. Samples: 11464998. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:52:42,044][72530] Avg episode reward: [(0, '108749.531'), (1, '162877.908')]
+-[2023-09-19 11:52:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13930496. Throughput: 0: 2736.3, 1: 2736.0. Samples: 11496824. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:52:47,044][72530] Avg episode reward: [(0, '107670.741'), (1, '161974.202')]
+-[2023-09-19 11:52:52,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13955072. Throughput: 0: 2755.3, 1: 2755.3. Samples: 11514836. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:52:52,044][72530] Avg episode reward: [(0, '109926.959'), (1, '161647.451')]
+-[2023-09-19 11:52:52,084][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013656_6991872.pth...
+-[2023-09-19 11:52:52,087][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013616_6971392.pth...
+-[2023-09-19 11:52:52,090][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013496_6909952.pth
+-[2023-09-19 11:52:52,092][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013456_6889472.pth
+-[2023-09-19 11:52:56,529][73219] Updated weights for policy 1, policy_version 13640 (0.0015)
+-[2023-09-19 11:52:56,529][73145] Updated weights for policy 0, policy_version 13680 (0.0013)
+-[2023-09-19 11:52:57,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13987840. Throughput: 0: 2750.2, 1: 2750.3. Samples: 11549176. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:52:57,044][72530] Avg episode reward: [(0, '109926.959'), (1, '161647.451')]
+-[2023-09-19 11:53:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14012416. Throughput: 0: 2745.7, 1: 2746.6. Samples: 11583242. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:02,044][72530] Avg episode reward: [(0, '108812.138'), (1, '160242.020')]
+-[2023-09-19 11:53:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 14045184. Throughput: 0: 2738.7, 1: 2739.8. Samples: 11599938. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:07,044][72530] Avg episode reward: [(0, '109280.885'), (1, '160242.020')]
+-[2023-09-19 11:53:07,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013696_7012352.pth...
+-[2023-09-19 11:53:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013736_7032832.pth...
+-[2023-09-19 11:53:07,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013528_6926336.pth
+-[2023-09-19 11:53:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013568_6946816.pth
+-[2023-09-19 11:53:10,573][73145] Updated weights for policy 0, policy_version 13760 (0.0015)
+-[2023-09-19 11:53:10,573][73219] Updated weights for policy 1, policy_version 13720 (0.0015)
+-[2023-09-19 11:53:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14069760. Throughput: 0: 2777.5, 1: 2777.6. Samples: 11635244. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:53:12,044][72530] Avg episode reward: [(0, '107640.671'), (1, '160924.342')]
+-[2023-09-19 11:53:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 14102528. Throughput: 0: 2813.6, 1: 2813.8. Samples: 11668628. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:53:17,045][72530] Avg episode reward: [(0, '106086.364'), (1, '160888.486')]
+-[2023-09-19 11:53:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14127104. Throughput: 0: 2820.8, 1: 2820.8. Samples: 11686240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:22,044][72530] Avg episode reward: [(0, '105829.988'), (1, '160815.863')]
+-[2023-09-19 11:53:22,079][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013824_7077888.pth...
+-[2023-09-19 11:53:22,082][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013656_6991872.pth
+-[2023-09-19 11:53:22,084][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013784_7057408.pth...
+-[2023-09-19 11:53:22,091][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013616_6971392.pth
+-[2023-09-19 11:53:25,330][73145] Updated weights for policy 0, policy_version 13840 (0.0015)
+-[2023-09-19 11:53:25,331][73219] Updated weights for policy 1, policy_version 13800 (0.0013)
+-[2023-09-19 11:53:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 14159872. Throughput: 0: 2819.4, 1: 2819.5. Samples: 11718750. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:27,044][72530] Avg episode reward: [(0, '105059.149'), (1, '160896.515')]
+-[2023-09-19 11:53:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 14184448. Throughput: 0: 2847.1, 1: 2847.4. Samples: 11753076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:32,044][72530] Avg episode reward: [(0, '104051.203'), (1, '160838.692')]
+-[2023-09-19 11:53:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 14209024. Throughput: 0: 2817.1, 1: 2817.1. Samples: 11768374. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:37,044][72530] Avg episode reward: [(0, '108523.798'), (1, '161743.570')]
+-[2023-09-19 11:53:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013856_7094272.pth...
+-[2023-09-19 11:53:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013896_7114752.pth...
+-[2023-09-19 11:53:37,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013736_7032832.pth
+-[2023-09-19 11:53:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013696_7012352.pth
+-[2023-09-19 11:53:40,930][73145] Updated weights for policy 0, policy_version 13920 (0.0017)
+-[2023-09-19 11:53:40,930][73219] Updated weights for policy 1, policy_version 13880 (0.0016)
+-[2023-09-19 11:53:42,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14233600. Throughput: 0: 2753.8, 1: 2753.5. Samples: 11797004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:42,044][72530] Avg episode reward: [(0, '108523.798'), (1, '161743.570')]
+-[2023-09-19 11:53:47,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14258176. Throughput: 0: 2724.0, 1: 2723.2. Samples: 11828370. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:47,044][72530] Avg episode reward: [(0, '108688.999'), (1, '160237.416')]
+-[2023-09-19 11:53:52,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14282752. Throughput: 0: 2709.0, 1: 2708.0. Samples: 11843704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:52,045][72530] Avg episode reward: [(0, '112242.915'), (1, '159716.483')]
+-[2023-09-19 11:53:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013928_7131136.pth...
+-[2023-09-19 11:53:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013968_7151616.pth...
+-[2023-09-19 11:53:52,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013784_7057408.pth
+-[2023-09-19 11:53:52,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013824_7077888.pth
+-[2023-09-19 11:53:57,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 14307328. Throughput: 0: 2611.5, 1: 2612.1. Samples: 11870304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:57,044][72530] Avg episode reward: [(0, '112242.915'), (1, '159730.340')]
+-[2023-09-19 11:53:57,810][73145] Updated weights for policy 0, policy_version 14000 (0.0013)
+-[2023-09-19 11:53:57,810][73219] Updated weights for policy 1, policy_version 13960 (0.0012)
+-[2023-09-19 11:54:02,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 14331904. Throughput: 0: 2594.1, 1: 2593.9. Samples: 11902086. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:54:02,044][72530] Avg episode reward: [(0, '116633.173'), (1, '156732.668')]
+-[2023-09-19 11:54:07,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5470.6). Total num frames: 14356480. Throughput: 0: 2554.6, 1: 2554.5. Samples: 11916152. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:54:07,044][72530] Avg episode reward: [(0, '119968.454'), (1, '156732.668')]
+-[2023-09-19 11:54:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014000_7168000.pth...
+-[2023-09-19 11:54:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014040_7188480.pth...
+-[2023-09-19 11:54:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013856_7094272.pth
+-[2023-09-19 11:54:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013896_7114752.pth
+-[2023-09-19 11:54:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5470.6). Total num frames: 14381056. Throughput: 0: 2531.6, 1: 2531.5. Samples: 11946590. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:54:12,044][72530] Avg episode reward: [(0, '126021.713'), (1, '155674.672')]
+-[2023-09-19 11:54:13,622][73219] Updated weights for policy 1, policy_version 14040 (0.0013)
+-[2023-09-19 11:54:13,623][73145] Updated weights for policy 0, policy_version 14080 (0.0014)
+-[2023-09-19 11:54:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5188.3, 300 sec: 5470.6). Total num frames: 14413824. Throughput: 0: 2509.2, 1: 2509.1. Samples: 11978896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:54:17,044][72530] Avg episode reward: [(0, '128184.575'), (1, '154083.119')]
+-[2023-09-19 11:54:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5470.6). Total num frames: 14438400. Throughput: 0: 2497.2, 1: 2498.2. Samples: 11993164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:54:22,044][72530] Avg episode reward: [(0, '128184.575'), (1, '154040.425')]
+-[2023-09-19 11:54:22,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014080_7208960.pth...
+-[2023-09-19 11:54:22,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014120_7229440.pth...
+-[2023-09-19 11:54:22,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013928_7131136.pth
+-[2023-09-19 11:54:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013968_7151616.pth
+-[2023-09-19 11:54:27,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5051.7, 300 sec: 5442.8). Total num frames: 14462976. Throughput: 0: 2535.1, 1: 2535.4. Samples: 12025176. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:27,044][72530] Avg episode reward: [(0, '140472.932'), (1, '154651.060')]
+-[2023-09-19 11:54:29,535][73145] Updated weights for policy 0, policy_version 14160 (0.0011)
+-[2023-09-19 11:54:29,536][73219] Updated weights for policy 1, policy_version 14120 (0.0014)
+-[2023-09-19 11:54:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5051.7, 300 sec: 5442.8). Total num frames: 14487552. Throughput: 0: 2522.9, 1: 2522.9. Samples: 12055430. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:32,044][72530] Avg episode reward: [(0, '141718.503'), (1, '154651.060')]
+-[2023-09-19 11:54:37,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5051.7, 300 sec: 5442.8). Total num frames: 14512128. Throughput: 0: 2513.4, 1: 2513.2. Samples: 12069904. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:37,044][72530] Avg episode reward: [(0, '150806.538'), (1, '155291.907')]
+-[2023-09-19 11:54:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014152_7245824.pth...
+-[2023-09-19 11:54:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014192_7266304.pth...
+-[2023-09-19 11:54:37,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000014000_7168000.pth
+-[2023-09-19 11:54:37,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000014040_7188480.pth
+-[2023-09-19 11:54:42,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5051.7, 300 sec: 5442.8). Total num frames: 14536704. Throughput: 0: 2545.0, 1: 2545.5. Samples: 12099376. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:54:42,045][72530] Avg episode reward: [(0, '151204.698'), (1, '156645.148')]
+-[2023-09-19 11:54:46,277][73145] Updated weights for policy 0, policy_version 14240 (0.0011)
+-[2023-09-19 11:54:46,277][73219] Updated weights for policy 1, policy_version 14200 (0.0011)
+-[2023-09-19 11:54:47,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5051.7, 300 sec: 5415.1). Total num frames: 14561280. Throughput: 0: 2519.7, 1: 2520.0. Samples: 12128874. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:54:47,044][72530] Avg episode reward: [(0, '151204.698'), (1, '156645.148')]
+-[2023-09-19 11:54:52,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5415.0). Total num frames: 14585856. Throughput: 0: 2545.9, 1: 2545.9. Samples: 12145282. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:52,045][72530] Avg episode reward: [(0, '150668.353'), (1, '159741.496')]
+-[2023-09-19 11:54:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014224_7282688.pth...
+-[2023-09-19 11:54:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014264_7303168.pth...
+-[2023-09-19 11:54:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000014080_7208960.pth
+-[2023-09-19 11:54:52,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000014120_7229440.pth
+-[2023-09-19 11:54:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5415.1). Total num frames: 14610432. Throughput: 0: 2537.3, 1: 2537.6. Samples: 12174958. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:57,045][72530] Avg episode reward: [(0, '151344.969'), (1, '159741.496')]
+-[2023-09-19 11:55:02,044][72530] Fps is (10 sec: 4914.7, 60 sec: 5051.6, 300 sec: 5387.3). Total num frames: 14635008. Throughput: 0: 2521.2, 1: 2521.7. Samples: 12205832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:55:02,045][72530] Avg episode reward: [(0, '151628.001'), (1, '160794.096')]
+-[2023-09-19 11:55:02,322][73219] Updated weights for policy 1, policy_version 14280 (0.0013)
+-[2023-09-19 11:55:02,323][73145] Updated weights for policy 0, policy_version 14320 (0.0013)
+-[2023-09-19 11:55:07,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5415.1). Total num frames: 14659584. Throughput: 0: 2513.9, 1: 2512.9. Samples: 12219370. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:55:07,044][72530] Avg episode reward: [(0, '148176.544'), (1, '161684.229')]
+-[2023-09-19 11:55:07,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014296_7319552.pth...
+-[2023-09-19 11:55:07,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014336_7340032.pth...
+-[2023-09-19 11:55:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000014152_7245824.pth
+-[2023-09-19 11:55:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000014192_7266304.pth
+-[2023-09-19 11:55:12,043][72530] Fps is (10 sec: 4915.8, 60 sec: 5051.7, 300 sec: 5387.3). Total num frames: 14684160. Throughput: 0: 2444.2, 1: 2444.4. Samples: 12245164. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:55:12,045][72530] Avg episode reward: [(0, '148176.544'), (1, '161684.229')]
+-[2023-09-19 11:55:17,043][72530] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5387.3). Total num frames: 14708736. Throughput: 0: 2444.5, 1: 2444.5. Samples: 12275438. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:55:17,045][72530] Avg episode reward: [(0, '148556.520'), (1, '161543.907')]
+-[2023-09-19 11:55:19,505][73219] Updated weights for policy 1, policy_version 14360 (0.0011)
+-[2023-09-19 11:55:19,506][73145] Updated weights for policy 0, policy_version 14400 (0.0014)
+-[2023-09-19 11:55:22,043][72530] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5387.3). Total num frames: 14733312. Throughput: 0: 2457.9, 1: 2457.9. Samples: 12291112. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:55:22,044][72530] Avg episode reward: [(0, '146305.866'), (1, '161543.272')]
+-[2023-09-19 11:55:22,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth...
+-[2023-09-19 11:55:22,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth...
+-[2023-09-19 11:55:22,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000014224_7282688.pth
+-[2023-09-19 11:55:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000014264_7303168.pth
+-[2023-09-19 11:55:22,280][72530] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 72530], exiting...
+-[2023-09-19 11:55:22,281][72530] Runner profile tree view:
+-main_loop: 2141.4988
+-[2023-09-19 11:55:22,282][72530] Collected {1: 7356416, 0: 7376896}, FPS: 5741.9
+-[2023-09-19 11:55:22,281][73130] Stopping Batcher_0...
+-[2023-09-19 11:55:22,281][73131] Stopping Batcher_1...
+-[2023-09-19 11:55:22,282][73130] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:55:22,282][73131] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:55:22,282][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth...
+-[2023-09-19 11:55:22,283][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth...
+-[2023-09-19 11:55:22,285][73221] Stopping RolloutWorker_w1...
+-[2023-09-19 11:55:22,285][73221] Loop rollout_proc1_evt_loop terminating...
+-[2023-09-19 11:55:22,288][73220] Stopping RolloutWorker_w2...
+-[2023-09-19 11:55:22,288][73130] Stopping LearnerWorker_p0...
+-[2023-09-19 11:55:22,288][73220] Loop rollout_proc2_evt_loop terminating...
+-[2023-09-19 11:55:22,288][73130] Loop learner_proc0_evt_loop terminating...
+-[2023-09-19 11:55:22,288][73222] Stopping RolloutWorker_w6...
+-[2023-09-19 11:55:22,288][73131] Stopping LearnerWorker_p1...
+-[2023-09-19 11:55:22,289][73222] Loop rollout_proc6_evt_loop terminating...
+-[2023-09-19 11:55:22,289][73131] Loop learner_proc1_evt_loop terminating...
+-[2023-09-19 11:55:22,290][73218] Stopping RolloutWorker_w0...
+-[2023-09-19 11:55:22,290][73224] Stopping RolloutWorker_w4...
+-[2023-09-19 11:55:22,291][73218] Loop rollout_proc0_evt_loop terminating...
+-[2023-09-19 11:55:22,291][73223] Stopping RolloutWorker_w3...
+-[2023-09-19 11:55:22,291][73224] Loop rollout_proc4_evt_loop terminating...
+-[2023-09-19 11:55:22,291][73223] Loop rollout_proc3_evt_loop terminating...
+-[2023-09-19 11:55:22,292][73226] Stopping RolloutWorker_w7...
+-[2023-09-19 11:55:22,292][73226] Loop rollout_proc7_evt_loop terminating...
+-[2023-09-19 11:55:22,295][73229] Stopping RolloutWorker_w5...
+-[2023-09-19 11:55:22,295][73229] Loop rollout_proc5_evt_loop terminating...
+-[2023-09-19 11:55:22,296][73145] Weights refcount: 2 0
+-[2023-09-19 11:55:22,297][73145] Stopping InferenceWorker_p0-w0...
+-[2023-09-19 11:55:22,297][73145] Loop inference_proc0-0_evt_loop terminating...
+-[2023-09-19 11:55:22,301][73219] Weights refcount: 2 0
+-[2023-09-19 11:55:22,303][73219] Stopping InferenceWorker_p1-w0...
+-[2023-09-19 11:55:22,303][73219] Loop inference_proc1-0_evt_loop terminating...
++[2023-09-21 15:10:45,648][101116] Worker 0 uses CPU cores [0, 1, 2, 3]
++[2023-09-21 15:10:45,774][101118] Worker 1 uses CPU cores [4, 5, 6, 7]
++[2023-09-21 15:10:46,022][101035] Using optimizer <class 'torch.optim.adam.Adam'>
++[2023-09-21 15:10:46,023][101035] No checkpoints found
++[2023-09-21 15:10:46,023][101035] Did not load from checkpoint, starting from scratch!
++[2023-09-21 15:10:46,023][101035] Initialized policy 1 weights for model version 0
++[2023-09-21 15:10:46,025][101035] LearnerWorker_p1 finished initialization!
++[2023-09-21 15:10:46,025][101035] Using GPUs [0] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:46,158][101034] Using optimizer <class 'torch.optim.adam.Adam'>
++[2023-09-21 15:10:46,159][101034] No checkpoints found
++[2023-09-21 15:10:46,159][101034] Did not load from checkpoint, starting from scratch!
++[2023-09-21 15:10:46,159][101034] Initialized policy 0 weights for model version 0
++[2023-09-21 15:10:46,161][101034] LearnerWorker_p0 finished initialization!
++[2023-09-21 15:10:46,161][101034] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:46,569][101117] RunningMeanStd input shape: (376,)
++[2023-09-21 15:10:46,570][101117] RunningMeanStd input shape: (1,)
++[2023-09-21 15:10:46,602][99566] Inference worker 1-0 is ready!
++[2023-09-21 15:10:46,707][101115] RunningMeanStd input shape: (376,)
++[2023-09-21 15:10:46,707][101115] RunningMeanStd input shape: (1,)
++[2023-09-21 15:10:46,739][99566] Inference worker 0-0 is ready!
++[2023-09-21 15:10:46,740][99566] All inference workers are ready! Signal rollout workers to start!
++[2023-09-21 15:10:46,835][101122] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,836][101122] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,836][101120] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,837][101120] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,838][101118] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,838][101116] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,839][101118] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,839][101119] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,839][101116] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,840][101119] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,840][101121] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,841][101121] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,843][101124] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,844][101124] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,851][101123] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,852][101123] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,887][101120] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,887][101122] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,888][101116] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,892][101119] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,893][101118] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,893][101121] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,897][101124] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,903][101123] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,985][101116] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,985][101122] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,985][101120] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,989][101119] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,990][101118] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,995][101121] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,998][101124] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:47,003][101123] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:47,149][101119] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,153][101120] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,154][101116] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,156][101122] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,157][101118] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,163][101121] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,164][101123] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,170][101124] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,345][101119] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,348][101120] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,349][101118] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,359][101123] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,363][101122] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,370][101121] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,372][101124] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,377][101116] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,595][101123] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,596][101120] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,600][101118] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,603][101119] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,609][101122] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,611][101121] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,632][101116] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,633][101124] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,892][101118] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,903][101119] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,910][101122] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,915][101121] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,915][101123] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,917][101120] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,930][101124] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,947][101116] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:49,496][99566] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan, 1: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
++[2023-09-21 15:10:54,497][99566] Fps is (10 sec: 3276.5, 60 sec: 3276.5, 300 sec: 3276.5). Total num frames: 16384. Throughput: 0: 1638.3, 1: 1638.3. Samples: 16384. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:10:54,861][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000024_12288.pth...
++[2023-09-21 15:10:54,871][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000024_12288.pth...
++[2023-09-21 15:10:59,497][99566] Fps is (10 sec: 5734.3, 60 sec: 5734.3, 300 sec: 5734.3). Total num frames: 57344. Throughput: 0: 2677.6, 1: 2619.8. Samples: 52974. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:10:59,498][99566] Avg episode reward: [(0, '29111.123'), (1, '26500.965')]
++[2023-09-21 15:11:03,368][101115] Updated weights for policy 0, policy_version 80 (0.0014)
++[2023-09-21 15:11:03,369][101117] Updated weights for policy 1, policy_version 80 (0.0013)
++[2023-09-21 15:11:03,395][99566] Heartbeat connected on Batcher_0
++[2023-09-21 15:11:03,398][99566] Heartbeat connected on LearnerWorker_p0
++[2023-09-21 15:11:03,401][99566] Heartbeat connected on Batcher_1
++[2023-09-21 15:11:03,404][99566] Heartbeat connected on LearnerWorker_p1
++[2023-09-21 15:11:03,410][99566] Heartbeat connected on InferenceWorker_p0-w0
++[2023-09-21 15:11:03,415][99566] Heartbeat connected on InferenceWorker_p1-w0
++[2023-09-21 15:11:03,419][99566] Heartbeat connected on RolloutWorker_w0
++[2023-09-21 15:11:03,420][99566] Heartbeat connected on RolloutWorker_w1
++[2023-09-21 15:11:03,425][99566] Heartbeat connected on RolloutWorker_w2
++[2023-09-21 15:11:03,430][99566] Heartbeat connected on RolloutWorker_w5
++[2023-09-21 15:11:03,432][99566] Heartbeat connected on RolloutWorker_w3
++[2023-09-21 15:11:03,435][99566] Heartbeat connected on RolloutWorker_w4
++[2023-09-21 15:11:03,435][99566] Heartbeat connected on RolloutWorker_w6
++[2023-09-21 15:11:03,441][99566] Heartbeat connected on RolloutWorker_w7
++[2023-09-21 15:11:04,497][99566] Fps is (10 sec: 6553.8, 60 sec: 5461.3, 300 sec: 5461.3). Total num frames: 81920. Throughput: 0: 2445.3, 1: 2433.3. Samples: 73180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:04,498][99566] Avg episode reward: [(0, '32653.580'), (1, '29531.158')]
++[2023-09-21 15:11:09,497][99566] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5734.4). Total num frames: 114688. Throughput: 0: 2741.4, 1: 2711.0. Samples: 109048. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:11:09,497][99566] Avg episode reward: [(0, '42202.736'), (1, '37345.618')]
++[2023-09-21 15:11:09,500][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000112_57344.pth...
++[2023-09-21 15:11:09,500][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000112_57344.pth...
++[2023-09-21 15:11:14,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6225.9, 300 sec: 6225.9). Total num frames: 155648. Throughput: 0: 3059.7, 1: 3035.7. Samples: 152388. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:11:14,498][99566] Avg episode reward: [(0, '44269.193'), (1, '39095.771')]
++[2023-09-21 15:11:15,281][101117] Updated weights for policy 1, policy_version 160 (0.0014)
++[2023-09-21 15:11:15,282][101115] Updated weights for policy 0, policy_version 160 (0.0014)
++[2023-09-21 15:11:19,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6280.5, 300 sec: 6280.5). Total num frames: 188416. Throughput: 0: 2891.8, 1: 2871.1. Samples: 172888. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:11:19,498][99566] Avg episode reward: [(0, '52608.069'), (1, '46035.948')]
++[2023-09-21 15:11:24,497][99566] Fps is (10 sec: 7372.7, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 229376. Throughput: 0: 3103.4, 1: 3086.0. Samples: 216632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:24,498][99566] Avg episode reward: [(0, '52608.069'), (1, '49544.367')]
++[2023-09-21 15:11:24,502][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000224_114688.pth...
++[2023-09-21 15:11:24,502][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000224_114688.pth...
++[2023-09-21 15:11:24,508][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000024_12288.pth
++[2023-09-21 15:11:24,509][101035] Saving new best policy, reward=49544.367!
++[2023-09-21 15:11:24,510][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000024_12288.pth
++[2023-09-21 15:11:24,511][101034] Saving new best policy, reward=52608.069!
++[2023-09-21 15:11:26,547][101117] Updated weights for policy 1, policy_version 240 (0.0011)
++[2023-09-21 15:11:26,548][101115] Updated weights for policy 0, policy_version 240 (0.0012)
++[2023-09-21 15:11:29,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 262144. Throughput: 0: 3277.6, 1: 3275.7. Samples: 262134. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
++[2023-09-21 15:11:29,497][99566] Avg episode reward: [(0, '66016.832'), (1, '59449.959')]
++[2023-09-21 15:11:29,498][101034] Saving new best policy, reward=66016.832!
++[2023-09-21 15:11:29,498][101035] Saving new best policy, reward=59449.959!
++[2023-09-21 15:11:34,496][99566] Fps is (10 sec: 6963.4, 60 sec: 6644.6, 300 sec: 6644.6). Total num frames: 299008. Throughput: 0: 3152.0, 1: 3139.7. Samples: 283126. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:34,497][99566] Avg episode reward: [(0, '68820.170'), (1, '64166.988')]
++[2023-09-21 15:11:34,497][101034] Saving new best policy, reward=68820.170!
++[2023-09-21 15:11:34,499][101035] Saving new best policy, reward=64166.988!
++[2023-09-21 15:11:37,925][101117] Updated weights for policy 1, policy_version 320 (0.0015)
++[2023-09-21 15:11:37,925][101115] Updated weights for policy 0, policy_version 320 (0.0013)
++[2023-09-21 15:11:39,497][99566] Fps is (10 sec: 7372.6, 60 sec: 6717.4, 300 sec: 6717.4). Total num frames: 335872. Throughput: 0: 3456.7, 1: 3448.0. Samples: 327094. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:39,498][99566] Avg episode reward: [(0, '75159.121'), (1, '68598.547')]
++[2023-09-21 15:11:39,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000328_167936.pth...
++[2023-09-21 15:11:39,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000328_167936.pth...
++[2023-09-21 15:11:39,513][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000112_57344.pth
++[2023-09-21 15:11:39,513][101035] Saving new best policy, reward=68598.547!
++[2023-09-21 15:11:39,515][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000112_57344.pth
++[2023-09-21 15:11:39,516][101034] Saving new best policy, reward=75159.121!
++[2023-09-21 15:11:44,497][99566] Fps is (10 sec: 6963.0, 60 sec: 6702.5, 300 sec: 6702.5). Total num frames: 368640. Throughput: 0: 3484.0, 1: 3483.4. Samples: 366510. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:44,498][99566] Avg episode reward: [(0, '77287.138'), (1, '73006.291')]
++[2023-09-21 15:11:44,499][101034] Saving new best policy, reward=77287.138!
++[2023-09-21 15:11:44,499][101035] Saving new best policy, reward=73006.291!
++[2023-09-21 15:11:49,496][99566] Fps is (10 sec: 6553.8, 60 sec: 6690.1, 300 sec: 6690.1). Total num frames: 401408. Throughput: 0: 3500.4, 1: 3490.9. Samples: 387786. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:49,497][99566] Avg episode reward: [(0, '79728.904'), (1, '73989.310')]
++[2023-09-21 15:11:49,498][101034] Saving new best policy, reward=79728.904!
++[2023-09-21 15:11:49,498][101035] Saving new best policy, reward=73989.310!
++[2023-09-21 15:11:49,630][101117] Updated weights for policy 1, policy_version 400 (0.0014)
++[2023-09-21 15:11:49,630][101115] Updated weights for policy 0, policy_version 400 (0.0015)
++[2023-09-21 15:11:54,496][99566] Fps is (10 sec: 7372.8, 60 sec: 7099.8, 300 sec: 6805.7). Total num frames: 442368. Throughput: 0: 3564.5, 1: 3565.1. Samples: 429880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:54,497][99566] Avg episode reward: [(0, '83640.081'), (1, '77200.239')]
++[2023-09-21 15:11:54,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000432_221184.pth...
++[2023-09-21 15:11:54,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000432_221184.pth...
++[2023-09-21 15:11:54,512][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000224_114688.pth
++[2023-09-21 15:11:54,512][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000224_114688.pth
++[2023-09-21 15:11:54,513][101034] Saving new best policy, reward=83640.081!
++[2023-09-21 15:11:54,513][101035] Saving new best policy, reward=77200.239!
++[2023-09-21 15:11:59,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6826.7, 300 sec: 6670.6). Total num frames: 466944. Throughput: 0: 3511.4, 1: 3516.1. Samples: 468628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:59,498][99566] Avg episode reward: [(0, '84922.994'), (1, '77768.201')]
++[2023-09-21 15:11:59,499][101034] Saving new best policy, reward=84922.994!
++[2023-09-21 15:11:59,499][101035] Saving new best policy, reward=77768.201!
++[2023-09-21 15:12:02,658][101117] Updated weights for policy 1, policy_version 480 (0.0016)
++[2023-09-21 15:12:02,658][101115] Updated weights for policy 0, policy_version 480 (0.0011)
++[2023-09-21 15:12:04,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6963.2, 300 sec: 6662.8). Total num frames: 499712. Throughput: 0: 3466.4, 1: 3468.6. Samples: 484962. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:12:04,497][99566] Avg episode reward: [(0, '88681.435'), (1, '80463.062')]
++[2023-09-21 15:12:04,498][101034] Saving new best policy, reward=88681.435!
++[2023-09-21 15:12:04,498][101035] Saving new best policy, reward=80463.062!
++[2023-09-21 15:12:09,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6963.2, 300 sec: 6656.0). Total num frames: 532480. Throughput: 0: 3427.1, 1: 3427.7. Samples: 525100. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:12:09,498][99566] Avg episode reward: [(0, '89644.782'), (1, '81336.452')]
++[2023-09-21 15:12:09,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000520_266240.pth...
++[2023-09-21 15:12:09,509][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000520_266240.pth...
++[2023-09-21 15:12:09,515][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000328_167936.pth
++[2023-09-21 15:12:09,516][101035] Saving new best policy, reward=81336.452!
++[2023-09-21 15:12:09,517][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000328_167936.pth
++[2023-09-21 15:12:09,517][101034] Saving new best policy, reward=89644.782!
++[2023-09-21 15:12:14,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6826.7, 300 sec: 6650.0). Total num frames: 565248. Throughput: 0: 3353.4, 1: 3345.7. Samples: 563594. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:12:14,498][99566] Avg episode reward: [(0, '93904.727'), (1, '84817.215')]
++[2023-09-21 15:12:14,499][101034] Saving new best policy, reward=93904.727!
++[2023-09-21 15:12:14,499][101035] Saving new best policy, reward=84817.215!
++[2023-09-21 15:12:15,959][101117] Updated weights for policy 1, policy_version 560 (0.0014)
++[2023-09-21 15:12:15,960][101115] Updated weights for policy 0, policy_version 560 (0.0012)
++[2023-09-21 15:12:19,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6826.7, 300 sec: 6644.6). Total num frames: 598016. Throughput: 0: 3291.8, 1: 3291.1. Samples: 579360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:12:19,498][99566] Avg episode reward: [(0, '95010.164'), (1, '85718.694')]
++[2023-09-21 15:12:19,499][101034] Saving new best policy, reward=95010.164!
++[2023-09-21 15:12:19,499][101035] Saving new best policy, reward=85718.694!
++[2023-09-21 15:12:24,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6639.8). Total num frames: 630784. Throughput: 0: 3273.7, 1: 3269.4. Samples: 621534. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:12:24,498][99566] Avg episode reward: [(0, '98412.703'), (1, '89341.648')]
++[2023-09-21 15:12:24,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000616_315392.pth...
++[2023-09-21 15:12:24,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000616_315392.pth...
++[2023-09-21 15:12:24,515][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000432_221184.pth
++[2023-09-21 15:12:24,516][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000432_221184.pth
++[2023-09-21 15:12:24,516][101034] Saving new best policy, reward=98412.703!
++[2023-09-21 15:12:24,517][101035] Saving new best policy, reward=89341.648!
++[2023-09-21 15:12:27,494][101115] Updated weights for policy 0, policy_version 640 (0.0013)
++[2023-09-21 15:12:27,495][101117] Updated weights for policy 1, policy_version 640 (0.0015)
++[2023-09-21 15:12:29,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6690.1, 300 sec: 6635.5). Total num frames: 663552. Throughput: 0: 3307.6, 1: 3308.7. Samples: 664240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:12:29,497][99566] Avg episode reward: [(0, '100510.374'), (1, '91250.829')]
++[2023-09-21 15:12:29,498][101034] Saving new best policy, reward=100510.374!
++[2023-09-21 15:12:29,498][101035] Saving new best policy, reward=91250.829!
++[2023-09-21 15:12:34,496][99566] Fps is (10 sec: 7372.9, 60 sec: 6758.4, 300 sec: 6709.6). Total num frames: 704512. Throughput: 0: 3325.3, 1: 3326.3. Samples: 687108. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:12:34,498][99566] Avg episode reward: [(0, '106969.058'), (1, '95836.961')]
++[2023-09-21 15:12:34,499][101034] Saving new best policy, reward=106969.058!
++[2023-09-21 15:12:34,499][101035] Saving new best policy, reward=95836.961!
++[2023-09-21 15:12:38,780][101115] Updated weights for policy 0, policy_version 720 (0.0012)
++[2023-09-21 15:12:38,780][101117] Updated weights for policy 1, policy_version 720 (0.0015)
++[2023-09-21 15:12:39,497][99566] Fps is (10 sec: 7372.7, 60 sec: 6690.1, 300 sec: 6702.5). Total num frames: 737280. Throughput: 0: 3329.2, 1: 3331.7. Samples: 729624. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:12:39,498][99566] Avg episode reward: [(0, '106969.058'), (1, '97182.862')]
++[2023-09-21 15:12:39,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000720_368640.pth...
++[2023-09-21 15:12:39,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000720_368640.pth...
++[2023-09-21 15:12:39,517][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000520_266240.pth
++[2023-09-21 15:12:39,517][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000520_266240.pth
++[2023-09-21 15:12:39,517][101035] Saving new best policy, reward=97182.862!
++[2023-09-21 15:12:44,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6690.1, 300 sec: 6696.1). Total num frames: 770048. Throughput: 0: 3327.6, 1: 3329.0. Samples: 768176. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
++[2023-09-21 15:12:44,497][99566] Avg episode reward: [(0, '113117.062'), (1, '101505.450')]
++[2023-09-21 15:12:44,498][101034] Saving new best policy, reward=113117.062!
++[2023-09-21 15:12:44,498][101035] Saving new best policy, reward=101505.450!
++[2023-09-21 15:12:49,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6690.1, 300 sec: 6690.1). Total num frames: 802816. Throughput: 0: 3349.2, 1: 3355.5. Samples: 786672. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:12:49,497][99566] Avg episode reward: [(0, '113117.062'), (1, '101932.079')]
++[2023-09-21 15:12:49,499][101035] Saving new best policy, reward=101932.079!
++[2023-09-21 15:12:51,683][101115] Updated weights for policy 0, policy_version 800 (0.0014)
++[2023-09-21 15:12:51,683][101117] Updated weights for policy 1, policy_version 800 (0.0013)
++[2023-09-21 15:12:54,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6684.7). Total num frames: 835584. Throughput: 0: 3348.4, 1: 3351.9. Samples: 826612. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:12:54,497][99566] Avg episode reward: [(0, '116085.972'), (1, '103659.764')]
++[2023-09-21 15:12:54,505][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000816_417792.pth...
++[2023-09-21 15:12:54,505][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000816_417792.pth...
++[2023-09-21 15:12:54,509][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000616_315392.pth
++[2023-09-21 15:12:54,509][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000616_315392.pth
++[2023-09-21 15:12:54,509][101034] Saving new best policy, reward=116085.972!
++[2023-09-21 15:12:54,509][101035] Saving new best policy, reward=103659.764!
++[2023-09-21 15:12:59,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6679.6). Total num frames: 868352. Throughput: 0: 3349.9, 1: 3347.9. Samples: 864992. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:12:59,497][99566] Avg episode reward: [(0, '116085.972'), (1, '104473.905')]
++[2023-09-21 15:12:59,498][101035] Saving new best policy, reward=104473.905!
++[2023-09-21 15:13:04,444][101115] Updated weights for policy 0, policy_version 880 (0.0016)
++[2023-09-21 15:13:04,444][101117] Updated weights for policy 1, policy_version 880 (0.0015)
++[2023-09-21 15:13:04,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6675.0). Total num frames: 901120. Throughput: 0: 3359.1, 1: 3359.9. Samples: 881714. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:13:04,497][99566] Avg episode reward: [(0, '120958.463'), (1, '109086.335')]
++[2023-09-21 15:13:04,498][101034] Saving new best policy, reward=120958.463!
++[2023-09-21 15:13:04,498][101035] Saving new best policy, reward=109086.335!
++[2023-09-21 15:13:09,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6690.1, 300 sec: 6670.6). Total num frames: 933888. Throughput: 0: 3373.1, 1: 3378.0. Samples: 925336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:09,497][99566] Avg episode reward: [(0, '121585.003'), (1, '109071.902')]
++[2023-09-21 15:13:09,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000912_466944.pth...
++[2023-09-21 15:13:09,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000912_466944.pth...
++[2023-09-21 15:13:09,516][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000720_368640.pth
++[2023-09-21 15:13:09,516][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000720_368640.pth
++[2023-09-21 15:13:09,517][101034] Saving new best policy, reward=121585.003!
++[2023-09-21 15:13:14,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6666.6). Total num frames: 966656. Throughput: 0: 3353.0, 1: 3356.2. Samples: 966154. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
++[2023-09-21 15:13:14,497][99566] Avg episode reward: [(0, '122500.165'), (1, '112494.272')]
++[2023-09-21 15:13:14,498][101034] Saving new best policy, reward=122500.165!
++[2023-09-21 15:13:14,498][101035] Saving new best policy, reward=112494.272!
++[2023-09-21 15:13:16,904][101117] Updated weights for policy 1, policy_version 960 (0.0014)
++[2023-09-21 15:13:16,904][101115] Updated weights for policy 0, policy_version 960 (0.0012)
++[2023-09-21 15:13:19,497][99566] Fps is (10 sec: 5734.4, 60 sec: 6553.6, 300 sec: 6608.2). Total num frames: 991232. Throughput: 0: 3280.2, 1: 3286.4. Samples: 982602. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:19,497][99566] Avg episode reward: [(0, '124457.495'), (1, '113067.463')]
++[2023-09-21 15:13:19,499][101034] Saving new best policy, reward=124457.495!
++[2023-09-21 15:13:19,499][101035] Saving new best policy, reward=113067.463!
++[2023-09-21 15:13:24,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6553.6, 300 sec: 6606.4). Total num frames: 1024000. Throughput: 0: 3215.8, 1: 3213.7. Samples: 1018952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:24,498][99566] Avg episode reward: [(0, '128172.103'), (1, '116190.090')]
++[2023-09-21 15:13:24,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001000_512000.pth...
++[2023-09-21 15:13:24,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001000_512000.pth...
++[2023-09-21 15:13:24,513][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000816_417792.pth
++[2023-09-21 15:13:24,513][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000816_417792.pth
++[2023-09-21 15:13:24,513][101035] Saving new best policy, reward=116190.090!
++[2023-09-21 15:13:24,514][101034] Saving new best policy, reward=128172.103!
++[2023-09-21 15:13:29,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6604.8). Total num frames: 1056768. Throughput: 0: 3251.9, 1: 3247.1. Samples: 1060632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:29,498][99566] Avg episode reward: [(0, '129655.387'), (1, '116680.591')]
++[2023-09-21 15:13:29,499][101034] Saving new best policy, reward=129655.387!
++[2023-09-21 15:13:29,499][101035] Saving new best policy, reward=116680.591!
++[2023-09-21 15:13:29,751][101117] Updated weights for policy 1, policy_version 1040 (0.0013)
++[2023-09-21 15:13:29,751][101115] Updated weights for policy 0, policy_version 1040 (0.0013)
++[2023-09-21 15:13:34,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6603.2). Total num frames: 1089536. Throughput: 0: 3241.6, 1: 3235.9. Samples: 1078160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:34,498][99566] Avg episode reward: [(0, '131544.446'), (1, '116603.723')]
++[2023-09-21 15:13:34,499][101034] Saving new best policy, reward=131544.446!
++[2023-09-21 15:13:39,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6601.8). Total num frames: 1122304. Throughput: 0: 3209.9, 1: 3206.6. Samples: 1115360. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:13:39,498][99566] Avg episode reward: [(0, '132903.044'), (1, '116397.835')]
++[2023-09-21 15:13:39,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001096_561152.pth...
++[2023-09-21 15:13:39,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001096_561152.pth...
++[2023-09-21 15:13:39,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000912_466944.pth
++[2023-09-21 15:13:39,516][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000912_466944.pth
++[2023-09-21 15:13:39,517][101034] Saving new best policy, reward=132903.044!
++[2023-09-21 15:13:42,911][101115] Updated weights for policy 0, policy_version 1120 (0.0014)
++[2023-09-21 15:13:42,911][101117] Updated weights for policy 1, policy_version 1120 (0.0013)
++[2023-09-21 15:13:44,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6600.4). Total num frames: 1155072. Throughput: 0: 3195.6, 1: 3195.7. Samples: 1152604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:44,498][99566] Avg episode reward: [(0, '137104.414'), (1, '119496.691')]
++[2023-09-21 15:13:44,499][101034] Saving new best policy, reward=137104.414!
++[2023-09-21 15:13:44,499][101035] Saving new best policy, reward=119496.691!
++[2023-09-21 15:13:49,496][99566] Fps is (10 sec: 5734.5, 60 sec: 6280.5, 300 sec: 6553.6). Total num frames: 1179648. Throughput: 0: 3200.2, 1: 3200.0. Samples: 1169724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:49,497][99566] Avg episode reward: [(0, '137104.414'), (1, '121701.677')]
++[2023-09-21 15:13:49,526][101035] Saving new best policy, reward=121701.677!
++[2023-09-21 15:13:54,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.0, 300 sec: 6597.9). Total num frames: 1220608. Throughput: 0: 3163.7, 1: 3159.2. Samples: 1209864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:54,498][99566] Avg episode reward: [(0, '142552.888'), (1, '126028.832')]
++[2023-09-21 15:13:54,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001192_610304.pth...
++[2023-09-21 15:13:54,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001192_610304.pth...
++[2023-09-21 15:13:54,515][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001000_512000.pth
++[2023-09-21 15:13:54,515][101035] Saving new best policy, reward=126028.832!
++[2023-09-21 15:13:54,516][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001000_512000.pth
++[2023-09-21 15:13:54,516][101034] Saving new best policy, reward=142552.888!
++[2023-09-21 15:13:55,395][101117] Updated weights for policy 1, policy_version 1200 (0.0013)
++[2023-09-21 15:13:55,395][101115] Updated weights for policy 0, policy_version 1200 (0.0014)
++[2023-09-21 15:13:59,496][99566] Fps is (10 sec: 7372.9, 60 sec: 6417.1, 300 sec: 6596.7). Total num frames: 1253376. Throughput: 0: 3178.4, 1: 3175.2. Samples: 1252066. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:59,497][99566] Avg episode reward: [(0, '143172.574'), (1, '126257.348')]
++[2023-09-21 15:13:59,498][101034] Saving new best policy, reward=143172.574!
++[2023-09-21 15:13:59,498][101035] Saving new best policy, reward=126257.348!
++[2023-09-21 15:14:04,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6595.6). Total num frames: 1286144. Throughput: 0: 3190.2, 1: 3193.8. Samples: 1269880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:04,497][99566] Avg episode reward: [(0, '143312.733'), (1, '133847.080')]
++[2023-09-21 15:14:04,498][101035] Saving new best policy, reward=133847.080!
++[2023-09-21 15:14:04,498][101034] Saving new best policy, reward=143312.733!
++[2023-09-21 15:14:07,603][101117] Updated weights for policy 1, policy_version 1280 (0.0015)
++[2023-09-21 15:14:07,604][101115] Updated weights for policy 0, policy_version 1280 (0.0013)
++[2023-09-21 15:14:09,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6594.6). Total num frames: 1318912. Throughput: 0: 3247.3, 1: 3248.9. Samples: 1311276. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:14:09,497][99566] Avg episode reward: [(0, '142024.998'), (1, '135803.021')]
++[2023-09-21 15:14:09,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001288_659456.pth...
++[2023-09-21 15:14:09,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001288_659456.pth...
++[2023-09-21 15:14:09,514][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001096_561152.pth
++[2023-09-21 15:14:09,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001096_561152.pth
++[2023-09-21 15:14:09,514][101035] Saving new best policy, reward=135803.021!
++[2023-09-21 15:14:14,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6593.6). Total num frames: 1351680. Throughput: 0: 3252.1, 1: 3252.0. Samples: 1353318. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:14:14,497][99566] Avg episode reward: [(0, '137567.192'), (1, '137580.324')]
++[2023-09-21 15:14:14,498][101035] Saving new best policy, reward=137580.324!
++[2023-09-21 15:14:19,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6553.6, 300 sec: 6592.6). Total num frames: 1384448. Throughput: 0: 3300.0, 1: 3298.9. Samples: 1375110. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:14:19,497][99566] Avg episode reward: [(0, '135167.354'), (1, '138853.897')]
++[2023-09-21 15:14:19,498][101035] Saving new best policy, reward=138853.897!
++[2023-09-21 15:14:19,579][101115] Updated weights for policy 0, policy_version 1360 (0.0013)
++[2023-09-21 15:14:19,580][101117] Updated weights for policy 1, policy_version 1360 (0.0011)
++[2023-09-21 15:14:24,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6417.1, 300 sec: 6553.6). Total num frames: 1409024. Throughput: 0: 3251.1, 1: 3259.6. Samples: 1408344. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:14:24,497][99566] Avg episode reward: [(0, '133135.888'), (1, '140760.635')]
++[2023-09-21 15:14:24,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001376_704512.pth...
++[2023-09-21 15:14:24,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001376_704512.pth...
++[2023-09-21 15:14:24,519][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001192_610304.pth
++[2023-09-21 15:14:24,519][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001192_610304.pth
++[2023-09-21 15:14:24,520][101035] Saving new best policy, reward=140760.635!
++[2023-09-21 15:14:29,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6417.1, 300 sec: 6553.6). Total num frames: 1441792. Throughput: 0: 3224.6, 1: 3224.8. Samples: 1442826. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:14:29,498][99566] Avg episode reward: [(0, '133811.659'), (1, '141653.024')]
++[2023-09-21 15:14:29,499][101035] Saving new best policy, reward=141653.024!
++[2023-09-21 15:14:33,167][101115] Updated weights for policy 0, policy_version 1440 (0.0014)
++[2023-09-21 15:14:33,167][101117] Updated weights for policy 1, policy_version 1440 (0.0011)
++[2023-09-21 15:14:34,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6553.6, 300 sec: 6590.0). Total num frames: 1482752. Throughput: 0: 3281.4, 1: 3281.6. Samples: 1465058. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:34,498][99566] Avg episode reward: [(0, '137138.699'), (1, '143246.225')]
++[2023-09-21 15:14:34,499][101035] Saving new best policy, reward=143246.225!
++[2023-09-21 15:14:39,496][99566] Fps is (10 sec: 7372.9, 60 sec: 6553.6, 300 sec: 6589.2). Total num frames: 1515520. Throughput: 0: 3298.9, 1: 3303.3. Samples: 1506962. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:39,497][99566] Avg episode reward: [(0, '138323.470'), (1, '146247.815')]
++[2023-09-21 15:14:39,505][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001480_757760.pth...
++[2023-09-21 15:14:39,505][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001480_757760.pth...
++[2023-09-21 15:14:39,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001288_659456.pth
++[2023-09-21 15:14:39,515][101035] Saving new best policy, reward=146247.815!
++[2023-09-21 15:14:39,515][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001288_659456.pth
++[2023-09-21 15:14:44,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6553.6, 300 sec: 6588.5). Total num frames: 1548288. Throughput: 0: 3242.7, 1: 3242.9. Samples: 1543918. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:44,497][99566] Avg episode reward: [(0, '146316.476'), (1, '147786.818')]
++[2023-09-21 15:14:44,498][101034] Saving new best policy, reward=146316.476!
++[2023-09-21 15:14:44,498][101035] Saving new best policy, reward=147786.818!
++[2023-09-21 15:14:46,115][101115] Updated weights for policy 0, policy_version 1520 (0.0014)
++[2023-09-21 15:14:46,115][101117] Updated weights for policy 1, policy_version 1520 (0.0015)
++[2023-09-21 15:14:49,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 1572864. Throughput: 0: 3228.2, 1: 3221.9. Samples: 1560134. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:49,497][99566] Avg episode reward: [(0, '148683.548'), (1, '148519.388')]
++[2023-09-21 15:14:49,498][101034] Saving new best policy, reward=148683.548!
++[2023-09-21 15:14:49,498][101035] Saving new best policy, reward=148519.388!
++[2023-09-21 15:14:54,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6417.1, 300 sec: 6553.6). Total num frames: 1605632. Throughput: 0: 3169.4, 1: 3167.6. Samples: 1596444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:54,497][99566] Avg episode reward: [(0, '154239.879'), (1, '148233.580')]
++[2023-09-21 15:14:54,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001568_802816.pth...
++[2023-09-21 15:14:54,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001568_802816.pth...
++[2023-09-21 15:14:54,512][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001376_704512.pth
++[2023-09-21 15:14:54,514][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001376_704512.pth
++[2023-09-21 15:14:54,514][101034] Saving new best policy, reward=154239.879!
++[2023-09-21 15:14:59,496][99566] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6520.8). Total num frames: 1630208. Throughput: 0: 3099.2, 1: 3100.9. Samples: 1632322. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
++[2023-09-21 15:14:59,498][99566] Avg episode reward: [(0, '154239.879'), (1, '148584.617')]
++[2023-09-21 15:14:59,499][101035] Saving new best policy, reward=148584.617!
++[2023-09-21 15:14:59,981][101117] Updated weights for policy 1, policy_version 1600 (0.0013)
++[2023-09-21 15:14:59,981][101115] Updated weights for policy 0, policy_version 1600 (0.0013)
++[2023-09-21 15:15:04,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6521.5). Total num frames: 1662976. Throughput: 0: 3053.0, 1: 3054.0. Samples: 1649926. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:04,498][99566] Avg episode reward: [(0, '155604.981'), (1, '151719.185')]
++[2023-09-21 15:15:04,499][101034] Saving new best policy, reward=155604.981!
++[2023-09-21 15:15:04,499][101035] Saving new best policy, reward=151719.185!
++[2023-09-21 15:15:09,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6522.1). Total num frames: 1695744. Throughput: 0: 3104.8, 1: 3104.4. Samples: 1687760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:09,498][99566] Avg episode reward: [(0, '155604.981'), (1, '151719.185')]
++[2023-09-21 15:15:09,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001656_847872.pth...
++[2023-09-21 15:15:09,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001656_847872.pth...
++[2023-09-21 15:15:09,514][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001480_757760.pth
++[2023-09-21 15:15:09,517][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001480_757760.pth
++[2023-09-21 15:15:12,938][101115] Updated weights for policy 0, policy_version 1680 (0.0015)
++[2023-09-21 15:15:12,938][101117] Updated weights for policy 1, policy_version 1680 (0.0013)
++[2023-09-21 15:15:14,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6522.7). Total num frames: 1728512. Throughput: 0: 3141.0, 1: 3140.8. Samples: 1725508. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:15:14,497][99566] Avg episode reward: [(0, '155183.801'), (1, '155086.429')]
++[2023-09-21 15:15:14,498][101035] Saving new best policy, reward=155086.429!
++[2023-09-21 15:15:19,497][99566] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6492.9). Total num frames: 1753088. Throughput: 0: 3084.1, 1: 3084.4. Samples: 1742640. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:15:19,498][99566] Avg episode reward: [(0, '155183.801'), (1, '155086.429')]
++[2023-09-21 15:15:24,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6494.0). Total num frames: 1785856. Throughput: 0: 3047.1, 1: 3042.9. Samples: 1781016. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:15:24,497][99566] Avg episode reward: [(0, '156547.028'), (1, '156937.777')]
++[2023-09-21 15:15:24,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001744_892928.pth...
++[2023-09-21 15:15:24,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001744_892928.pth...
++[2023-09-21 15:15:24,514][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001568_802816.pth
++[2023-09-21 15:15:24,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001568_802816.pth
++[2023-09-21 15:15:24,515][101035] Saving new best policy, reward=156937.777!
++[2023-09-21 15:15:24,515][101034] Saving new best policy, reward=156547.028!
++[2023-09-21 15:15:25,925][101115] Updated weights for policy 0, policy_version 1760 (0.0016)
++[2023-09-21 15:15:25,926][101117] Updated weights for policy 1, policy_version 1760 (0.0016)
++[2023-09-21 15:15:29,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6280.6, 300 sec: 6495.1). Total num frames: 1818624. Throughput: 0: 3045.6, 1: 3055.0. Samples: 1818448. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:15:29,497][99566] Avg episode reward: [(0, '156547.028'), (1, '156937.777')]
++[2023-09-21 15:15:34,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6496.1). Total num frames: 1851392. Throughput: 0: 3056.4, 1: 3058.8. Samples: 1835316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:34,497][99566] Avg episode reward: [(0, '157397.752'), (1, '159312.801')]
++[2023-09-21 15:15:34,498][101034] Saving new best policy, reward=157397.752!
++[2023-09-21 15:15:34,498][101035] Saving new best policy, reward=159312.801!
++[2023-09-21 15:15:39,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6468.9). Total num frames: 1875968. Throughput: 0: 3089.1, 1: 3090.0. Samples: 1874502. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:15:39,497][99566] Avg episode reward: [(0, '156903.730'), (1, '159312.801')]
++[2023-09-21 15:15:39,554][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001840_942080.pth...
++[2023-09-21 15:15:39,555][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001840_942080.pth...
++[2023-09-21 15:15:39,558][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001656_847872.pth
++[2023-09-21 15:15:39,559][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001656_847872.pth
++[2023-09-21 15:15:39,559][101117] Updated weights for policy 1, policy_version 1840 (0.0011)
++[2023-09-21 15:15:39,560][101115] Updated weights for policy 0, policy_version 1840 (0.0013)
++[2023-09-21 15:15:44,496][99566] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6498.1). Total num frames: 1916928. Throughput: 0: 3111.8, 1: 3110.3. Samples: 1912318. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:44,498][99566] Avg episode reward: [(0, '157395.614'), (1, '159854.521')]
++[2023-09-21 15:15:44,499][101035] Saving new best policy, reward=159854.521!
++[2023-09-21 15:15:49,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6280.5, 300 sec: 6553.6). Total num frames: 1949696. Throughput: 0: 3142.5, 1: 3145.9. Samples: 1932904. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:15:49,497][99566] Avg episode reward: [(0, '157502.563'), (1, '159854.521')]
++[2023-09-21 15:15:49,498][101034] Saving new best policy, reward=157502.563!
++[2023-09-21 15:15:51,986][101115] Updated weights for policy 0, policy_version 1920 (0.0012)
++[2023-09-21 15:15:51,986][101117] Updated weights for policy 1, policy_version 1920 (0.0012)
++[2023-09-21 15:15:54,496][99566] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6498.1). Total num frames: 1974272. Throughput: 0: 3146.4, 1: 3140.3. Samples: 1970662. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:54,497][99566] Avg episode reward: [(0, '154117.366'), (1, '160110.948')]
++[2023-09-21 15:15:54,503][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001928_987136.pth...
++[2023-09-21 15:15:54,503][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001928_987136.pth...
++[2023-09-21 15:15:54,507][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001744_892928.pth
++[2023-09-21 15:15:54,507][101035] Saving new best policy, reward=160110.948!
++[2023-09-21 15:15:54,512][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001744_892928.pth
++[2023-09-21 15:15:59,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6553.6). Total num frames: 2015232. Throughput: 0: 3161.0, 1: 3160.7. Samples: 2009984. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:15:59,498][99566] Avg episode reward: [(0, '152354.094'), (1, '160110.948')]
++[2023-09-21 15:16:04,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6525.8). Total num frames: 2039808. Throughput: 0: 3201.8, 1: 3202.4. Samples: 2030826. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:16:04,497][99566] Avg episode reward: [(0, '145305.518'), (1, '161252.171')]
++[2023-09-21 15:16:04,498][101035] Saving new best policy, reward=161252.171!
++[2023-09-21 15:16:04,810][101117] Updated weights for policy 1, policy_version 2000 (0.0015)
++[2023-09-21 15:16:04,810][101115] Updated weights for policy 0, policy_version 2000 (0.0012)
++[2023-09-21 15:16:09,497][99566] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6498.1). Total num frames: 2072576. Throughput: 0: 3152.8, 1: 3155.5. Samples: 2064886. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:16:09,498][99566] Avg episode reward: [(0, '144668.785'), (1, '161252.171')]
++[2023-09-21 15:16:09,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002024_1036288.pth...
++[2023-09-21 15:16:09,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002024_1036288.pth...
++[2023-09-21 15:16:09,511][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001840_942080.pth
++[2023-09-21 15:16:09,513][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001840_942080.pth
++[2023-09-21 15:16:14,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6470.3). Total num frames: 2097152. Throughput: 0: 3118.9, 1: 3111.8. Samples: 2098830. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:16:14,498][99566] Avg episode reward: [(0, '143485.830'), (1, '162275.771')]
++[2023-09-21 15:16:14,500][101035] Saving new best policy, reward=162275.771!
++[2023-09-21 15:16:18,984][101115] Updated weights for policy 0, policy_version 2080 (0.0014)
++[2023-09-21 15:16:18,985][101117] Updated weights for policy 1, policy_version 2080 (0.0014)
++[2023-09-21 15:16:19,497][99566] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6442.5). Total num frames: 2129920. Throughput: 0: 3111.4, 1: 3107.0. Samples: 2115142. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:19,498][99566] Avg episode reward: [(0, '141474.267'), (1, '162345.285')]
++[2023-09-21 15:16:19,499][101035] Saving new best policy, reward=162345.285!
++[2023-09-21 15:16:24,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6442.5). Total num frames: 2162688. Throughput: 0: 3106.0, 1: 3115.1. Samples: 2154452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:24,498][99566] Avg episode reward: [(0, '140839.183'), (1, '163464.763')]
++[2023-09-21 15:16:24,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002112_1081344.pth...
++[2023-09-21 15:16:24,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002112_1081344.pth...
++[2023-09-21 15:16:24,516][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001928_987136.pth
++[2023-09-21 15:16:24,516][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001928_987136.pth
++[2023-09-21 15:16:24,517][101035] Saving new best policy, reward=163464.763!
++[2023-09-21 15:16:29,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6428.6). Total num frames: 2195456. Throughput: 0: 3110.6, 1: 3111.2. Samples: 2192296. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:16:29,497][99566] Avg episode reward: [(0, '141474.326'), (1, '163612.163')]
++[2023-09-21 15:16:29,498][101035] Saving new best policy, reward=163612.163!
++[2023-09-21 15:16:32,534][101115] Updated weights for policy 0, policy_version 2160 (0.0013)
++[2023-09-21 15:16:32,534][101117] Updated weights for policy 1, policy_version 2160 (0.0015)
++[2023-09-21 15:16:34,496][99566] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6387.0). Total num frames: 2220032. Throughput: 0: 3060.2, 1: 3058.9. Samples: 2208266. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:34,497][99566] Avg episode reward: [(0, '143510.663'), (1, '161964.692')]
++[2023-09-21 15:16:39,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6387.0). Total num frames: 2252800. Throughput: 0: 3029.4, 1: 3028.4. Samples: 2243264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:39,498][99566] Avg episode reward: [(0, '144449.158'), (1, '159709.222')]
++[2023-09-21 15:16:39,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002200_1126400.pth...
++[2023-09-21 15:16:39,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002200_1126400.pth...
++[2023-09-21 15:16:39,513][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002024_1036288.pth
++[2023-09-21 15:16:39,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002024_1036288.pth
++[2023-09-21 15:16:44,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6359.2). Total num frames: 2277376. Throughput: 0: 2993.8, 1: 2994.1. Samples: 2279440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:44,497][99566] Avg episode reward: [(0, '144500.336'), (1, '159960.034')]
++[2023-09-21 15:16:46,205][101117] Updated weights for policy 1, policy_version 2240 (0.0015)
++[2023-09-21 15:16:46,206][101115] Updated weights for policy 0, policy_version 2240 (0.0013)
++[2023-09-21 15:16:49,496][99566] Fps is (10 sec: 5734.5, 60 sec: 6007.5, 300 sec: 6331.4). Total num frames: 2310144. Throughput: 0: 2960.0, 1: 2959.9. Samples: 2297222. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:49,497][99566] Avg episode reward: [(0, '148419.870'), (1, '157559.143')]
++[2023-09-21 15:16:54,497][99566] Fps is (10 sec: 6553.4, 60 sec: 6144.0, 300 sec: 6359.2). Total num frames: 2342912. Throughput: 0: 2975.2, 1: 2973.6. Samples: 2332580. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:16:54,498][99566] Avg episode reward: [(0, '148104.147'), (1, '157533.887')]
++[2023-09-21 15:16:54,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002288_1171456.pth...
++[2023-09-21 15:16:54,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002288_1171456.pth...
++[2023-09-21 15:16:54,512][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002112_1081344.pth
++[2023-09-21 15:16:54,513][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002112_1081344.pth
++[2023-09-21 15:16:59,496][99566] Fps is (10 sec: 5734.5, 60 sec: 5871.0, 300 sec: 6331.4). Total num frames: 2367488. Throughput: 0: 3009.8, 1: 3008.9. Samples: 2369672. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
++[2023-09-21 15:16:59,497][99566] Avg episode reward: [(0, '149878.068'), (1, '156400.338')]
++[2023-09-21 15:16:59,928][101115] Updated weights for policy 0, policy_vers
\ No newline at end of file
diff --git a/replay.mp4 b/replay.mp4
new file mode 100644
index 0000000000000000000000000000000000000000..7c5446776bb51f0e8b597cd1e213dea7e7fcdf4e
--- /dev/null
+++ b/replay.mp4
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d722c5f81ebaca63a6b6c8541b26bcdae3516eabd83c19d6bfc6b777ea99526
+size 14904028
diff --git a/sf_log.txt b/sf_log.txt
new file mode 100644
index 0000000000000000000000000000000000000000..edf68ed6420a06ef0541c040ef7087829e699fa8
--- /dev/null
+++ b/sf_log.txt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a23c39bcdb8c0038faaa536b5f037063996b822dead11722b9f530e0fc3cf92
+size 49592736