diff --git a/ppo_v86/policy_update805.state.json b/ppo_v86/policy_update805.state.json deleted file mode 100644 index b1529f7f730011e38a1e7fe2ac5b369c62e2bc06..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update805.state.json +++ /dev/null @@ -1,102 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 806, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2322432, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update810.safetensors b/ppo_v86/policy_update810.safetensors deleted file mode 100644 index 403c56013caaaa2d6b9655725c626e31208bfb49..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update810.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8440a3eba61f6ca02667911cae92b684557362fb7da2512ea77beeac73ae0281 -size 48494336 diff --git a/ppo_v86/policy_update810.state.json b/ppo_v86/policy_update810.state.json deleted file mode 100644 index 671c99057d620ebec9ec4571da7d5eeb91b7684e..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update810.state.json +++ /dev/null @@ -1,102 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 811, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2348032, - "recent_wins": [ - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update815.safetensors b/ppo_v86/policy_update815.safetensors deleted file mode 100644 index a397afc69dae2e286d405492b47eba05577c016a..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update815.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:24de26a8b0bf47c6bf1b805c85f7c43d01d74576b9c5e75123f7b71cff58bdac -size 48494336 diff --git a/ppo_v86/policy_update815.state.json b/ppo_v86/policy_update815.state.json deleted file mode 100644 index 9ef193c0c2fd10b81596ceff4983a7809d92a048..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update815.state.json +++ /dev/null @@ -1,102 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 816, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2373632, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update820.safetensors b/ppo_v86/policy_update820.safetensors deleted file mode 100644 index 404a8c15c55196b38ec44a3cab74e2d168cf8dc0..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update820.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9f331822a42b235f15bda03f3ca2449bb3235a2e8bc737037e80ef09f85f2dec -size 48494336 diff --git a/ppo_v86/policy_update820.state.json b/ppo_v86/policy_update820.state.json deleted file mode 100644 index 56c01ef1982274a80b74794e3ba1a462207c47ea..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update820.state.json +++ /dev/null @@ -1,102 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 821, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2388992, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update825.safetensors b/ppo_v86/policy_update825.safetensors deleted file mode 100644 index 69ecffdaaa988244c7e0f17e947a7074caf7fa57..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update825.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5378cc091206a61ae6830695931443946bcbd94af348920799f1122a159cbf20 -size 48494336 diff --git a/ppo_v86/policy_update825.state.json b/ppo_v86/policy_update825.state.json deleted file mode 100644 index 52e37213c554dc6fc3ca71c855bdec0762971c4b..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update825.state.json +++ /dev/null @@ -1,102 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 826, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2404352, - "recent_wins": [ - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update830.safetensors b/ppo_v86/policy_update830.safetensors deleted file mode 100644 index 3394ef0f0ddf1b67bf6e4f9d79c2b3ed75257c9f..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update830.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a48719125379289d72192e0ed923ade0224a29e9faedc4c21cf8bf581b75376 -size 48494336 diff --git a/ppo_v86/policy_update830.state.json b/ppo_v86/policy_update830.state.json deleted file mode 100644 index 172ecb6b30c44f277bd2b4a72ab6b22feb60c73e..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update830.state.json +++ /dev/null @@ -1,103 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 831, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2419712, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update835.safetensors b/ppo_v86/policy_update835.safetensors deleted file mode 100644 index 99e9236665552a3d901b01b28fdda4a5cf31e75a..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update835.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1953e615badb2fbd26abf8ffdc39993fb9b975231fe99ba367108311f26db3cf -size 48494336 diff --git a/ppo_v86/policy_update835.state.json b/ppo_v86/policy_update835.state.json deleted file mode 100644 index e98fc53fa88c75ca830a9e4fb2bd3dc53a942fac..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update835.state.json +++ /dev/null @@ -1,106 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 836, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2435072, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update840.safetensors b/ppo_v86/policy_update840.safetensors deleted file mode 100644 index 47291caefde269edef4604fbd1535bb9bfff10b9..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update840.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9a0f90e55a1d1ed551825b77841ecc62f498327bcb99a6bb7f55abd246b1904a -size 48494336 diff --git a/ppo_v86/policy_update840.state.json b/ppo_v86/policy_update840.state.json deleted file mode 100644 index ef656a3e4ef3e9900b2b7d08d6827c4ed5e5b318..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update840.state.json +++ /dev/null @@ -1,114 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 841, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2450432, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update845.safetensors b/ppo_v86/policy_update845.safetensors deleted file mode 100644 index da10b8c06ba942e2fecdac1fd439c280059156f8..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update845.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a21bf06b16855c56839274feb8e21e1e9df780c59aba8e7efa9d2850794cc33a -size 48494336 diff --git a/ppo_v86/policy_update845.state.json b/ppo_v86/policy_update845.state.json deleted file mode 100644 index 83576328b692eab1529143eaa4edbe8b18d21d93..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update845.state.json +++ /dev/null @@ -1,116 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 846, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2465792, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update850.safetensors b/ppo_v86/policy_update850.safetensors deleted file mode 100644 index a31a1d80559949b01064cde62b97754a95a906af..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update850.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1ec701dd74e74f11d591dd125e2afae819242aab0ac20df35f4466a505f49767 -size 48494336 diff --git a/ppo_v86/policy_update850.state.json b/ppo_v86/policy_update850.state.json deleted file mode 100644 index bc738b3800a1e2502b3db6967d0186be2f93bd84..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update850.state.json +++ /dev/null @@ -1,118 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 851, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2481152, - "recent_wins": [ - 0.0, - 1.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 1.0, - 0.0, - 0.0, - 1.0, - 1.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update855.safetensors b/ppo_v86/policy_update855.safetensors deleted file mode 100644 index 1032e7bf66bb39626e83b289547a4c599d327d47..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update855.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:61a559fe71a26e10389cb86b26ae11fa4a1af0797bb5b0b4a25b7c2ae3d16299 -size 48494336 diff --git a/ppo_v86/policy_update855.state.json b/ppo_v86/policy_update855.state.json deleted file mode 100644 index f5269612b7ee1ba491e75b8c79021b5ef73daa57..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update855.state.json +++ /dev/null @@ -1,118 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 856, - "stage": 6, - "ent_scale": 1.0, - "lr_now": 0.00009428737890624998, - "total_env_steps": 2496512, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 1.0, - 0.0, - 0.0, - 1.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 1.0, - 0.0, - 1.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update860.safetensors b/ppo_v86/policy_update860.safetensors deleted file mode 100644 index a9947e3451888a3e732f469d306bdc07e315704b..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update860.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ca94144d2e20a0f2d21c3ee21bc4a28e854c9e0b12b4f896029cb1c57f84cd43 -size 48494336 diff --git a/ppo_v86/policy_update860.state.json b/ppo_v86/policy_update860.state.json deleted file mode 100644 index 5adeb9075cf00164544b1be931f5cc30a86404f2..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update860.state.json +++ /dev/null @@ -1,45 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 861, - "stage": 7, - "ent_scale": 1.0, - "lr_now": 0.00008014427207031247, - "total_env_steps": 2511872, - "recent_wins": [ - 0.0, - 1.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update865.safetensors b/ppo_v86/policy_update865.safetensors deleted file mode 100644 index eaeee544138204c4dea8c75e299485aaf6c1e9e1..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update865.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5ac9551e4c2baa3e6a5eb675952ad6163773327b44c23fbc300d0bc34e5a9ee1 -size 48494336 diff --git a/ppo_v86/policy_update865.state.json b/ppo_v86/policy_update865.state.json deleted file mode 100644 index ee0f21562c231d181ae965365f710b834cf03460..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update865.state.json +++ /dev/null @@ -1,64 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 866, - "stage": 7, - "ent_scale": 1.0, - "lr_now": 0.00008014427207031247, - "total_env_steps": 2527232, - "recent_wins": [ - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update870.safetensors b/ppo_v86/policy_update870.safetensors deleted file mode 100644 index 951bd1dd32ea60c729068fd8dbe3faf28c24f81c..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update870.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c28743279ee2ee02b76ab91ae191713916ece8b12d32ec0d022d3774b1f56a38 -size 48494336 diff --git a/ppo_v86/policy_update870.state.json b/ppo_v86/policy_update870.state.json deleted file mode 100644 index 41284e297d4841ef0cdf6a85b33c962abb02d2be..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update870.state.json +++ /dev/null @@ -1,78 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 871, - "stage": 7, - "ent_scale": 1.0, - "lr_now": 0.00008014427207031247, - "total_env_steps": 2542592, - "recent_wins": [ - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0 - ], - "recent_conversions": [ - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update875.safetensors b/ppo_v86/policy_update875.safetensors deleted file mode 100644 index 1c0cb34e289f03577fde3a73e527a1401e03d9af..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update875.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:093850df25e653e25b8dd0dce504b2a9f8495be837753c417fef9f56ff12ff58 -size 48494336 diff --git a/ppo_v86/policy_update875.state.json b/ppo_v86/policy_update875.state.json deleted file mode 100644 index e9dab0d6d8466a63d8bc0d9b67150e1194609a18..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update875.state.json +++ /dev/null @@ -1,92 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 876, - "stage": 7, - "ent_scale": 1.0, - "lr_now": 0.00008014427207031247, - "total_env_steps": 2557952, - "recent_wins": [ - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 1.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 1.0, - 1.0, - 0.0, - 1.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update880.safetensors b/ppo_v86/policy_update880.safetensors deleted file mode 100644 index 8ff71e725ccd652c89d004ed74de90ba8429a39c..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update880.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:48931a3d21c1b0eb282f16ea78b2292d5675b4009b64d5de3eb477689b861c84 -size 48494336 diff --git a/ppo_v86/policy_update880.state.json b/ppo_v86/policy_update880.state.json deleted file mode 100644 index 2a64765101e8e39ce69833b5de7e8cdd4ce5294a..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update880.state.json +++ /dev/null @@ -1,96 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 881, - "stage": 7, - "ent_scale": 1.0, - "lr_now": 0.00008014427207031247, - "total_env_steps": 2573312, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 1.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0 - ], - "recent_conversions": [ - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 1.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update890.safetensors b/ppo_v86/policy_update890.safetensors deleted file mode 100644 index dc25585602427d12bd111a4ae1deb6108b4305fd..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update890.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8e09560c3990638078ef17d4c9b8b652ea33e74077d7f050f17bc6d3f9bdfa88 -size 48494336 diff --git a/ppo_v86/policy_update890.state.json b/ppo_v86/policy_update890.state.json deleted file mode 100644 index 61a3cbb1237424543e7005e326467f8e802f1c26..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update890.state.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 891, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2603008, - "recent_wins": [ - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update895.safetensors b/ppo_v86/policy_update895.safetensors deleted file mode 100644 index 5cf3b671afa17bef144e0e525d76bdafc017e31f..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update895.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5d4b0d0f4493ef22ad5bf8d520e0bcc94cb365344257709dde46d72a97a50d4c -size 48494336 diff --git a/ppo_v86/policy_update895.state.json b/ppo_v86/policy_update895.state.json deleted file mode 100644 index bd19857a4baac5a72f2bc1c6a27b7bf829cdfe47..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update895.state.json +++ /dev/null @@ -1,43 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 896, - "stage": 8, - "ent_scale": 3.7129300000000014, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2618368, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update900.safetensors b/ppo_v86/policy_update900.safetensors deleted file mode 100644 index d8b615a39e3eec0a3905585f0f8f98b0dfc7b5a3..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update900.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b0b6ca2a3641684eb721313bff620374896290a5f96d01801bd9c4cabebcd4e2 -size 48494336 diff --git a/ppo_v86/policy_update900.state.json b/ppo_v86/policy_update900.state.json deleted file mode 100644 index 8f3185c2044d6d63074a66a346c3e677556d0ff3..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update900.state.json +++ /dev/null @@ -1,48 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 901, - "stage": 8, - "ent_scale": 3.9710277096477293, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2633728, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update905.safetensors b/ppo_v86/policy_update905.safetensors deleted file mode 100644 index 6ac3e3bb3725ecd2a2c1e28bf73513d1661fc86e..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update905.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0e99354d41878fe4d397eb15a7f3014a8483ab26fea6ea429f2dc93b240e4ca0 -size 48494336 diff --git a/ppo_v86/policy_update905.state.json b/ppo_v86/policy_update905.state.json deleted file mode 100644 index 31e4a3003739f0c529b893c0cc065b45bc464798..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update905.state.json +++ /dev/null @@ -1,59 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 906, - "stage": 8, - "ent_scale": 3.11140411828031, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2649088, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update910.safetensors b/ppo_v86/policy_update910.safetensors deleted file mode 100644 index 483ce64fc0fc20d67bc735ef3ebf333c9cceddcd..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update910.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dee5bfce4b1693d120a24b69e0f18516c8f15afc0e1fb2df85817f57637fda29 -size 48494336 diff --git a/ppo_v86/policy_update910.state.json b/ppo_v86/policy_update910.state.json deleted file mode 100644 index ec7aa7fa6f53fa68591f80048b409f7dd5ff1ef8..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update910.state.json +++ /dev/null @@ -1,83 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 911, - "stage": 8, - "ent_scale": 2.4378665411303464, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2664448, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update915.safetensors b/ppo_v86/policy_update915.safetensors deleted file mode 100644 index dd46b459e3ace4010553efe5c9078f320f7f0880..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update915.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c9bb299c27838cbf7a324a3594c3bf2778cef0a61e48a128694305d2b1ef9955 -size 48494336 diff --git a/ppo_v86/policy_update915.state.json b/ppo_v86/policy_update915.state.json deleted file mode 100644 index df3afc8a3542ea9a1e5a8b106a2cae404f913f52..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update915.state.json +++ /dev/null @@ -1,84 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 916, - "stage": 8, - "ent_scale": 1.9101322253335822, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2679808, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update920.safetensors b/ppo_v86/policy_update920.safetensors deleted file mode 100644 index 2cbb5f1af178a9c98643875c58194e8e9181c447..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update920.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fdf3eaf70b1ea8190bb30527152f9e58aa90ab0e10cc8394a10c0732f7186e1f -size 48494336 diff --git a/ppo_v86/policy_update920.state.json b/ppo_v86/policy_update920.state.json deleted file mode 100644 index 22f1bad66745e8d3f457e506c68300968f74eeaf..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update920.state.json +++ /dev/null @@ -1,86 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 921, - "stage": 8, - "ent_scale": 1.496638579963488, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2695168, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update925.safetensors b/ppo_v86/policy_update925.safetensors deleted file mode 100644 index df53d4e2fda80d52b1b54babe7bf799cf0149cf3..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update925.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b6ef76aee70d6e0125c872de33ecc55989bccb1ff547531465efb9e027bd8dbb -size 48494336 diff --git a/ppo_v86/policy_update925.state.json b/ppo_v86/policy_update925.state.json deleted file mode 100644 index cdd79079cd4f671b2b74f099649a07e2ffe754a6..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update925.state.json +++ /dev/null @@ -1,88 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 926, - "stage": 8, - "ent_scale": 1.1726554891475898, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2710528, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update930.safetensors b/ppo_v86/policy_update930.safetensors deleted file mode 100644 index cb071c699c6c6005083e05bad7e265080f505feb..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update930.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:baaa753bd3ee959f5f4b554b05b27b4c5751fb500a8690ab2d173255f500f17a -size 48494336 diff --git a/ppo_v86/policy_update930.state.json b/ppo_v86/policy_update930.state.json deleted file mode 100644 index abbd5603afd13195101308c3e2195b22e530caf9..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update930.state.json +++ /dev/null @@ -1,88 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 931, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2725888, - "recent_wins": [ - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update935.safetensors b/ppo_v86/policy_update935.safetensors deleted file mode 100644 index 8cfedb19cee5b8ab82b272d15683eaa4b12d52f1..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update935.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a62ec8909f0ac8cadfbe66a501b1240e9d04c71016ec2ff2a266024befc137d -size 48494336 diff --git a/ppo_v86/policy_update935.state.json b/ppo_v86/policy_update935.state.json deleted file mode 100644 index 026040f5e217796df06867ddd2a4caf22dbdea81..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update935.state.json +++ /dev/null @@ -1,89 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 936, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2741248, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update940.safetensors b/ppo_v86/policy_update940.safetensors deleted file mode 100644 index 2441e8bd81cfc44b9938280f61c09cb49fdd4eaf..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update940.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2be5a62bf1593b3da37d9377de9d595f98fe1ecd44a3a6469123e7b0311922cf -size 48494336 diff --git a/ppo_v86/policy_update940.state.json b/ppo_v86/policy_update940.state.json deleted file mode 100644 index 0418545bfaefcd27458e62b350268c60cc7c1312..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update940.state.json +++ /dev/null @@ -1,92 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 941, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2756608, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update945.safetensors b/ppo_v86/policy_update945.safetensors deleted file mode 100644 index d1f3aee37d3f0c03994386e3382b2f01ee66874c..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update945.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:58484e0aed8ac89b101dd374698bfb76025fc7cb984304c0f7ca5a7c01ac43fc -size 48494336 diff --git a/ppo_v86/policy_update945.state.json b/ppo_v86/policy_update945.state.json deleted file mode 100644 index c98613b6b51ea6ba444f683a492df4666e4c116d..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update945.state.json +++ /dev/null @@ -1,96 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 946, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2771968, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update950.safetensors b/ppo_v86/policy_update950.safetensors deleted file mode 100644 index 07146425ed53e41425a7b3e4689d516383566e65..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update950.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3503746184006165edb5261fefaf8cb347764ff2aa82b2e07c92d8463d81941d -size 48494336 diff --git a/ppo_v86/policy_update950.state.json b/ppo_v86/policy_update950.state.json deleted file mode 100644 index 6807212cd0ff05e4f8837945a599699579dcd0fa..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update950.state.json +++ /dev/null @@ -1,99 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 951, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2787328, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update955.safetensors b/ppo_v86/policy_update955.safetensors deleted file mode 100644 index f4cfa445c5bf5ac1c48e7f74b77c27c829b21d34..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update955.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8da0e23138c9f7ec6246b555281b58b89a26a183efbe90dc09d7f6839d3f929b -size 48494336 diff --git a/ppo_v86/policy_update955.state.json b/ppo_v86/policy_update955.state.json deleted file mode 100644 index 17b15a20f36e149aff837d3575e07fb7f18e3470..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update955.state.json +++ /dev/null @@ -1,99 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 956, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2802688, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update960.safetensors b/ppo_v86/policy_update960.safetensors deleted file mode 100644 index 2dafcf2d011eb34c1a9028d0c29217f346053ecc..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update960.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:82f02d59d0133ef4644267fe730523583a706463f426bb44cd481c7e4955643a -size 48494336 diff --git a/ppo_v86/policy_update960.state.json b/ppo_v86/policy_update960.state.json deleted file mode 100644 index 434d4a7f1e74bff98958b2a2cf2e98788cfb3111..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update960.state.json +++ /dev/null @@ -1,99 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 961, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2818048, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update965.safetensors b/ppo_v86/policy_update965.safetensors deleted file mode 100644 index 9f0ddd7b4c2fad697a2cda3b91020d5fe6994a0c..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update965.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:505da07f7f0e92e00c72729b92e121a8957a43c4a65670e0170ac99e0f79fee6 -size 48494336 diff --git a/ppo_v86/policy_update965.state.json b/ppo_v86/policy_update965.state.json deleted file mode 100644 index c08b106e4fb4f7127c6170ac28dccf67b2212f23..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update965.state.json +++ /dev/null @@ -1,99 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 966, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2833408, - "recent_wins": [ - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update970.safetensors b/ppo_v86/policy_update970.safetensors deleted file mode 100644 index f78198d41fd1c5f897631820e159136b4608b44d..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update970.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:eac56b3543fc729128f08ab9cb69e36a0f8c77bf6ed40fc23541b4beb5fa86a3 -size 48494336 diff --git a/ppo_v86/policy_update970.state.json b/ppo_v86/policy_update970.state.json deleted file mode 100644 index be1347e23d3cc866f2a5499c91ab06ae0f8bb3e1..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update970.state.json +++ /dev/null @@ -1,99 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 971, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2848768, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update975.safetensors b/ppo_v86/policy_update975.safetensors deleted file mode 100644 index 93ddacffbb32a7e7a1d476fe6fdb707649075e65..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update975.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4536f81be205f2de57d7f61966dbf283a05af69ec6fc551c13149bed1e868315 -size 48494336 diff --git a/ppo_v86/policy_update975.state.json b/ppo_v86/policy_update975.state.json deleted file mode 100644 index 33fdafd3a80d31e8538c4bffb51b1fb630d6e926..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update975.state.json +++ /dev/null @@ -1,110 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 976, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2864128, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update980.safetensors b/ppo_v86/policy_update980.safetensors deleted file mode 100644 index e76d0fe980183e5f1865b7d50978ed0c73e0acc0..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update980.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:834a84028e37892e7cf21b78966f214e34fad2f6b1055549df4c77cb252d83fd -size 48494336 diff --git a/ppo_v86/policy_update980.state.json b/ppo_v86/policy_update980.state.json deleted file mode 100644 index e351f80b313a78b99c754afc0cf440af824c8134..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update980.state.json +++ /dev/null @@ -1,110 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 981, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2879488, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update985.safetensors b/ppo_v86/policy_update985.safetensors deleted file mode 100644 index 2015da3bedfef1b699a13ff5cfd66c49aceda9c2..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update985.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:87f9cbea884a3995b3b62a2945e040f4b4243a4b85f14e1efc6147d520473bb6 -size 48494336 diff --git a/ppo_v86/policy_update985.state.json b/ppo_v86/policy_update985.state.json deleted file mode 100644 index 415722bdfd5ef6f9d2fa1a2288d17fdb4be1cafd..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update985.state.json +++ /dev/null @@ -1,111 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 986, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2894848, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update990.safetensors b/ppo_v86/policy_update990.safetensors deleted file mode 100644 index f7727a27fd299a9304c8d58a6d9c9d82d5149dda..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update990.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b6f2d64836de567d182c7d5eef4d36af05031e6dad1aea35978f0f5ecc6f861e -size 48494336 diff --git a/ppo_v86/policy_update990.state.json b/ppo_v86/policy_update990.state.json deleted file mode 100644 index 2a9dd923910cb68a7b74fd707331dafc8eedb0bc..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update990.state.json +++ /dev/null @@ -1,112 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 991, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2910208, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v86/policy_update995.safetensors b/ppo_v86/policy_update995.safetensors deleted file mode 100644 index 88ab2acce664160a9dad8a2b99abb4c8fb6e8128..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update995.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:38e46f38bf315c22b0a26b56dcec25824f83b7c0bea4dc6ab20918cd292019cf -size 48494336 diff --git a/ppo_v86/policy_update995.state.json b/ppo_v86/policy_update995.state.json deleted file mode 100644 index a95224aed51d3e37c4ac5e381f4596bff1dca5ca..0000000000000000000000000000000000000000 --- a/ppo_v86/policy_update995.state.json +++ /dev/null @@ -1,115 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 996, - "stage": 8, - "ent_scale": 1.0, - "lr_now": 0.0000681226312597656, - "total_env_steps": 2925568, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0 - ], - "recent_conversions": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0 - ], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v8.3", - "reward_profile": "v8.6-attack-fair-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 16, - 12, - 10, - 12, - 10, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 12, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v8_rust_8gpu/metadata.json b/ppo_v8_rust_8gpu/metadata.json deleted file mode 100644 index 394c673ed302db5566c43409e1daca0a12a56b9f..0000000000000000000000000000000000000000 --- a/ppo_v8_rust_8gpu/metadata.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "run_name": "ppo_v8_rust_8gpu", - "artifact": "policy_update200.ot", - "latest_alias": "policy_latest.ot", - "repo": "djmango/openfront-rl", - "source_pod": "openfront-v8-8gpu-final", - "source_path": "/root/openfront-ai-v8/rust/checkpoints/policy_update200.ot", - "uploaded_utc": "2026-07-09T16:27:53Z", - "git_sha": "d9bdb70ac4e403523aefb00afe7dcce6459689b7", - "sha256": "37259e1f60b9c8437624108ab6e1269503c13bca1e044bbae8bda9c08b25acb1", - "size_bytes": 44697096, - "command": "./target/release/oftrain --num-envs 32 --num-gpus 8 --rollout-len 64 --updates 100000 --epochs 2 --minibatches 4 --device cuda --log-every 1 --ckpt-every 25 --ckpt-dir checkpoints", - "checkpoint_update": 200, - "checkpoint_log_line": "[update 200] steps/s= 905.3 decisions_total= 3293184 eps_done=16469 recent_reward= 12.163 pg=-0.0018 v=0.8120 ent=0.204 entq=-0.484 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3728s update_s=18.1 collect_s=18.1 train_s=15.5 gpu_mem%=92 min_mean_util%=57 [gpu0=36% gpu1=0% gpu2=32% gpu3=29% gpu4=31% gpu5=14% gpu6=12% gpu7=28%]", - "last_log_line_at_copy": "[update 211] steps/s= 906.8 decisions_total= 3473408 eps_done=17425 recent_reward= 12.726 pg=-0.0038 v=0.5749 ent=0.231 entq=-0.512 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3928s update_s=18.1 collect_s=18.0 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=28% gpu1=12% gpu2=33% gpu3=26% gpu4=30% gpu5=0% gpu6=0% gpu7=28%]", - "format_note": "Rust tch VarStore .ot checkpoint; not a Python torch.save policy.pt. Load with rust/oftrain policy architecture." -} diff --git a/ppo_v8_rust_8gpu/policy_latest.ot b/ppo_v8_rust_8gpu/policy_latest.ot deleted file mode 100644 index 959d1c45fe9ac122508d341b4fbe2c69abc04994..0000000000000000000000000000000000000000 --- a/ppo_v8_rust_8gpu/policy_latest.ot +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:37259e1f60b9c8437624108ab6e1269503c13bca1e044bbae8bda9c08b25acb1 -size 44697096 diff --git a/ppo_v8_rust_8gpu/policy_update200.ot b/ppo_v8_rust_8gpu/policy_update200.ot deleted file mode 100644 index 959d1c45fe9ac122508d341b4fbe2c69abc04994..0000000000000000000000000000000000000000 --- a/ppo_v8_rust_8gpu/policy_update200.ot +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:37259e1f60b9c8437624108ab6e1269503c13bca1e044bbae8bda9c08b25acb1 -size 44697096 diff --git a/ppo_v8_rust_8gpu/train_final.log b/ppo_v8_rust_8gpu/train_final.log deleted file mode 100644 index d09a5d8f83761338507edb5ee48c99d1867ca787..0000000000000000000000000000000000000000 --- a/ppo_v8_rust_8gpu/train_final.log +++ /dev/null @@ -1,224 +0,0 @@ -[oftrain] device=Cuda(0) -[train] spawning 256 env workers across 8 shard(s) [Cuda(0), Cuda(1), Cuda(2), Cuda(3), Cuda(4), Cuda(5), Cuda(6), Cuda(7)] (stage=0, max_ticks=3000)... -[train] all 256 envs ready -[train] policy params: 11166694 per shard x 8 shard(s) on [Cuda(0), Cuda(1), Cuda(2), Cuda(3), Cuda(4), Cuda(5), Cuda(6), Cuda(7)] -[update 0] steps/s= 838.9 decisions_total= 16384 eps_done= 1 recent_reward= 3.496 pg=-0.0136 v=0.2101 ent=2.889 entq=-0.103 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=29s update_s=19.5 collect_s=19.5 train_s=19.0 gpu_mem%=87 min_mean_util%=37 [gpu0=25% gpu1=2% gpu2=0% gpu3=0% gpu4=0% gpu5=0% gpu6=0% gpu7=0%] -[update 1] steps/s= 905.5 decisions_total= 32768 eps_done= 6 recent_reward= 3.341 pg=+0.0160 v=0.0870 ent=3.649 entq=-0.079 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=48s update_s=18.1 collect_s=18.1 train_s=16.5 gpu_mem%=88 min_mean_util%=44 [gpu0=0% gpu1=15% gpu2=0% gpu3=2% gpu4=0% gpu5=30% gpu6=0% gpu7=25%] -[update 2] steps/s= 945.1 decisions_total= 49152 eps_done= 256 recent_reward= 6.405 pg=-0.1168 v=0.1797 ent=4.284 entq=-0.103 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=65s update_s=17.3 collect_s=17.3 train_s=15.3 gpu_mem%=88 min_mean_util%=47 [gpu0=25% gpu1=29% gpu2=9% gpu3=11% gpu4=0% gpu5=0% gpu6=13% gpu7=25%] -[update 3] steps/s= 902.6 decisions_total= 65536 eps_done= 256 recent_reward= 6.405 pg=+0.3740 v=2.3871 ent=3.344 entq=-0.096 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=83s update_s=18.2 collect_s=18.0 train_s=16.4 gpu_mem%=88 min_mean_util%=49 [gpu0=0% gpu1=0% gpu2=25% gpu3=25% gpu4=0% gpu5=0% gpu6=0% gpu7=14%] -[update 4] steps/s= 885.7 decisions_total= 81920 eps_done= 262 recent_reward= 6.438 pg=+0.0549 v=0.4944 ent=4.224 entq=-0.091 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=102s update_s=18.5 collect_s=18.3 train_s=17.2 gpu_mem%=88 min_mean_util%=51 [gpu0=0% gpu1=24% gpu2=29% gpu3=25% gpu4=0% gpu5=0% gpu6=25% gpu7=26%] -[update 5] steps/s= 856.4 decisions_total= 98304 eps_done= 512 recent_reward= 7.386 pg=+0.3175 v=731.0077 ent=1.778 entq=-1.392 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=121s update_s=19.1 collect_s=19.0 train_s=18.8 gpu_mem%=88 min_mean_util%=53 [gpu0=45% gpu1=99% gpu2=77% gpu3=53% gpu4=77% gpu5=93% gpu6=100% gpu7=100%] -[update 6] steps/s= 837.8 decisions_total= 114688 eps_done= 512 recent_reward= 7.386 pg=+0.4172 v=7.6023 ent=2.310 entq=-0.084 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=140s update_s=19.6 collect_s=19.5 train_s=18.4 gpu_mem%=88 min_mean_util%=53 [gpu0=25% gpu1=0% gpu2=0% gpu3=0% gpu4=11% gpu5=0% gpu6=26% gpu7=24%] -[update 7] steps/s= 864.6 decisions_total= 131072 eps_done= 518 recent_reward= 7.404 pg=+0.0582 v=42.4978 ent=0.410 entq=-0.483 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=159s update_s=19.0 collect_s=18.9 train_s=16.9 gpu_mem%=88 min_mean_util%=54 [gpu0=24% gpu1=28% gpu2=0% gpu3=10% gpu4=25% gpu5=27% gpu6=23% gpu7=26%] -[update 8] steps/s= 866.0 decisions_total= 147456 eps_done= 768 recent_reward= 6.769 pg=+0.0968 v=5.4085 ent=0.961 entq=-0.443 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=178s update_s=18.9 collect_s=18.9 train_s=18.1 gpu_mem%=88 min_mean_util%=54 [gpu0=28% gpu1=21% gpu2=28% gpu3=0% gpu4=23% gpu5=25% gpu6=27% gpu7=2%] -[update 9] steps/s= 896.1 decisions_total= 163840 eps_done= 769 recent_reward= 6.695 pg=+0.3513 v=66.1757 ent=0.514 entq=-0.132 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=196s update_s=18.3 collect_s=18.2 train_s=15.8 gpu_mem%=88 min_mean_util%=54 [gpu0=23% gpu1=26% gpu2=0% gpu3=28% gpu4=28% gpu5=0% gpu6=0% gpu7=31%] -[update 10] steps/s= 843.6 decisions_total= 180224 eps_done= 776 recent_reward= 6.518 pg=+0.5868 v=15.0915 ent=1.409 entq=-0.915 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=216s update_s=19.4 collect_s=19.4 train_s=16.4 gpu_mem%=88 min_mean_util%=54 [gpu0=28% gpu1=13% gpu2=0% gpu3=0% gpu4=0% gpu5=26% gpu6=0% gpu7=21%] -[update 11] steps/s= 851.6 decisions_total= 196608 eps_done= 1024 recent_reward= 8.055 pg=+0.1619 v=42.1973 ent=0.331 entq=-1.118 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=235s update_s=19.2 collect_s=19.2 train_s=16.9 gpu_mem%=88 min_mean_util%=54 [gpu0=26% gpu1=28% gpu2=0% gpu3=0% gpu4=0% gpu5=28% gpu6=0% gpu7=0%] -[update 12] steps/s= 844.3 decisions_total= 212992 eps_done= 1025 recent_reward= 8.028 pg=+0.3512 v=14.0555 ent=1.862 entq=-0.203 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=254s update_s=19.4 collect_s=19.4 train_s=17.3 gpu_mem%=88 min_mean_util%=53 [gpu0=28% gpu1=0% gpu2=26% gpu3=30% gpu4=22% gpu5=0% gpu6=28% gpu7=0%] -[update 13] steps/s= 867.8 decisions_total= 229376 eps_done= 1032 recent_reward= 7.631 pg=+0.5421 v=15.2264 ent=2.821 entq=-0.607 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=273s update_s=18.9 collect_s=18.8 train_s=17.0 gpu_mem%=89 min_mean_util%=54 [gpu0=26% gpu1=28% gpu2=16% gpu3=25% gpu4=26% gpu5=24% gpu6=28% gpu7=11%] -[update 14] steps/s= 892.2 decisions_total= 245760 eps_done= 1280 recent_reward= 5.488 pg=+0.2646 v=212.4965 ent=2.227 entq=-0.573 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=292s update_s=18.4 collect_s=18.3 train_s=16.1 gpu_mem%=89 min_mean_util%=54 [gpu0=33% gpu1=27% gpu2=26% gpu3=20% gpu4=29% gpu5=25% gpu6=30% gpu7=25%] -[update 15] steps/s= 904.8 decisions_total= 262144 eps_done= 1282 recent_reward= 5.430 pg=+0.7461 v=151.3084 ent=1.762 entq=-0.990 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=310s update_s=18.1 collect_s=18.1 train_s=17.2 gpu_mem%=91 min_mean_util%=54 [gpu0=15% gpu1=25% gpu2=28% gpu3=29% gpu4=30% gpu5=31% gpu6=28% gpu7=15%] -[update 16] steps/s= 861.5 decisions_total= 278528 eps_done= 1297 recent_reward= 5.244 pg=+0.5019 v=3.2465 ent=2.868 entq=-0.177 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=329s update_s=19.0 collect_s=19.0 train_s=16.7 gpu_mem%=91 min_mean_util%=54 [gpu0=28% gpu1=0% gpu2=0% gpu3=36% gpu4=7% gpu5=12% gpu6=12% gpu7=28%] -[update 17] steps/s= 903.9 decisions_total= 294912 eps_done= 1536 recent_reward= 5.785 pg=+0.1446 v=51.4666 ent=3.921 entq=-0.336 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=347s update_s=18.1 collect_s=18.1 train_s=17.0 gpu_mem%=91 min_mean_util%=54 [gpu0=12% gpu1=26% gpu2=25% gpu3=19% gpu4=21% gpu5=14% gpu6=25% gpu7=15%] -[update 18] steps/s= 870.3 decisions_total= 311296 eps_done= 1537 recent_reward= 5.784 pg=+0.4625 v=1393.3689 ent=2.558 entq=-0.199 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=366s update_s=18.8 collect_s=18.8 train_s=18.4 gpu_mem%=91 min_mean_util%=54 [gpu0=0% gpu1=33% gpu2=24% gpu3=2% gpu4=2% gpu5=11% gpu6=2% gpu7=17%] -[update 19] steps/s= 888.9 decisions_total= 327680 eps_done= 1562 recent_reward= 5.583 pg=+0.1290 v=86.0014 ent=1.946 entq=-0.973 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=384s update_s=18.4 collect_s=18.4 train_s=17.4 gpu_mem%=91 min_mean_util%=54 [gpu0=11% gpu1=0% gpu2=12% gpu3=0% gpu4=11% gpu5=0% gpu6=0% gpu7=30%] -[update 20] steps/s= 892.7 decisions_total= 344064 eps_done= 1792 recent_reward= 6.057 pg=+0.2472 v=77.0128 ent=5.619 entq=-0.059 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=403s update_s=18.4 collect_s=18.3 train_s=18.0 gpu_mem%=91 min_mean_util%=54 [gpu0=25% gpu1=0% gpu2=2% gpu3=27% gpu4=28% gpu5=2% gpu6=25% gpu7=14%] -[update 21] steps/s= 916.9 decisions_total= 360448 eps_done= 1795 recent_reward= 5.944 pg=+0.2665 v=1298.1292 ent=3.764 entq=-1.944 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=420s update_s=17.9 collect_s=17.8 train_s=16.4 gpu_mem%=91 min_mean_util%=54 [gpu0=37% gpu1=23% gpu2=30% gpu3=26% gpu4=0% gpu5=0% gpu6=32% gpu7=0%] -[update 22] steps/s= 895.8 decisions_total= 376832 eps_done= 1817 recent_reward= 5.620 pg=+0.6737 v=22.0915 ent=4.608 entq=-0.089 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=439s update_s=18.3 collect_s=18.2 train_s=16.4 gpu_mem%=91 min_mean_util%=54 [gpu0=0% gpu1=4% gpu2=0% gpu3=5% gpu4=23% gpu5=30% gpu6=0% gpu7=0%] -[update 23] steps/s= 914.0 decisions_total= 393216 eps_done= 2048 recent_reward= 5.761 pg=+0.1554 v=617.6539 ent=0.973 entq=-1.660 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=457s update_s=17.9 collect_s=17.9 train_s=15.8 gpu_mem%=91 min_mean_util%=55 [gpu0=22% gpu1=27% gpu2=27% gpu3=21% gpu4=19% gpu5=25% gpu6=0% gpu7=26%] -[update 24] steps/s= 851.0 decisions_total= 409600 eps_done= 2050 recent_reward= 5.782 pg=+0.3644 v=482.2890 ent=1.663 entq=-0.136 ecoef=0.0100 stage=0 lr=3.00e-4 elapsed=476s update_s=19.3 collect_s=19.2 train_s=16.8 gpu_mem%=91 min_mean_util%=54 [gpu0=21% gpu1=29% gpu2=12% gpu3=0% gpu4=0% gpu5=0% gpu6=28% gpu7=0%] -[update 25] steps/s= 886.6 decisions_total= 425984 eps_done= 2073 recent_reward= 6.230 pg=+0.1420 v=701.1448 ent=1.116 entq=-0.014 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=494s update_s=18.5 collect_s=18.4 train_s=16.1 gpu_mem%=92 min_mean_util%=54 [gpu0=15% gpu1=35% gpu2=28% gpu3=35% gpu4=25% gpu5=29% gpu6=34% gpu7=28%] -[train] checkpoint saved: checkpoints/policy_update25.ot -[update 26] steps/s= 875.3 decisions_total= 442368 eps_done= 2118 recent_reward= 6.089 pg=+0.0424 v=18.3161 ent=1.431 entq=-0.009 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=513s update_s=18.7 collect_s=18.7 train_s=16.3 gpu_mem%=91 min_mean_util%=55 [gpu0=24% gpu1=19% gpu2=29% gpu3=0% gpu4=29% gpu5=10% gpu6=27% gpu7=0%] -[update 27] steps/s= 869.3 decisions_total= 458752 eps_done= 2307 recent_reward= 6.378 pg=+0.1266 v=36.6137 ent=0.364 entq=-0.000 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=532s update_s=18.8 collect_s=18.8 train_s=16.9 gpu_mem%=91 min_mean_util%=55 [gpu0=27% gpu1=38% gpu2=35% gpu3=0% gpu4=26% gpu5=24% gpu6=0% gpu7=0%] -[update 28] steps/s= 843.0 decisions_total= 475136 eps_done= 2327 recent_reward= 6.748 pg=+0.1959 v=68.7315 ent=0.527 entq=-0.000 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=551s update_s=19.4 collect_s=19.4 train_s=17.2 gpu_mem%=91 min_mean_util%=55 [gpu0=29% gpu1=0% gpu2=0% gpu3=0% gpu4=27% gpu5=0% gpu6=25% gpu7=0%] -[update 29] steps/s= 848.5 decisions_total= 491520 eps_done= 2369 recent_reward= 7.453 pg=+0.0537 v=25.9977 ent=1.140 entq=-0.052 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=571s update_s=19.3 collect_s=19.3 train_s=16.9 gpu_mem%=91 min_mean_util%=55 [gpu0=33% gpu1=27% gpu2=26% gpu3=29% gpu4=26% gpu5=27% gpu6=27% gpu7=21%] -[update 30] steps/s= 868.7 decisions_total= 507904 eps_done= 2562 recent_reward= 7.848 pg=+0.0760 v=23.2998 ent=1.295 entq=-0.097 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=590s update_s=18.9 collect_s=18.8 train_s=16.6 gpu_mem%=91 min_mean_util%=55 [gpu0=29% gpu1=0% gpu2=0% gpu3=0% gpu4=0% gpu5=33% gpu6=8% gpu7=0%] -[update 31] steps/s= 850.1 decisions_total= 524288 eps_done= 2580 recent_reward= 7.640 pg=+0.2288 v=137.1612 ent=1.083 entq=-0.005 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=609s update_s=19.3 collect_s=19.2 train_s=17.2 gpu_mem%=91 min_mean_util%=55 [gpu0=12% gpu1=25% gpu2=0% gpu3=0% gpu4=32% gpu5=23% gpu6=24% gpu7=0%] -[update 32] steps/s= 847.5 decisions_total= 540672 eps_done= 2620 recent_reward= 7.013 pg=+0.1280 v=70.6863 ent=1.296 entq=-0.085 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=628s update_s=19.3 collect_s=19.3 train_s=18.4 gpu_mem%=91 min_mean_util%=55 [gpu0=25% gpu1=25% gpu2=21% gpu3=26% gpu4=37% gpu5=0% gpu6=0% gpu7=12%] -[update 33] steps/s= 859.8 decisions_total= 557056 eps_done= 2818 recent_reward= 10.335 pg=+0.1906 v=360.5235 ent=0.746 entq=-0.023 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=647s update_s=19.1 collect_s=19.0 train_s=17.4 gpu_mem%=91 min_mean_util%=55 [gpu0=0% gpu1=0% gpu2=0% gpu3=0% gpu4=36% gpu5=0% gpu6=0% gpu7=27%] -[update 34] steps/s= 851.6 decisions_total= 573440 eps_done= 2832 recent_reward= 9.129 pg=+0.1788 v=47.4989 ent=1.153 entq=-0.047 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=666s update_s=19.2 collect_s=19.2 train_s=18.5 gpu_mem%=91 min_mean_util%=55 [gpu0=30% gpu1=33% gpu2=37% gpu3=25% gpu4=26% gpu5=25% gpu6=0% gpu7=0%] -[update 35] steps/s= 864.8 decisions_total= 589824 eps_done= 2871 recent_reward= 6.311 pg=+0.0749 v=158.5300 ent=1.710 entq=-0.005 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=685s update_s=18.9 collect_s=18.9 train_s=17.3 gpu_mem%=91 min_mean_util%=55 [gpu0=26% gpu1=28% gpu2=29% gpu3=26% gpu4=22% gpu5=11% gpu6=31% gpu7=12%] -[update 36] steps/s= 838.1 decisions_total= 606208 eps_done= 3074 recent_reward= 6.022 pg=+0.0392 v=25.4236 ent=2.246 entq=-0.031 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=705s update_s=19.5 collect_s=19.5 train_s=16.8 gpu_mem%=91 min_mean_util%=55 [gpu0=32% gpu1=0% gpu2=30% gpu3=29% gpu4=26% gpu5=15% gpu6=23% gpu7=0%] -[update 37] steps/s= 845.7 decisions_total= 622592 eps_done= 3087 recent_reward= 6.665 pg=+0.0303 v=15.1308 ent=0.905 entq=-0.016 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=724s update_s=19.4 collect_s=19.3 train_s=18.0 gpu_mem%=91 min_mean_util%=55 [gpu0=26% gpu1=12% gpu2=11% gpu3=29% gpu4=24% gpu5=35% gpu6=0% gpu7=0%] -[update 38] steps/s= 865.2 decisions_total= 638976 eps_done= 3122 recent_reward= 7.927 pg=+0.5757 v=30.0962 ent=2.378 entq=-0.328 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=743s update_s=18.9 collect_s=18.9 train_s=16.4 gpu_mem%=91 min_mean_util%=55 [gpu0=24% gpu1=29% gpu2=28% gpu3=31% gpu4=0% gpu5=26% gpu6=0% gpu7=0%] -[update 39] steps/s= 863.2 decisions_total= 655360 eps_done= 3328 recent_reward= 9.606 pg=+0.0776 v=26.5073 ent=1.947 entq=-0.001 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=762s update_s=19.0 collect_s=18.9 train_s=16.9 gpu_mem%=91 min_mean_util%=55 [gpu0=27% gpu1=0% gpu2=12% gpu3=37% gpu4=0% gpu5=38% gpu6=11% gpu7=0%] -[update 40] steps/s= 908.8 decisions_total= 671744 eps_done= 3335 recent_reward= 9.733 pg=+0.1535 v=14.4100 ent=1.706 entq=-0.060 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=780s update_s=18.0 collect_s=18.0 train_s=17.0 gpu_mem%=91 min_mean_util%=55 [gpu0=25% gpu1=0% gpu2=0% gpu3=0% gpu4=0% gpu5=0% gpu6=11% gpu7=0%] -[update 41] steps/s= 936.2 decisions_total= 688128 eps_done= 3376 recent_reward= 6.786 pg=+0.0639 v=67.6912 ent=1.153 entq=-0.337 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=798s update_s=17.5 collect_s=17.5 train_s=15.6 gpu_mem%=91 min_mean_util%=55 [gpu0=11% gpu1=35% gpu2=32% gpu3=26% gpu4=29% gpu5=32% gpu6=26% gpu7=26%] -[update 42] steps/s= 883.8 decisions_total= 704512 eps_done= 3584 recent_reward= 6.805 pg=+0.1417 v=9.2507 ent=2.028 entq=-0.102 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=816s update_s=18.5 collect_s=18.5 train_s=18.2 gpu_mem%=91 min_mean_util%=55 [gpu0=100% gpu1=100% gpu2=100% gpu3=100% gpu4=100% gpu5=100% gpu6=100% gpu7=100%] -[update 43] steps/s= 914.4 decisions_total= 720896 eps_done= 3588 recent_reward= 7.110 pg=+0.1606 v=36.4001 ent=0.769 entq=-0.068 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=834s update_s=17.9 collect_s=17.9 train_s=16.2 gpu_mem%=91 min_mean_util%=55 [gpu0=11% gpu1=0% gpu2=27% gpu3=0% gpu4=29% gpu5=24% gpu6=30% gpu7=14%] -[update 44] steps/s= 859.7 decisions_total= 737280 eps_done= 3627 recent_reward= 7.153 pg=+0.1530 v=2.1996 ent=1.711 entq=-0.563 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=853s update_s=19.1 collect_s=19.0 train_s=17.7 gpu_mem%=91 min_mean_util%=55 [gpu0=19% gpu1=26% gpu2=27% gpu3=16% gpu4=24% gpu5=20% gpu6=0% gpu7=26%] -[update 45] steps/s= 927.6 decisions_total= 753664 eps_done= 3840 recent_reward= 6.514 pg=+0.0658 v=276.4028 ent=2.131 entq=-0.025 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=871s update_s=17.7 collect_s=17.6 train_s=16.1 gpu_mem%=91 min_mean_util%=56 [gpu0=31% gpu1=9% gpu2=26% gpu3=27% gpu4=29% gpu5=34% gpu6=25% gpu7=31%] -[update 46] steps/s= 920.1 decisions_total= 770048 eps_done= 3844 recent_reward= 6.320 pg=+0.4103 v=64.7149 ent=1.852 entq=-0.016 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=889s update_s=17.8 collect_s=17.8 train_s=16.6 gpu_mem%=91 min_mean_util%=56 [gpu0=27% gpu1=25% gpu2=27% gpu3=26% gpu4=25% gpu5=25% gpu6=16% gpu7=29%] -[update 47] steps/s= 871.8 decisions_total= 786432 eps_done= 3881 recent_reward= 6.557 pg=+0.0727 v=10.1575 ent=1.921 entq=-0.035 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=908s update_s=18.8 collect_s=18.8 train_s=16.7 gpu_mem%=91 min_mean_util%=56 [gpu0=27% gpu1=23% gpu2=23% gpu3=23% gpu4=21% gpu5=21% gpu6=18% gpu7=25%] -[update 48] steps/s= 815.5 decisions_total= 802816 eps_done= 4096 recent_reward= 7.071 pg=+0.1244 v=0.5447 ent=3.189 entq=-0.024 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=928s update_s=20.1 collect_s=20.0 train_s=17.4 gpu_mem%=91 min_mean_util%=56 [gpu0=28% gpu1=0% gpu2=0% gpu3=28% gpu4=0% gpu5=0% gpu6=0% gpu7=12%] -[update 49] steps/s= 870.6 decisions_total= 819200 eps_done= 4099 recent_reward= 7.074 pg=+0.2330 v=15.2458 ent=3.855 entq=-0.152 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=946s update_s=18.8 collect_s=18.8 train_s=16.6 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=30% gpu2=26% gpu3=31% gpu4=15% gpu5=0% gpu6=25% gpu7=27%] -[update 50] steps/s= 840.6 decisions_total= 835584 eps_done= 4131 recent_reward= 7.517 pg=+0.2130 v=3.4246 ent=1.255 entq=-0.427 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=966s update_s=19.5 collect_s=19.4 train_s=17.1 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=30% gpu2=0% gpu3=29% gpu4=26% gpu5=28% gpu6=0% gpu7=0%] -[train] checkpoint saved: checkpoints/policy_update50.ot -[update 51] steps/s= 834.8 decisions_total= 851968 eps_done= 4183 recent_reward= 7.263 pg=+0.1109 v=1.3679 ent=2.864 entq=-0.025 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=986s update_s=19.6 collect_s=19.6 train_s=16.9 gpu_mem%=92 min_mean_util%=56 [gpu0=26% gpu1=24% gpu2=29% gpu3=20% gpu4=30% gpu5=27% gpu6=21% gpu7=29%] -[update 52] steps/s= 840.5 decisions_total= 868352 eps_done= 4355 recent_reward= 6.752 pg=+0.1408 v=1.5845 ent=5.235 entq=-0.020 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1005s update_s=19.5 collect_s=19.4 train_s=17.5 gpu_mem%=92 min_mean_util%=56 [gpu0=27% gpu1=25% gpu2=25% gpu3=0% gpu4=26% gpu5=25% gpu6=26% gpu7=0%] -[update 53] steps/s= 859.3 decisions_total= 884736 eps_done= 4383 recent_reward= 7.466 pg=+0.4548 v=7.2336 ent=1.540 entq=-0.006 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1024s update_s=19.1 collect_s=19.0 train_s=17.2 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=27% gpu2=25% gpu3=27% gpu4=25% gpu5=26% gpu6=22% gpu7=11%] -[update 54] steps/s= 854.0 decisions_total= 901120 eps_done= 4434 recent_reward= 6.841 pg=+0.0554 v=2.4454 ent=4.020 entq=-0.010 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1043s update_s=19.2 collect_s=19.1 train_s=18.3 gpu_mem%=92 min_mean_util%=56 [gpu0=25% gpu1=13% gpu2=31% gpu3=33% gpu4=17% gpu5=31% gpu6=27% gpu7=24%] -[update 55] steps/s= 891.1 decisions_total= 917504 eps_done= 4610 recent_reward= 7.128 pg=+0.2481 v=2.0204 ent=2.558 entq=-0.002 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1062s update_s=18.4 collect_s=18.3 train_s=16.9 gpu_mem%=92 min_mean_util%=56 [gpu0=27% gpu1=13% gpu2=24% gpu3=27% gpu4=28% gpu5=26% gpu6=27% gpu7=23%] -[update 56] steps/s= 836.8 decisions_total= 933888 eps_done= 4636 recent_reward= 7.561 pg=+0.0652 v=2.0617 ent=2.211 entq=-0.012 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1081s update_s=19.6 collect_s=19.5 train_s=18.1 gpu_mem%=92 min_mean_util%=56 [gpu0=25% gpu1=0% gpu2=14% gpu3=34% gpu4=0% gpu5=0% gpu6=0% gpu7=31%] -[update 57] steps/s= 865.6 decisions_total= 950272 eps_done= 4684 recent_reward= 9.464 pg=+0.0590 v=3.7349 ent=3.008 entq=-0.000 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1100s update_s=18.9 collect_s=18.9 train_s=16.6 gpu_mem%=92 min_mean_util%=56 [gpu0=27% gpu1=31% gpu2=29% gpu3=28% gpu4=0% gpu5=0% gpu6=11% gpu7=28%] -[update 58] steps/s= 875.4 decisions_total= 966656 eps_done= 4866 recent_reward= 7.369 pg=+0.0953 v=4.2191 ent=2.074 entq=-0.004 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1119s update_s=18.7 collect_s=18.7 train_s=17.3 gpu_mem%=92 min_mean_util%=56 [gpu0=27% gpu1=0% gpu2=30% gpu3=30% gpu4=36% gpu5=22% gpu6=26% gpu7=23%] -[update 59] steps/s= 876.7 decisions_total= 983040 eps_done= 4881 recent_reward= 7.282 pg=+0.1328 v=3.7055 ent=1.098 entq=-0.005 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1138s update_s=18.7 collect_s=18.6 train_s=16.5 gpu_mem%=92 min_mean_util%=56 [gpu0=17% gpu1=14% gpu2=16% gpu3=14% gpu4=25% gpu5=26% gpu6=11% gpu7=27%] -[update 60] steps/s= 879.3 decisions_total= 999424 eps_done= 4944 recent_reward= 7.962 pg=+0.0570 v=1.5570 ent=2.222 entq=-0.009 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1156s update_s=18.6 collect_s=18.6 train_s=17.6 gpu_mem%=92 min_mean_util%=56 [gpu0=25% gpu1=0% gpu2=0% gpu3=0% gpu4=0% gpu5=0% gpu6=0% gpu7=25%] -[update 61] steps/s= 885.6 decisions_total= 1015808 eps_done= 5122 recent_reward= 8.817 pg=+0.1703 v=7.4907 ent=3.351 entq=-0.002 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1175s update_s=18.5 collect_s=18.5 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=0% gpu1=0% gpu2=0% gpu3=0% gpu4=26% gpu5=0% gpu6=0% gpu7=2%] -[update 62] steps/s= 851.2 decisions_total= 1032192 eps_done= 5135 recent_reward= 9.150 pg=-0.0287 v=2.1823 ent=2.455 entq=-0.008 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1194s update_s=19.2 collect_s=19.2 train_s=18.0 gpu_mem%=92 min_mean_util%=56 [gpu0=24% gpu1=0% gpu2=25% gpu3=25% gpu4=10% gpu5=10% gpu6=0% gpu7=26%] -[update 63] steps/s= 898.1 decisions_total= 1048576 eps_done= 5193 recent_reward= 7.844 pg=+0.1319 v=1.3819 ent=1.254 entq=-0.003 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1212s update_s=18.2 collect_s=18.2 train_s=17.8 gpu_mem%=92 min_mean_util%=56 [gpu0=21% gpu1=2% gpu2=27% gpu3=10% gpu4=14% gpu5=29% gpu6=34% gpu7=72%] -[update 64] steps/s= 869.8 decisions_total= 1064960 eps_done= 5376 recent_reward= 6.625 pg=+0.0822 v=21.5305 ent=1.133 entq=-0.002 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1231s update_s=18.8 collect_s=18.8 train_s=18.3 gpu_mem%=92 min_mean_util%=56 [gpu0=26% gpu1=28% gpu2=29% gpu3=21% gpu4=26% gpu5=25% gpu6=27% gpu7=26%] -[update 65] steps/s= 889.7 decisions_total= 1081344 eps_done= 5388 recent_reward= 6.374 pg=-0.0455 v=4.8901 ent=0.593 entq=-0.003 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1250s update_s=18.4 collect_s=18.4 train_s=16.0 gpu_mem%=92 min_mean_util%=56 [gpu0=32% gpu1=29% gpu2=26% gpu3=25% gpu4=36% gpu5=26% gpu6=26% gpu7=25%] -[update 66] steps/s= 862.7 decisions_total= 1097728 eps_done= 5444 recent_reward= 8.320 pg=+0.1025 v=2.9835 ent=0.512 entq=-0.016 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1269s update_s=19.0 collect_s=18.9 train_s=16.3 gpu_mem%=92 min_mean_util%=56 [gpu0=17% gpu1=26% gpu2=29% gpu3=25% gpu4=14% gpu5=29% gpu6=15% gpu7=0%] -[update 67] steps/s= 897.1 decisions_total= 1114112 eps_done= 5632 recent_reward= 7.000 pg=+0.0951 v=2.2674 ent=0.537 entq=-0.001 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1287s update_s=18.3 collect_s=18.2 train_s=15.7 gpu_mem%=92 min_mean_util%=56 [gpu0=31% gpu1=33% gpu2=30% gpu3=41% gpu4=27% gpu5=14% gpu6=39% gpu7=15%] -[update 68] steps/s= 834.2 decisions_total= 1130496 eps_done= 5647 recent_reward= 6.900 pg=+0.0788 v=6.1331 ent=0.486 entq=-0.000 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1306s update_s=19.6 collect_s=19.6 train_s=17.1 gpu_mem%=92 min_mean_util%=56 [gpu0=14% gpu1=24% gpu2=11% gpu3=26% gpu4=27% gpu5=28% gpu6=0% gpu7=0%] -[update 69] steps/s= 887.5 decisions_total= 1146880 eps_done= 5697 recent_reward= 7.900 pg=+0.0761 v=0.1837 ent=0.424 entq=-0.000 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1325s update_s=18.5 collect_s=18.4 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=31% gpu2=25% gpu3=24% gpu4=25% gpu5=23% gpu6=14% gpu7=25%] -[update 70] steps/s= 871.7 decisions_total= 1163264 eps_done= 5888 recent_reward= 9.212 pg=+0.0077 v=4.6087 ent=1.136 entq=-0.002 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1344s update_s=18.8 collect_s=18.7 train_s=16.6 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=24% gpu2=0% gpu3=18% gpu4=27% gpu5=0% gpu6=26% gpu7=0%] -[update 71] steps/s= 859.2 decisions_total= 1179648 eps_done= 5900 recent_reward= 8.463 pg=-0.0300 v=6.3514 ent=0.796 entq=-0.001 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1363s update_s=19.1 collect_s=19.0 train_s=16.9 gpu_mem%=92 min_mean_util%=56 [gpu0=26% gpu1=24% gpu2=23% gpu3=0% gpu4=0% gpu5=25% gpu6=26% gpu7=0%] -[update 72] steps/s= 897.5 decisions_total= 1196032 eps_done= 5952 recent_reward= 8.991 pg=+0.0648 v=0.8689 ent=0.767 entq=-0.001 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1381s update_s=18.3 collect_s=18.2 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=31% gpu1=0% gpu2=27% gpu3=27% gpu4=26% gpu5=0% gpu6=0% gpu7=0%] -[update 73] steps/s= 887.7 decisions_total= 1212416 eps_done= 6144 recent_reward= 8.129 pg=+0.0347 v=1.3187 ent=0.980 entq=-0.000 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1399s update_s=18.5 collect_s=18.4 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=29% gpu2=27% gpu3=17% gpu4=13% gpu5=0% gpu6=22% gpu7=24%] -[update 74] steps/s= 876.2 decisions_total= 1228800 eps_done= 6156 recent_reward= 7.538 pg=+0.0645 v=2.9938 ent=1.115 entq=-0.005 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1418s update_s=18.7 collect_s=18.7 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=31% gpu1=30% gpu2=0% gpu3=28% gpu4=25% gpu5=30% gpu6=30% gpu7=21%] -[update 75] steps/s= 866.8 decisions_total= 1245184 eps_done= 6201 recent_reward= 6.742 pg=+0.0255 v=0.4432 ent=0.276 entq=-0.003 ecoef=0.0099 stage=0 lr=3.00e-4 elapsed=1437s update_s=18.9 collect_s=18.8 train_s=16.3 gpu_mem%=92 min_mean_util%=56 [gpu0=27% gpu1=28% gpu2=27% gpu3=0% gpu4=0% gpu5=0% gpu6=11% gpu7=11%] -[train] checkpoint saved: checkpoints/policy_update75.ot -[update 76] steps/s= 883.6 decisions_total= 1261568 eps_done= 6274 recent_reward= 8.364 pg=+0.0505 v=5.1202 ent=0.225 entq=-0.000 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1456s update_s=18.5 collect_s=18.5 train_s=16.5 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=25% gpu2=30% gpu3=28% gpu4=20% gpu5=26% gpu6=0% gpu7=26%] -[update 77] steps/s= 877.8 decisions_total= 1277952 eps_done= 6410 recent_reward= 7.229 pg=+0.0123 v=2.2266 ent=0.338 entq=-0.000 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1474s update_s=18.7 collect_s=18.6 train_s=16.8 gpu_mem%=92 min_mean_util%=56 [gpu0=32% gpu1=11% gpu2=0% gpu3=12% gpu4=36% gpu5=0% gpu6=0% gpu7=0%] -[update 78] steps/s= 879.2 decisions_total= 1294336 eps_done= 6450 recent_reward= 7.966 pg=+0.0006 v=0.3834 ent=0.418 entq=-0.001 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1493s update_s=18.6 collect_s=18.6 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=26% gpu2=0% gpu3=30% gpu4=28% gpu5=29% gpu6=0% gpu7=0%] -[update 79] steps/s= 863.7 decisions_total= 1310720 eps_done= 6518 recent_reward= 11.603 pg=+0.0667 v=1.6787 ent=0.525 entq=-0.001 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1512s update_s=19.0 collect_s=18.9 train_s=16.2 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=9% gpu2=0% gpu3=29% gpu4=24% gpu5=12% gpu6=0% gpu7=0%] -[update 80] steps/s= 868.2 decisions_total= 1327104 eps_done= 6666 recent_reward= 11.730 pg=-0.0604 v=1.2676 ent=0.753 entq=-0.005 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1531s update_s=18.9 collect_s=18.8 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=42% gpu2=26% gpu3=0% gpu4=13% gpu5=0% gpu6=0% gpu7=27%] -[update 81] steps/s= 875.2 decisions_total= 1343488 eps_done= 6708 recent_reward= 10.121 pg=+0.0371 v=3.5656 ent=0.588 entq=-0.001 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1550s update_s=18.7 collect_s=18.7 train_s=16.6 gpu_mem%=92 min_mean_util%=56 [gpu0=14% gpu1=17% gpu2=21% gpu3=27% gpu4=26% gpu5=22% gpu6=26% gpu7=0%] -[update 82] steps/s= 874.5 decisions_total= 1359872 eps_done= 6770 recent_reward= 8.533 pg=-0.0352 v=4.3367 ent=0.632 entq=-0.024 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1568s update_s=18.7 collect_s=18.7 train_s=16.2 gpu_mem%=92 min_mean_util%=56 [gpu0=22% gpu1=20% gpu2=33% gpu3=28% gpu4=20% gpu5=13% gpu6=24% gpu7=20%] -[update 83] steps/s= 919.8 decisions_total= 1376256 eps_done= 6920 recent_reward= 9.205 pg=+0.0395 v=1.2532 ent=0.614 entq=-0.000 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1586s update_s=17.8 collect_s=17.8 train_s=15.9 gpu_mem%=92 min_mean_util%=56 [gpu0=32% gpu1=36% gpu2=26% gpu3=28% gpu4=29% gpu5=0% gpu6=25% gpu7=20%] -[update 84] steps/s= 891.5 decisions_total= 1392640 eps_done= 6957 recent_reward= 8.582 pg=+0.0595 v=2.2908 ent=0.999 entq=-0.001 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1604s update_s=18.4 collect_s=18.3 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=19% gpu2=27% gpu3=26% gpu4=28% gpu5=23% gpu6=0% gpu7=26%] -[update 85] steps/s= 889.4 decisions_total= 1409024 eps_done= 7023 recent_reward= 6.359 pg=-0.0235 v=0.2492 ent=0.201 entq=-0.000 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1623s update_s=18.4 collect_s=18.4 train_s=16.2 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=26% gpu2=27% gpu3=0% gpu4=26% gpu5=19% gpu6=0% gpu7=0%] -[update 86] steps/s= 875.9 decisions_total= 1425408 eps_done= 7176 recent_reward= 6.734 pg=+0.0746 v=0.3159 ent=0.428 entq=-0.000 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1642s update_s=18.7 collect_s=18.7 train_s=17.0 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=11% gpu2=26% gpu3=26% gpu4=36% gpu5=0% gpu6=22% gpu7=0%] -[update 87] steps/s= 848.9 decisions_total= 1441792 eps_done= 7211 recent_reward= 7.618 pg=+0.0034 v=1.3817 ent=0.303 entq=-0.001 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1661s update_s=19.3 collect_s=19.3 train_s=17.7 gpu_mem%=92 min_mean_util%=56 [gpu0=24% gpu1=29% gpu2=25% gpu3=16% gpu4=2% gpu5=0% gpu6=0% gpu7=0%] -[update 88] steps/s= 868.1 decisions_total= 1458176 eps_done= 7270 recent_reward= 8.035 pg=+0.0772 v=0.5244 ent=0.273 entq=-0.001 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1680s update_s=18.9 collect_s=18.8 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=30% gpu2=19% gpu3=0% gpu4=26% gpu5=0% gpu6=0% gpu7=0%] -[update 89] steps/s= 878.8 decisions_total= 1474560 eps_done= 7428 recent_reward= 7.923 pg=+0.0279 v=0.7294 ent=0.712 entq=-0.001 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1698s update_s=18.6 collect_s=18.6 train_s=15.7 gpu_mem%=92 min_mean_util%=56 [gpu0=12% gpu1=29% gpu2=0% gpu3=30% gpu4=30% gpu5=0% gpu6=0% gpu7=0%] -[update 90] steps/s= 885.5 decisions_total= 1490944 eps_done= 7460 recent_reward= 8.973 pg=-0.0658 v=1.9296 ent=0.302 entq=-0.001 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1717s update_s=18.5 collect_s=18.5 train_s=16.5 gpu_mem%=92 min_mean_util%=56 [gpu0=27% gpu1=28% gpu2=31% gpu3=24% gpu4=16% gpu5=13% gpu6=19% gpu7=26%] -[update 91] steps/s= 863.6 decisions_total= 1507328 eps_done= 7521 recent_reward= 7.079 pg=+0.0176 v=0.1575 ent=0.219 entq=-0.001 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1736s update_s=19.0 collect_s=18.9 train_s=16.2 gpu_mem%=92 min_mean_util%=56 [gpu0=0% gpu1=29% gpu2=28% gpu3=0% gpu4=0% gpu5=26% gpu6=0% gpu7=0%] -[update 92] steps/s= 883.6 decisions_total= 1523712 eps_done= 7684 recent_reward= 8.091 pg=-0.0775 v=1.3131 ent=0.512 entq=-0.002 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1754s update_s=18.5 collect_s=18.5 train_s=16.5 gpu_mem%=92 min_mean_util%=56 [gpu0=25% gpu1=25% gpu2=28% gpu3=25% gpu4=0% gpu5=25% gpu6=26% gpu7=0%] -[update 93] steps/s= 896.5 decisions_total= 1540096 eps_done= 7710 recent_reward= 7.384 pg=+0.0464 v=1.1568 ent=0.386 entq=-0.002 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1773s update_s=18.3 collect_s=18.2 train_s=16.2 gpu_mem%=92 min_mean_util%=56 [gpu0=27% gpu1=24% gpu2=17% gpu3=12% gpu4=24% gpu5=25% gpu6=0% gpu7=24%] -[update 94] steps/s= 884.2 decisions_total= 1556480 eps_done= 7769 recent_reward= 8.709 pg=-0.0230 v=0.1435 ent=0.239 entq=-0.009 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1791s update_s=18.5 collect_s=18.5 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=11% gpu2=27% gpu3=34% gpu4=25% gpu5=0% gpu6=26% gpu7=32%] -[update 95] steps/s= 855.0 decisions_total= 1572864 eps_done= 7943 recent_reward= 8.105 pg=+0.0117 v=0.5599 ent=0.384 entq=-0.010 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1810s update_s=19.2 collect_s=19.1 train_s=16.7 gpu_mem%=92 min_mean_util%=56 [gpu0=0% gpu1=12% gpu2=0% gpu3=40% gpu4=0% gpu5=26% gpu6=23% gpu7=23%] -[update 96] steps/s= 903.1 decisions_total= 1589248 eps_done= 7958 recent_reward= 7.452 pg=+0.0272 v=0.4786 ent=0.442 entq=-0.012 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1828s update_s=18.1 collect_s=18.1 train_s=16.9 gpu_mem%=92 min_mean_util%=56 [gpu0=26% gpu1=7% gpu2=22% gpu3=23% gpu4=20% gpu5=0% gpu6=32% gpu7=29%] -[update 97] steps/s= 886.5 decisions_total= 1605632 eps_done= 8021 recent_reward= 7.963 pg=+0.0298 v=0.3455 ent=0.282 entq=-0.009 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1847s update_s=18.5 collect_s=18.4 train_s=15.9 gpu_mem%=92 min_mean_util%=56 [gpu0=18% gpu1=0% gpu2=25% gpu3=29% gpu4=27% gpu5=0% gpu6=22% gpu7=13%] -[update 98] steps/s= 880.1 decisions_total= 1622016 eps_done= 8199 recent_reward= 7.992 pg=+0.0065 v=1.0840 ent=0.364 entq=-0.012 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1866s update_s=18.6 collect_s=18.6 train_s=15.8 gpu_mem%=92 min_mean_util%=56 [gpu0=16% gpu1=28% gpu2=29% gpu3=18% gpu4=29% gpu5=0% gpu6=31% gpu7=0%] -[update 99] steps/s= 890.1 decisions_total= 1638400 eps_done= 8213 recent_reward= 7.473 pg=+0.0225 v=1.7441 ent=0.235 entq=-0.018 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1884s update_s=18.4 collect_s=18.4 train_s=16.5 gpu_mem%=92 min_mean_util%=56 [gpu0=26% gpu1=30% gpu2=26% gpu3=26% gpu4=21% gpu5=22% gpu6=26% gpu7=0%] -[update 100] steps/s= 871.1 decisions_total= 1654784 eps_done= 8267 recent_reward= 8.127 pg=-0.0634 v=0.1477 ent=0.265 entq=-0.049 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1903s update_s=18.8 collect_s=18.8 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=31% gpu1=25% gpu2=32% gpu3=29% gpu4=24% gpu5=30% gpu6=26% gpu7=12%] -[train] checkpoint saved: checkpoints/policy_update100.ot -[update 101] steps/s= 886.9 decisions_total= 1671168 eps_done= 8358 recent_reward= 9.329 pg=-0.0091 v=0.2003 ent=0.437 entq=-0.038 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1921s update_s=18.5 collect_s=18.4 train_s=16.0 gpu_mem%=92 min_mean_util%=56 [gpu0=26% gpu1=26% gpu2=26% gpu3=33% gpu4=0% gpu5=0% gpu6=0% gpu7=11%] -[update 102] steps/s= 875.3 decisions_total= 1687552 eps_done= 8465 recent_reward= 8.301 pg=+0.0129 v=0.5120 ent=0.373 entq=-0.035 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1940s update_s=18.7 collect_s=18.7 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=0% gpu2=28% gpu3=13% gpu4=0% gpu5=12% gpu6=12% gpu7=0%] -[update 103] steps/s= 890.3 decisions_total= 1703936 eps_done= 8517 recent_reward= 8.089 pg=+0.0150 v=0.4572 ent=0.243 entq=-0.078 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1958s update_s=18.4 collect_s=18.4 train_s=16.5 gpu_mem%=92 min_mean_util%=56 [gpu0=36% gpu1=30% gpu2=26% gpu3=28% gpu4=25% gpu5=17% gpu6=0% gpu7=26%] -[update 104] steps/s= 886.5 decisions_total= 1720320 eps_done= 8601 recent_reward= 10.746 pg=+0.0198 v=0.6576 ent=0.390 entq=-0.018 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1977s update_s=18.5 collect_s=18.4 train_s=15.9 gpu_mem%=92 min_mean_util%=56 [gpu0=31% gpu1=32% gpu2=13% gpu3=28% gpu4=30% gpu5=29% gpu6=11% gpu7=30%] -[update 105] steps/s= 893.5 decisions_total= 1736704 eps_done= 8719 recent_reward= 9.625 pg=-0.0222 v=0.9782 ent=0.319 entq=-0.017 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=1995s update_s=18.3 collect_s=18.3 train_s=16.5 gpu_mem%=92 min_mean_util%=56 [gpu0=23% gpu1=37% gpu2=26% gpu3=26% gpu4=0% gpu5=0% gpu6=26% gpu7=26%] -[update 106] steps/s= 888.0 decisions_total= 1753088 eps_done= 8765 recent_reward= 9.360 pg=-0.0161 v=0.7943 ent=0.236 entq=-0.029 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2014s update_s=18.5 collect_s=18.4 train_s=15.8 gpu_mem%=92 min_mean_util%=56 [gpu0=34% gpu1=32% gpu2=29% gpu3=29% gpu4=0% gpu5=33% gpu6=29% gpu7=29%] -[update 107] steps/s= 917.4 decisions_total= 1769472 eps_done= 8848 recent_reward= 7.888 pg=+0.0443 v=0.6490 ent=0.301 entq=-0.027 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2032s update_s=17.9 collect_s=17.8 train_s=15.7 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=34% gpu2=22% gpu3=26% gpu4=24% gpu5=27% gpu6=24% gpu7=22%] -[update 108] steps/s= 881.7 decisions_total= 1785856 eps_done= 8974 recent_reward= 9.713 pg=+0.0010 v=1.6472 ent=0.346 entq=-0.045 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2050s update_s=18.6 collect_s=18.5 train_s=17.0 gpu_mem%=92 min_mean_util%=56 [gpu0=37% gpu1=0% gpu2=0% gpu3=0% gpu4=0% gpu5=0% gpu6=25% gpu7=0%] -[update 109] steps/s= 891.0 decisions_total= 1802240 eps_done= 9015 recent_reward= 10.090 pg=+0.0794 v=0.9182 ent=0.300 entq=-0.049 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2069s update_s=18.4 collect_s=18.3 train_s=16.5 gpu_mem%=92 min_mean_util%=56 [gpu0=24% gpu1=27% gpu2=25% gpu3=25% gpu4=25% gpu5=28% gpu6=25% gpu7=26%] -[update 110] steps/s= 902.0 decisions_total= 1818624 eps_done= 9093 recent_reward= 8.755 pg=+0.0387 v=0.5011 ent=0.364 entq=-0.066 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2087s update_s=18.2 collect_s=18.1 train_s=15.9 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=0% gpu2=23% gpu3=0% gpu4=27% gpu5=11% gpu6=25% gpu7=28%] -[update 111] steps/s= 891.1 decisions_total= 1835008 eps_done= 9230 recent_reward= 8.743 pg=-0.0187 v=0.1789 ent=0.437 entq=-0.049 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2105s update_s=18.4 collect_s=18.3 train_s=16.0 gpu_mem%=92 min_mean_util%=56 [gpu0=20% gpu1=37% gpu2=19% gpu3=0% gpu4=26% gpu5=27% gpu6=14% gpu7=27%] -[update 112] steps/s= 902.6 decisions_total= 1851392 eps_done= 9267 recent_reward= 9.799 pg=+0.0324 v=0.7585 ent=0.330 entq=-0.113 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2123s update_s=18.2 collect_s=18.1 train_s=15.8 gpu_mem%=92 min_mean_util%=56 [gpu0=16% gpu1=29% gpu2=35% gpu3=0% gpu4=30% gpu5=26% gpu6=29% gpu7=30%] -[update 113] steps/s= 870.6 decisions_total= 1867776 eps_done= 9339 recent_reward= 9.091 pg=-0.0336 v=0.5311 ent=0.371 entq=-0.099 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2142s update_s=18.8 collect_s=18.8 train_s=16.7 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=0% gpu2=25% gpu3=19% gpu4=0% gpu5=30% gpu6=0% gpu7=0%] -[update 114] steps/s= 891.5 decisions_total= 1884160 eps_done= 9482 recent_reward= 8.699 pg=-0.0660 v=0.3006 ent=0.541 entq=-0.069 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2160s update_s=18.4 collect_s=18.3 train_s=15.6 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=25% gpu2=13% gpu3=25% gpu4=31% gpu5=13% gpu6=29% gpu7=12%] -[update 115] steps/s= 899.4 decisions_total= 1900544 eps_done= 9517 recent_reward= 9.582 pg=+0.0224 v=1.1650 ent=0.412 entq=-0.134 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2179s update_s=18.2 collect_s=18.2 train_s=16.8 gpu_mem%=92 min_mean_util%=56 [gpu0=24% gpu1=23% gpu2=27% gpu3=26% gpu4=18% gpu5=28% gpu6=27% gpu7=26%] -[update 116] steps/s= 882.7 decisions_total= 1916928 eps_done= 9584 recent_reward= 10.474 pg=+0.0458 v=0.6485 ent=0.274 entq=-0.111 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2197s update_s=18.6 collect_s=18.5 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=33% gpu2=26% gpu3=25% gpu4=26% gpu5=0% gpu6=0% gpu7=25%] -[update 117] steps/s= 897.0 decisions_total= 1933312 eps_done= 9738 recent_reward= 9.343 pg=-0.0055 v=0.6007 ent=0.485 entq=-0.154 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2215s update_s=18.3 collect_s=18.2 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=35% gpu2=31% gpu3=0% gpu4=24% gpu5=26% gpu6=26% gpu7=25%] -[update 118] steps/s= 889.4 decisions_total= 1949696 eps_done= 9765 recent_reward= 9.405 pg=+0.0594 v=0.5824 ent=0.379 entq=-0.165 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2234s update_s=18.4 collect_s=18.4 train_s=15.9 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=27% gpu2=25% gpu3=15% gpu4=12% gpu5=12% gpu6=0% gpu7=0%] -[update 119] steps/s= 900.8 decisions_total= 1966080 eps_done= 9829 recent_reward= 10.488 pg=+0.0643 v=0.3039 ent=0.195 entq=-0.205 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2252s update_s=18.2 collect_s=18.1 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=28% gpu2=27% gpu3=26% gpu4=13% gpu5=0% gpu6=0% gpu7=24%] -[update 120] steps/s= 872.9 decisions_total= 1982464 eps_done= 9993 recent_reward= 10.756 pg=-0.0133 v=0.7664 ent=0.309 entq=-0.138 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2271s update_s=18.8 collect_s=18.7 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=29% gpu2=27% gpu3=29% gpu4=0% gpu5=0% gpu6=0% gpu7=0%] -[update 121] steps/s= 914.0 decisions_total= 1998848 eps_done=10013 recent_reward= 10.332 pg=-0.0416 v=0.7700 ent=0.310 entq=-0.214 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2289s update_s=17.9 collect_s=17.9 train_s=15.9 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=30% gpu2=20% gpu3=31% gpu4=25% gpu5=30% gpu6=26% gpu7=29%] -[update 122] steps/s= 885.7 decisions_total= 2015232 eps_done=10078 recent_reward= 10.287 pg=-0.0269 v=0.3167 ent=0.362 entq=-0.188 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2307s update_s=18.5 collect_s=18.5 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=28% gpu2=0% gpu3=30% gpu4=26% gpu5=12% gpu6=0% gpu7=28%] -[update 123] steps/s= 882.4 decisions_total= 2031616 eps_done=10248 recent_reward= 12.271 pg=-0.0377 v=0.5753 ent=0.583 entq=-0.113 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2326s update_s=18.6 collect_s=18.5 train_s=16.6 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=24% gpu2=25% gpu3=14% gpu4=12% gpu5=0% gpu6=11% gpu7=25%] -[update 124] steps/s= 875.3 decisions_total= 2048000 eps_done=10267 recent_reward= 11.725 pg=-0.0278 v=0.7189 ent=0.413 entq=-0.237 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2345s update_s=18.7 collect_s=18.7 train_s=16.7 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=0% gpu2=26% gpu3=35% gpu4=25% gpu5=10% gpu6=10% gpu7=12%] -[update 125] steps/s= 916.4 decisions_total= 2064384 eps_done=10322 recent_reward= 11.054 pg=+0.0192 v=1.6193 ent=0.256 entq=-0.167 ecoef=0.0098 stage=0 lr=3.00e-4 elapsed=2362s update_s=17.9 collect_s=17.8 train_s=15.9 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=37% gpu2=25% gpu3=30% gpu4=12% gpu5=26% gpu6=25% gpu7=28%] -[train] checkpoint saved: checkpoints/policy_update125.ot -[update 126] steps/s= 871.3 decisions_total= 2080768 eps_done=10416 recent_reward= 10.135 pg=+0.0483 v=1.5919 ent=0.245 entq=-0.151 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2381s update_s=18.8 collect_s=18.8 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=13% gpu1=23% gpu2=31% gpu3=29% gpu4=0% gpu5=30% gpu6=27% gpu7=0%] -[update 127] steps/s= 870.7 decisions_total= 2097152 eps_done=10519 recent_reward= 11.071 pg=+0.0427 v=0.7848 ent=0.264 entq=-0.206 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2400s update_s=18.8 collect_s=18.8 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=12% gpu2=0% gpu3=0% gpu4=0% gpu5=0% gpu6=0% gpu7=0%] -[update 128] steps/s= 866.4 decisions_total= 2113536 eps_done=10570 recent_reward= 9.975 pg=+0.0708 v=3.6043 ent=0.339 entq=-0.284 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2419s update_s=18.9 collect_s=18.9 train_s=16.1 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=0% gpu2=0% gpu3=0% gpu4=0% gpu5=0% gpu6=0% gpu7=0%] -[update 129] steps/s= 908.3 decisions_total= 2129920 eps_done=10658 recent_reward= 10.754 pg=+0.0036 v=1.4271 ent=0.667 entq=-0.160 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2437s update_s=18.0 collect_s=18.0 train_s=15.8 gpu_mem%=92 min_mean_util%=56 [gpu0=26% gpu1=30% gpu2=26% gpu3=30% gpu4=16% gpu5=26% gpu6=27% gpu7=26%] -[update 130] steps/s= 879.9 decisions_total= 2146304 eps_done=10771 recent_reward= 12.104 pg=+0.0511 v=2.6346 ent=0.292 entq=-0.197 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2456s update_s=18.6 collect_s=18.6 train_s=16.4 gpu_mem%=92 min_mean_util%=56 [gpu0=28% gpu1=19% gpu2=18% gpu3=28% gpu4=25% gpu5=20% gpu6=25% gpu7=27%] -[update 131] steps/s= 895.5 decisions_total= 2162688 eps_done=10817 recent_reward= 11.082 pg=+0.0345 v=1.9389 ent=0.294 entq=-0.226 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2474s update_s=18.3 collect_s=18.2 train_s=16.7 gpu_mem%=92 min_mean_util%=56 [gpu0=27% gpu1=24% gpu2=0% gpu3=12% gpu4=20% gpu5=23% gpu6=32% gpu7=27%] -[update 132] steps/s= 915.7 decisions_total= 2179072 eps_done=10903 recent_reward= 12.500 pg=-0.0309 v=16.9644 ent=0.406 entq=-0.179 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2492s update_s=17.9 collect_s=17.8 train_s=16.5 gpu_mem%=92 min_mean_util%=56 [gpu0=25% gpu1=35% gpu2=0% gpu3=26% gpu4=26% gpu5=29% gpu6=0% gpu7=26%] -[update 133] steps/s= 920.7 decisions_total= 2195456 eps_done=11025 recent_reward= 12.793 pg=+0.0059 v=1.0619 ent=0.678 entq=-0.209 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2510s update_s=17.8 collect_s=17.7 train_s=15.6 gpu_mem%=92 min_mean_util%=56 [gpu0=25% gpu1=27% gpu2=22% gpu3=28% gpu4=27% gpu5=30% gpu6=25% gpu7=26%] -[update 134] steps/s= 878.1 decisions_total= 2211840 eps_done=11067 recent_reward= 11.863 pg=+0.0306 v=1.7676 ent=0.404 entq=-0.284 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2528s update_s=18.7 collect_s=18.6 train_s=15.9 gpu_mem%=92 min_mean_util%=56 [gpu0=29% gpu1=33% gpu2=30% gpu3=26% gpu4=0% gpu5=13% gpu6=26% gpu7=28%] -[update 135] steps/s= 896.3 decisions_total= 2228224 eps_done=11150 recent_reward= 11.661 pg=+0.0052 v=1.4625 ent=0.462 entq=-0.214 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2547s update_s=18.3 collect_s=18.2 train_s=16.8 gpu_mem%=92 min_mean_util%=56 [gpu0=26% gpu1=0% gpu2=24% gpu3=34% gpu4=0% gpu5=0% gpu6=0% gpu7=25%] -[update 136] steps/s= 909.6 decisions_total= 2244608 eps_done=11279 recent_reward= 12.640 pg=+0.0378 v=1.3370 ent=0.570 entq=-0.185 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2565s update_s=18.0 collect_s=18.0 train_s=15.6 gpu_mem%=92 min_mean_util%=56 [gpu0=31% gpu1=35% gpu2=0% gpu3=0% gpu4=0% gpu5=38% gpu6=28% gpu7=29%] -[update 137] steps/s= 913.8 decisions_total= 2260992 eps_done=11318 recent_reward= 12.148 pg=+0.0065 v=2.1001 ent=0.427 entq=-0.244 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2583s update_s=17.9 collect_s=17.9 train_s=16.0 gpu_mem%=92 min_mean_util%=56 [gpu0=26% gpu1=28% gpu2=30% gpu3=19% gpu4=33% gpu5=30% gpu6=29% gpu7=30%] -[update 138] steps/s= 889.3 decisions_total= 2277376 eps_done=11391 recent_reward= 10.451 pg=-0.0002 v=0.4428 ent=0.414 entq=-0.265 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2601s update_s=18.4 collect_s=18.4 train_s=16.0 gpu_mem%=92 min_mean_util%=56 [gpu0=34% gpu1=0% gpu2=0% gpu3=0% gpu4=29% gpu5=19% gpu6=0% gpu7=4%] -[update 139] steps/s= 912.2 decisions_total= 2293760 eps_done=11531 recent_reward= 13.560 pg=+0.0119 v=1.0761 ent=0.403 entq=-0.179 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2619s update_s=18.0 collect_s=17.9 train_s=16.2 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=29% gpu2=13% gpu3=26% gpu4=27% gpu5=11% gpu6=25% gpu7=13%] -[update 140] steps/s= 887.4 decisions_total= 2310144 eps_done=11568 recent_reward= 11.341 pg=+0.0020 v=1.1428 ent=0.308 entq=-0.343 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2637s update_s=18.5 collect_s=18.4 train_s=17.2 gpu_mem%=92 min_mean_util%=57 [gpu0=0% gpu1=0% gpu2=0% gpu3=11% gpu4=0% gpu5=25% gpu6=32% gpu7=34%] -[update 141] steps/s= 900.2 decisions_total= 2326528 eps_done=11636 recent_reward= 11.019 pg=+0.0214 v=0.3894 ent=0.372 entq=-0.262 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2656s update_s=18.2 collect_s=18.2 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=28% gpu1=26% gpu2=0% gpu3=32% gpu4=24% gpu5=33% gpu6=26% gpu7=27%] -[update 142] steps/s= 903.5 decisions_total= 2342912 eps_done=11787 recent_reward= 11.683 pg=+0.0400 v=3.9972 ent=0.746 entq=-0.184 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2674s update_s=18.1 collect_s=18.1 train_s=16.3 gpu_mem%=92 min_mean_util%=57 [gpu0=28% gpu1=0% gpu2=17% gpu3=0% gpu4=0% gpu5=20% gpu6=5% gpu7=26%] -[update 143] steps/s= 898.3 decisions_total= 2359296 eps_done=11815 recent_reward= 11.587 pg=-0.0173 v=1.0271 ent=0.617 entq=-0.229 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2692s update_s=18.2 collect_s=18.2 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=33% gpu1=0% gpu2=0% gpu3=13% gpu4=0% gpu5=29% gpu6=29% gpu7=17%] -[update 144] steps/s= 894.8 decisions_total= 2375680 eps_done=11879 recent_reward= 12.280 pg=-0.0080 v=0.4445 ent=0.285 entq=-0.293 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2710s update_s=18.3 collect_s=18.3 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=12% gpu1=0% gpu2=36% gpu3=0% gpu4=13% gpu5=0% gpu6=0% gpu7=39%] -[update 145] steps/s= 893.0 decisions_total= 2392064 eps_done=12042 recent_reward= 10.472 pg=-0.0104 v=0.8157 ent=0.585 entq=-0.249 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2729s update_s=18.3 collect_s=18.3 train_s=16.6 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=0% gpu2=37% gpu3=0% gpu4=11% gpu5=18% gpu6=1% gpu7=34%] -[update 146] steps/s= 920.7 decisions_total= 2408448 eps_done=12062 recent_reward= 10.696 pg=-0.0928 v=1.5200 ent=0.233 entq=-0.226 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2746s update_s=17.8 collect_s=17.7 train_s=15.6 gpu_mem%=92 min_mean_util%=57 [gpu0=31% gpu1=23% gpu2=25% gpu3=29% gpu4=13% gpu5=29% gpu6=28% gpu7=22%] -[update 147] steps/s= 901.7 decisions_total= 2424832 eps_done=12127 recent_reward= 11.644 pg=-0.0274 v=1.7125 ent=0.307 entq=-0.243 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2765s update_s=18.2 collect_s=18.1 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=14% gpu1=30% gpu2=12% gpu3=0% gpu4=35% gpu5=0% gpu6=29% gpu7=32%] -[update 148] steps/s= 873.2 decisions_total= 2441216 eps_done=12297 recent_reward= 12.184 pg=+0.0216 v=2.6496 ent=0.436 entq=-0.231 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2783s update_s=18.8 collect_s=18.7 train_s=15.9 gpu_mem%=92 min_mean_util%=57 [gpu0=27% gpu1=0% gpu2=0% gpu3=0% gpu4=0% gpu5=0% gpu6=0% gpu7=12%] -[update 149] steps/s= 882.8 decisions_total= 2457600 eps_done=12316 recent_reward= 12.013 pg=-0.0067 v=2.0587 ent=0.464 entq=-0.267 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2802s update_s=18.6 collect_s=18.5 train_s=16.3 gpu_mem%=92 min_mean_util%=57 [gpu0=15% gpu1=17% gpu2=38% gpu3=28% gpu4=37% gpu5=26% gpu6=27% gpu7=26%] -[update 150] steps/s= 898.9 decisions_total= 2473984 eps_done=12370 recent_reward= 12.309 pg=+0.0315 v=0.4984 ent=0.326 entq=-0.295 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2820s update_s=18.2 collect_s=18.2 train_s=15.8 gpu_mem%=92 min_mean_util%=57 [gpu0=30% gpu1=0% gpu2=28% gpu3=13% gpu4=0% gpu5=28% gpu6=29% gpu7=29%] -[train] checkpoint saved: checkpoints/policy_update150.ot -[update 151] steps/s= 896.2 decisions_total= 2490368 eps_done=12466 recent_reward= 12.091 pg=+0.0408 v=0.9745 ent=0.642 entq=-0.242 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2838s update_s=18.3 collect_s=18.2 train_s=16.2 gpu_mem%=92 min_mean_util%=57 [gpu0=17% gpu1=32% gpu2=34% gpu3=33% gpu4=27% gpu5=27% gpu6=31% gpu7=22%] -[update 152] steps/s= 896.0 decisions_total= 2506752 eps_done=12568 recent_reward= 11.571 pg=+0.0720 v=0.8441 ent=0.525 entq=-0.255 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2857s update_s=18.3 collect_s=18.2 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=37% gpu1=0% gpu2=13% gpu3=13% gpu4=32% gpu5=0% gpu6=34% gpu7=26%] -[update 153] steps/s= 903.0 decisions_total= 2523136 eps_done=12619 recent_reward= 13.126 pg=+0.0370 v=0.7843 ent=0.472 entq=-0.331 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2875s update_s=18.1 collect_s=18.1 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=19% gpu1=29% gpu2=14% gpu3=0% gpu4=17% gpu5=10% gpu6=24% gpu7=26%] -[update 154] steps/s= 873.6 decisions_total= 2539520 eps_done=12708 recent_reward= 12.371 pg=+0.0129 v=0.4588 ent=0.761 entq=-0.291 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2894s update_s=18.8 collect_s=18.7 train_s=16.4 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=0% gpu2=27% gpu3=0% gpu4=39% gpu5=27% gpu6=28% gpu7=30%] -[update 155] steps/s= 883.6 decisions_total= 2555904 eps_done=12820 recent_reward= 10.995 pg=+0.0291 v=0.8400 ent=0.596 entq=-0.298 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2912s update_s=18.5 collect_s=18.5 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=41% gpu1=0% gpu2=0% gpu3=0% gpu4=0% gpu5=0% gpu6=0% gpu7=12%] -[update 156] steps/s= 896.4 decisions_total= 2572288 eps_done=12866 recent_reward= 11.868 pg=+0.0003 v=0.6673 ent=0.469 entq=-0.355 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2930s update_s=18.3 collect_s=18.2 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=32% gpu1=0% gpu2=26% gpu3=0% gpu4=31% gpu5=29% gpu6=13% gpu7=30%] -[update 157] steps/s= 898.0 decisions_total= 2588672 eps_done=12953 recent_reward= 12.281 pg=-0.0541 v=0.5386 ent=0.672 entq=-0.327 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2949s update_s=18.2 collect_s=18.2 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=29% gpu1=30% gpu2=0% gpu3=23% gpu4=28% gpu5=27% gpu6=27% gpu7=29%] -[update 158] steps/s= 892.7 decisions_total= 2605056 eps_done=13074 recent_reward= 14.765 pg=-0.0079 v=1.3651 ent=0.350 entq=-0.310 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2967s update_s=18.4 collect_s=18.3 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=30% gpu2=0% gpu3=27% gpu4=0% gpu5=23% gpu6=14% gpu7=30%] -[update 159] steps/s= 902.5 decisions_total= 2621440 eps_done=13116 recent_reward= 12.817 pg=-0.0316 v=0.9022 ent=0.453 entq=-0.361 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=2985s update_s=18.2 collect_s=18.1 train_s=15.5 gpu_mem%=92 min_mean_util%=57 [gpu0=30% gpu1=0% gpu2=0% gpu3=13% gpu4=0% gpu5=0% gpu6=0% gpu7=28%] -[update 160] steps/s= 901.6 decisions_total= 2637824 eps_done=13199 recent_reward= 12.246 pg=+0.0228 v=0.6447 ent=0.341 entq=-0.412 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3003s update_s=18.2 collect_s=18.1 train_s=16.9 gpu_mem%=92 min_mean_util%=57 [gpu0=27% gpu1=23% gpu2=0% gpu3=21% gpu4=26% gpu5=25% gpu6=0% gpu7=26%] -[update 161] steps/s= 934.7 decisions_total= 2654208 eps_done=13328 recent_reward= 12.273 pg=-0.0083 v=4.0213 ent=0.330 entq=-0.401 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3021s update_s=17.5 collect_s=17.5 train_s=16.6 gpu_mem%=92 min_mean_util%=57 [gpu0=12% gpu1=31% gpu2=28% gpu3=41% gpu4=33% gpu5=28% gpu6=28% gpu7=34%] -[update 162] steps/s= 900.2 decisions_total= 2670592 eps_done=13367 recent_reward= 12.403 pg=+0.0492 v=1.3130 ent=0.424 entq=-0.445 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3039s update_s=18.2 collect_s=18.2 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=25% gpu1=39% gpu2=0% gpu3=29% gpu4=0% gpu5=0% gpu6=0% gpu7=27%] -[update 163] steps/s= 900.9 decisions_total= 2686976 eps_done=13440 recent_reward= 12.116 pg=-0.0135 v=0.3100 ent=0.626 entq=-0.428 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3057s update_s=18.2 collect_s=18.1 train_s=15.9 gpu_mem%=92 min_mean_util%=57 [gpu0=25% gpu1=2% gpu2=26% gpu3=26% gpu4=27% gpu5=24% gpu6=28% gpu7=26%] -[update 164] steps/s= 890.6 decisions_total= 2703360 eps_done=13580 recent_reward= 13.358 pg=+0.0820 v=0.9293 ent=0.335 entq=-0.363 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3076s update_s=18.4 collect_s=18.4 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=27% gpu1=29% gpu2=0% gpu3=26% gpu4=29% gpu5=26% gpu6=27% gpu7=25%] -[update 165] steps/s= 899.5 decisions_total= 2719744 eps_done=13617 recent_reward= 13.111 pg=+0.0212 v=0.6901 ent=0.390 entq=-0.537 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3094s update_s=18.2 collect_s=18.2 train_s=16.2 gpu_mem%=92 min_mean_util%=57 [gpu0=23% gpu1=0% gpu2=0% gpu3=0% gpu4=25% gpu5=23% gpu6=11% gpu7=25%] -[update 166] steps/s= 899.2 decisions_total= 2736128 eps_done=13685 recent_reward= 11.686 pg=+0.0668 v=0.6906 ent=0.310 entq=-0.413 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3112s update_s=18.2 collect_s=18.2 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=22% gpu1=28% gpu2=26% gpu3=29% gpu4=20% gpu5=27% gpu6=29% gpu7=35%] -[update 167] steps/s= 913.5 decisions_total= 2752512 eps_done=13835 recent_reward= 12.603 pg=-0.0064 v=0.7260 ent=0.402 entq=-0.532 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3130s update_s=17.9 collect_s=17.9 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=25% gpu2=27% gpu3=26% gpu4=27% gpu5=36% gpu6=26% gpu7=26%] -[update 168] steps/s= 880.3 decisions_total= 2768896 eps_done=13863 recent_reward= 11.750 pg=-0.0076 v=1.1415 ent=0.461 entq=-0.608 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3149s update_s=18.6 collect_s=18.6 train_s=16.6 gpu_mem%=92 min_mean_util%=57 [gpu0=25% gpu1=28% gpu2=29% gpu3=0% gpu4=25% gpu5=27% gpu6=27% gpu7=26%] -[update 169] steps/s= 911.0 decisions_total= 2785280 eps_done=13928 recent_reward= 13.797 pg=+0.0019 v=0.6977 ent=0.284 entq=-0.545 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3167s update_s=18.0 collect_s=17.9 train_s=15.9 gpu_mem%=92 min_mean_util%=57 [gpu0=27% gpu1=34% gpu2=25% gpu3=25% gpu4=27% gpu5=23% gpu6=29% gpu7=31%] -[update 170] steps/s= 909.1 decisions_total= 2801664 eps_done=14090 recent_reward= 12.409 pg=-0.0018 v=0.8157 ent=0.379 entq=-0.508 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3185s update_s=18.0 collect_s=18.0 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=31% gpu2=26% gpu3=12% gpu4=23% gpu5=26% gpu6=25% gpu7=28%] -[update 171] steps/s= 917.0 decisions_total= 2818048 eps_done=14110 recent_reward= 12.829 pg=+0.0069 v=1.7222 ent=0.435 entq=-0.607 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3203s update_s=17.9 collect_s=17.8 train_s=16.2 gpu_mem%=92 min_mean_util%=57 [gpu0=27% gpu1=27% gpu2=28% gpu3=28% gpu4=29% gpu5=32% gpu6=29% gpu7=33%] -[update 172] steps/s= 885.0 decisions_total= 2834432 eps_done=14178 recent_reward= 11.272 pg=+0.0134 v=0.9034 ent=0.460 entq=-0.624 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3221s update_s=18.5 collect_s=18.5 train_s=15.9 gpu_mem%=92 min_mean_util%=57 [gpu0=0% gpu1=0% gpu2=0% gpu3=0% gpu4=28% gpu5=0% gpu6=0% gpu7=0%] -[update 173] steps/s= 919.5 decisions_total= 2850816 eps_done=14345 recent_reward= 12.761 pg=-0.0012 v=1.0982 ent=0.500 entq=-0.453 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3239s update_s=17.8 collect_s=17.8 train_s=15.6 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=22% gpu2=27% gpu3=26% gpu4=24% gpu5=25% gpu6=17% gpu7=23%] -[update 174] steps/s= 898.5 decisions_total= 2867200 eps_done=14364 recent_reward= 12.563 pg=-0.0421 v=1.6822 ent=0.335 entq=-0.531 ecoef=0.0097 stage=0 lr=3.00e-4 elapsed=3257s update_s=18.2 collect_s=18.2 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=3% gpu1=24% gpu2=0% gpu3=36% gpu4=12% gpu5=0% gpu6=0% gpu7=28%] -[update 175] steps/s= 921.5 decisions_total= 2883584 eps_done=14421 recent_reward= 12.300 pg=-0.0188 v=0.2347 ent=0.220 entq=-0.454 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3275s update_s=17.8 collect_s=17.7 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=17% gpu1=28% gpu2=25% gpu3=24% gpu4=24% gpu5=26% gpu6=15% gpu7=25%] -[train] checkpoint saved: checkpoints/policy_update175.ot -[update 176] steps/s= 919.5 decisions_total= 2899968 eps_done=14516 recent_reward= 13.818 pg=-0.0269 v=1.4778 ent=0.312 entq=-0.696 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3293s update_s=17.8 collect_s=17.8 train_s=16.3 gpu_mem%=92 min_mean_util%=57 [gpu0=30% gpu1=32% gpu2=10% gpu3=27% gpu4=29% gpu5=28% gpu6=0% gpu7=25%] -[update 177] steps/s= 907.1 decisions_total= 2916352 eps_done=14616 recent_reward= 13.286 pg=+0.0414 v=1.3076 ent=0.234 entq=-0.544 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3311s update_s=18.1 collect_s=18.0 train_s=16.3 gpu_mem%=92 min_mean_util%=57 [gpu0=28% gpu1=26% gpu2=0% gpu3=32% gpu4=24% gpu5=0% gpu6=36% gpu7=25%] -[update 178] steps/s= 904.8 decisions_total= 2932736 eps_done=14669 recent_reward= 13.530 pg=+0.0120 v=0.9107 ent=0.225 entq=-0.617 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3329s update_s=18.1 collect_s=18.1 train_s=15.9 gpu_mem%=92 min_mean_util%=57 [gpu0=31% gpu1=16% gpu2=32% gpu3=27% gpu4=32% gpu5=0% gpu6=21% gpu7=28%] -[update 179] steps/s= 894.1 decisions_total= 2949120 eps_done=14759 recent_reward= 12.927 pg=+0.0069 v=0.6857 ent=0.229 entq=-0.672 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3347s update_s=18.3 collect_s=18.3 train_s=16.5 gpu_mem%=92 min_mean_util%=57 [gpu0=17% gpu1=27% gpu2=25% gpu3=24% gpu4=25% gpu5=28% gpu6=0% gpu7=28%] -[update 180] steps/s= 904.3 decisions_total= 2965504 eps_done=14869 recent_reward= 13.611 pg=-0.0329 v=1.4909 ent=0.198 entq=-0.635 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3365s update_s=18.1 collect_s=18.1 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=30% gpu1=26% gpu2=11% gpu3=11% gpu4=29% gpu5=32% gpu6=29% gpu7=0%] -[update 181] steps/s= 900.4 decisions_total= 2981888 eps_done=14916 recent_reward= 12.328 pg=+0.0431 v=1.0894 ent=0.252 entq=-0.651 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3384s update_s=18.2 collect_s=18.1 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=25% gpu2=31% gpu3=29% gpu4=33% gpu5=18% gpu6=26% gpu7=23%] -[update 182] steps/s= 887.6 decisions_total= 2998272 eps_done=15003 recent_reward= 12.524 pg=-0.0296 v=0.8555 ent=0.251 entq=-0.604 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3402s update_s=18.5 collect_s=18.4 train_s=16.4 gpu_mem%=92 min_mean_util%=57 [gpu0=25% gpu1=28% gpu2=29% gpu3=27% gpu4=20% gpu5=27% gpu6=22% gpu7=26%] -[update 183] steps/s= 914.0 decisions_total= 3014656 eps_done=15123 recent_reward= 13.126 pg=-0.0292 v=0.7570 ent=0.321 entq=-0.607 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3420s update_s=17.9 collect_s=17.9 train_s=15.8 gpu_mem%=92 min_mean_util%=57 [gpu0=22% gpu1=28% gpu2=30% gpu3=25% gpu4=15% gpu5=25% gpu6=26% gpu7=25%] -[update 184] steps/s= 921.5 decisions_total= 3031040 eps_done=15166 recent_reward= 12.593 pg=-0.0600 v=1.0633 ent=0.301 entq=-0.637 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3438s update_s=17.8 collect_s=17.7 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=29% gpu1=16% gpu2=27% gpu3=0% gpu4=27% gpu5=26% gpu6=29% gpu7=27%] -[update 185] steps/s= 920.1 decisions_total= 3047424 eps_done=15249 recent_reward= 11.695 pg=+0.0912 v=0.7731 ent=0.418 entq=-0.620 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3455s update_s=17.8 collect_s=17.8 train_s=17.4 gpu_mem%=92 min_mean_util%=57 [gpu0=22% gpu1=2% gpu2=0% gpu3=10% gpu4=30% gpu5=31% gpu6=23% gpu7=25%] -[update 186] steps/s= 895.7 decisions_total= 3063808 eps_done=15377 recent_reward= 12.748 pg=-0.0150 v=1.3584 ent=0.306 entq=-0.609 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3474s update_s=18.3 collect_s=18.2 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=29% gpu1=19% gpu2=27% gpu3=15% gpu4=30% gpu5=26% gpu6=25% gpu7=14%] -[update 187] steps/s= 870.5 decisions_total= 3080192 eps_done=15415 recent_reward= 13.153 pg=-0.0415 v=0.8847 ent=0.416 entq=-0.618 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3493s update_s=18.8 collect_s=18.8 train_s=16.7 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=26% gpu2=27% gpu3=27% gpu4=28% gpu5=30% gpu6=27% gpu7=28%] -[update 188] steps/s= 928.0 decisions_total= 3096576 eps_done=15490 recent_reward= 12.543 pg=-0.0287 v=0.9971 ent=0.460 entq=-0.537 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3510s update_s=17.7 collect_s=17.6 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=25% gpu1=22% gpu2=23% gpu3=28% gpu4=26% gpu5=26% gpu6=26% gpu7=25%] -[update 189] steps/s= 913.3 decisions_total= 3112960 eps_done=15629 recent_reward= 13.360 pg=-0.0584 v=0.4916 ent=0.416 entq=-0.544 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3528s update_s=17.9 collect_s=17.9 train_s=15.9 gpu_mem%=92 min_mean_util%=57 [gpu0=28% gpu1=28% gpu2=26% gpu3=23% gpu4=30% gpu5=27% gpu6=27% gpu7=27%] -[update 190] steps/s= 894.6 decisions_total= 3129344 eps_done=15665 recent_reward= 12.089 pg=+0.0870 v=0.9965 ent=0.429 entq=-0.536 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3547s update_s=18.3 collect_s=18.3 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=29% gpu1=20% gpu2=0% gpu3=0% gpu4=0% gpu5=29% gpu6=29% gpu7=29%] -[update 191] steps/s= 922.6 decisions_total= 3145728 eps_done=15735 recent_reward= 12.636 pg=+0.0107 v=1.1614 ent=0.277 entq=-0.507 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3564s update_s=17.8 collect_s=17.7 train_s=15.5 gpu_mem%=92 min_mean_util%=57 [gpu0=27% gpu1=33% gpu2=24% gpu3=26% gpu4=31% gpu5=27% gpu6=26% gpu7=25%] -[update 192] steps/s= 892.0 decisions_total= 3162112 eps_done=15884 recent_reward= 12.777 pg=+0.0215 v=1.0759 ent=0.165 entq=-0.445 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3583s update_s=18.4 collect_s=18.3 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=38% gpu1=0% gpu2=0% gpu3=0% gpu4=0% gpu5=0% gpu6=26% gpu7=18%] -[update 193] steps/s= 902.0 decisions_total= 3178496 eps_done=15911 recent_reward= 12.577 pg=+0.0422 v=2.0538 ent=0.283 entq=-0.520 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3601s update_s=18.2 collect_s=18.1 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=24% gpu1=28% gpu2=31% gpu3=24% gpu4=31% gpu5=28% gpu6=30% gpu7=25%] -[update 194] steps/s= 897.1 decisions_total= 3194880 eps_done=15978 recent_reward= 13.988 pg=+0.0534 v=1.0551 ent=0.388 entq=-0.454 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3619s update_s=18.3 collect_s=18.2 train_s=15.7 gpu_mem%=92 min_mean_util%=57 [gpu0=31% gpu1=0% gpu2=16% gpu3=29% gpu4=30% gpu5=33% gpu6=28% gpu7=29%] -[update 195] steps/s= 904.0 decisions_total= 3211264 eps_done=16139 recent_reward= 13.116 pg=-0.0405 v=1.4474 ent=0.457 entq=-0.467 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3637s update_s=18.1 collect_s=18.1 train_s=15.9 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=13% gpu2=28% gpu3=31% gpu4=36% gpu5=32% gpu6=29% gpu7=11%] -[update 196] steps/s= 899.5 decisions_total= 3227648 eps_done=16159 recent_reward= 13.321 pg=+0.0271 v=1.0106 ent=0.174 entq=-0.319 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3655s update_s=18.2 collect_s=18.2 train_s=16.5 gpu_mem%=92 min_mean_util%=57 [gpu0=13% gpu1=31% gpu2=30% gpu3=30% gpu4=27% gpu5=20% gpu6=28% gpu7=25%] -[update 197] steps/s= 899.2 decisions_total= 3244032 eps_done=16226 recent_reward= 14.090 pg=-0.0426 v=1.0650 ent=0.131 entq=-0.503 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3674s update_s=18.2 collect_s=18.2 train_s=16.3 gpu_mem%=92 min_mean_util%=57 [gpu0=17% gpu1=26% gpu2=37% gpu3=26% gpu4=0% gpu5=17% gpu6=25% gpu7=31%] -[update 198] steps/s= 883.1 decisions_total= 3260416 eps_done=16394 recent_reward= 11.398 pg=-0.0504 v=1.9483 ent=0.367 entq=-0.498 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3692s update_s=18.6 collect_s=18.5 train_s=17.0 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=27% gpu2=0% gpu3=26% gpu4=27% gpu5=25% gpu6=26% gpu7=26%] -[update 199] steps/s= 913.8 decisions_total= 3276800 eps_done=16413 recent_reward= 11.162 pg=-0.0559 v=2.2105 ent=0.441 entq=-0.461 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3710s update_s=17.9 collect_s=17.9 train_s=16.9 gpu_mem%=92 min_mean_util%=57 [gpu0=32% gpu1=25% gpu2=28% gpu3=27% gpu4=21% gpu5=24% gpu6=23% gpu7=26%] -[update 200] steps/s= 905.3 decisions_total= 3293184 eps_done=16469 recent_reward= 12.163 pg=-0.0018 v=0.8120 ent=0.204 entq=-0.484 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3728s update_s=18.1 collect_s=18.1 train_s=15.5 gpu_mem%=92 min_mean_util%=57 [gpu0=36% gpu1=0% gpu2=32% gpu3=29% gpu4=31% gpu5=14% gpu6=12% gpu7=28%] -[train] checkpoint saved: checkpoints/policy_update200.ot -[update 201] steps/s= 902.7 decisions_total= 3309568 eps_done=16565 recent_reward= 12.997 pg=-0.0122 v=0.8939 ent=0.214 entq=-0.475 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3746s update_s=18.1 collect_s=18.1 train_s=16.3 gpu_mem%=92 min_mean_util%=57 [gpu0=0% gpu1=0% gpu2=25% gpu3=31% gpu4=11% gpu5=23% gpu6=26% gpu7=0%] -[update 202] steps/s= 907.6 decisions_total= 3325952 eps_done=16665 recent_reward= 13.392 pg=+0.0383 v=0.5179 ent=0.262 entq=-0.419 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3764s update_s=18.1 collect_s=18.0 train_s=16.1 gpu_mem%=92 min_mean_util%=57 [gpu0=26% gpu1=13% gpu2=29% gpu3=18% gpu4=30% gpu5=36% gpu6=26% gpu7=25%] -[update 203] steps/s= 901.3 decisions_total= 3342336 eps_done=16717 recent_reward= 13.606 pg=+0.0136 v=1.1313 ent=0.201 entq=-0.547 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3783s update_s=18.2 collect_s=18.1 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=30% gpu1=20% gpu2=31% gpu3=27% gpu4=18% gpu5=29% gpu6=26% gpu7=19%] -[update 204] steps/s= 893.4 decisions_total= 3358720 eps_done=16807 recent_reward= 13.655 pg=-0.0693 v=0.4960 ent=0.204 entq=-0.525 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3801s update_s=18.3 collect_s=18.3 train_s=15.8 gpu_mem%=92 min_mean_util%=57 [gpu0=30% gpu1=32% gpu2=20% gpu3=32% gpu4=34% gpu5=28% gpu6=27% gpu7=30%] -[update 205] steps/s= 908.4 decisions_total= 3375104 eps_done=16917 recent_reward= 12.325 pg=-0.0135 v=1.0432 ent=0.272 entq=-0.476 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3819s update_s=18.0 collect_s=18.0 train_s=16.6 gpu_mem%=92 min_mean_util%=57 [gpu0=0% gpu1=6% gpu2=25% gpu3=24% gpu4=39% gpu5=0% gpu6=25% gpu7=29%] -[update 206] steps/s= 897.5 decisions_total= 3391488 eps_done=16964 recent_reward= 12.865 pg=+0.0242 v=0.9418 ent=0.397 entq=-0.487 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3837s update_s=18.3 collect_s=18.2 train_s=17.0 gpu_mem%=92 min_mean_util%=57 [gpu0=0% gpu1=24% gpu2=25% gpu3=0% gpu4=0% gpu5=0% gpu6=11% gpu7=25%] -[update 207] steps/s= 896.4 decisions_total= 3407872 eps_done=17051 recent_reward= 13.629 pg=-0.0272 v=0.7444 ent=0.341 entq=-0.422 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3856s update_s=18.3 collect_s=18.2 train_s=16.9 gpu_mem%=92 min_mean_util%=57 [gpu0=15% gpu1=27% gpu2=13% gpu3=0% gpu4=12% gpu5=26% gpu6=31% gpu7=29%] -[update 208] steps/s= 899.1 decisions_total= 3424256 eps_done=17171 recent_reward= 13.650 pg=-0.0713 v=1.7546 ent=0.325 entq=-0.547 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3874s update_s=18.2 collect_s=18.2 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=27% gpu1=27% gpu2=28% gpu3=26% gpu4=29% gpu5=31% gpu6=27% gpu7=21%] -[update 209] steps/s= 888.7 decisions_total= 3440640 eps_done=17214 recent_reward= 14.003 pg=-0.0177 v=1.8682 ent=0.283 entq=-0.506 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3892s update_s=18.4 collect_s=18.4 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=27% gpu1=34% gpu2=24% gpu3=30% gpu4=25% gpu5=31% gpu6=25% gpu7=26%] -[update 210] steps/s= 902.7 decisions_total= 3457024 eps_done=17297 recent_reward= 14.029 pg=-0.0253 v=0.5032 ent=0.350 entq=-0.481 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3910s update_s=18.2 collect_s=18.1 train_s=16.2 gpu_mem%=92 min_mean_util%=57 [gpu0=25% gpu1=26% gpu2=26% gpu3=23% gpu4=26% gpu5=26% gpu6=27% gpu7=0%] -[update 211] steps/s= 906.8 decisions_total= 3473408 eps_done=17425 recent_reward= 12.726 pg=-0.0038 v=0.5749 ent=0.231 entq=-0.512 ecoef=0.0096 stage=0 lr=3.00e-4 elapsed=3928s update_s=18.1 collect_s=18.0 train_s=16.0 gpu_mem%=92 min_mean_util%=57 [gpu0=28% gpu1=12% gpu2=33% gpu3=26% gpu4=30% gpu5=0% gpu6=0% gpu7=28%] diff --git a/ppo_v9/policy_update10.safetensors b/ppo_v9/policy_update10.safetensors deleted file mode 100644 index 026b67676a7e5f52e724031892bc4e987db70837..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update10.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4a4f1568d172378b34d0deba07e7a9f82435b088c5e060eaa1ff4b54b7cb1b86 -size 48494336 diff --git a/ppo_v9/policy_update10.state.json b/ppo_v9/policy_update10.state.json deleted file mode 100644 index c9ee6eac76b43953d04988e0b066cdbaee8671dc..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update10.state.json +++ /dev/null @@ -1,67 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 11, - "stage": 0, - "ent_scale": 1.0, - "lr_now": 0.00025, - "total_env_steps": 42240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update100.safetensors b/ppo_v9/policy_update100.safetensors deleted file mode 100644 index 21460572f5194e3e25ca851457a7a1948d18d065..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update100.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fea8808c5398121b1d493d346201aa5e69f31b62d7fdefc0c9cbd7e9df32f6e4 -size 48494336 diff --git a/ppo_v9/policy_update100.state.json b/ppo_v9/policy_update100.state.json deleted file mode 100644 index 1fbf6f902f1fdea3d85ed2da59e9630982db1811..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update100.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 101, - "stage": 0, - "ent_scale": 1.0, - "lr_now": 0.00025, - "total_env_steps": 387840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 1.0, - 1.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1000.safetensors b/ppo_v9/policy_update1000.safetensors deleted file mode 100644 index e7c034fcf1c3e090f7be44216cdecb7563ad5fbf..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1000.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:61500c3554c416150e7bee5bdc7a2764b2eb8f82fb259b3441b96fcfa9adbb5f -size 48494336 diff --git a/ppo_v9/policy_update1000.state.json b/ppo_v9/policy_update1000.state.json deleted file mode 100644 index 1a7025fe9e485d723fec138d3c7bffdc4a4bb087..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1000.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1001, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 3843840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1005.safetensors b/ppo_v9/policy_update1005.safetensors deleted file mode 100644 index 3cb869f5704fbe063ce07b2fec0729efd691af70..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1005.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cf6ab98477e6ee846e6f948aa017143627834ad384cad9bf183a37f251b4a160 -size 48494336 diff --git a/ppo_v9/policy_update1005.state.json b/ppo_v9/policy_update1005.state.json deleted file mode 100644 index 95b360bdedb7354e6e74a50157447a25e733dd82..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1005.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1006, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 3863040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1010.safetensors b/ppo_v9/policy_update1010.safetensors deleted file mode 100644 index 96cb74be5f7ecc1487d2b6f8a2657707443ce576..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1010.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5b013cbd5dd72363f3dd4a18c80d2fb85181ac47e4b1ca2ac96b07b11dfe0698 -size 48494336 diff --git a/ppo_v9/policy_update1010.state.json b/ppo_v9/policy_update1010.state.json deleted file mode 100644 index ddc79fce22b3b516cf8595d27df4e3f9d8013a74..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1010.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1011, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 3882240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1015.safetensors b/ppo_v9/policy_update1015.safetensors deleted file mode 100644 index 18ebe3541ffb8dc7b673496276d96ccf13b36236..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1015.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:aa3fcd077f0c896031092cb7066d88460c57cf9d1a4cdf887528a38dbc03ebb6 -size 48494336 diff --git a/ppo_v9/policy_update1015.state.json b/ppo_v9/policy_update1015.state.json deleted file mode 100644 index 406b7a8bd76326b45717b827bc4979eae2f83f10..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1015.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1016, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 3901440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1020.safetensors b/ppo_v9/policy_update1020.safetensors deleted file mode 100644 index e1932aaadce6dfc9570cd300a6067bc82d988eee..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1020.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:14a8e04295e967e31195492ff6560ff9c276df68520c666bd393ea0f91f03dd7 -size 48494336 diff --git a/ppo_v9/policy_update1020.state.json b/ppo_v9/policy_update1020.state.json deleted file mode 100644 index 36925e1dde0eca13cd5d15fae71a3c2d99d85ef2..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1020.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1021, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 3920640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1025.safetensors b/ppo_v9/policy_update1025.safetensors deleted file mode 100644 index 05bc4d5daf1cbe65478144d4e68fe3090417dc9a..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1025.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0768bcc4fb190e3fc072c32bd18933428222b8ba2c05e5b90c617daa125e826b -size 48494336 diff --git a/ppo_v9/policy_update1025.state.json b/ppo_v9/policy_update1025.state.json deleted file mode 100644 index 8493555ad345dedec1f69518b2e94a90caa1dc77..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1025.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1026, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 3939840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1030.safetensors b/ppo_v9/policy_update1030.safetensors deleted file mode 100644 index 162f6667667f9c40c51d4ebfc69911b35bd21b0b..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1030.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9d196fd68ade2a3afc7d7bce5a0e986eec37bdc25d1fa71422c5ff6acc5b91d4 -size 48494336 diff --git a/ppo_v9/policy_update1030.state.json b/ppo_v9/policy_update1030.state.json deleted file mode 100644 index 14b959c1b3a51238a9dbe0d65e8f5b9ed5c67200..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1030.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1031, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 3959040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1035.safetensors b/ppo_v9/policy_update1035.safetensors deleted file mode 100644 index fc5640a2a4f6a0cd10be34b2a28bb370cd674baf..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1035.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7814f6c799a0703c38c45167b3e9cdb30b65af0ac5f3f297786be8f2df299b01 -size 48494336 diff --git a/ppo_v9/policy_update1035.state.json b/ppo_v9/policy_update1035.state.json deleted file mode 100644 index d56d4ec0822e6b95429d6d7531374701c149c20f..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1035.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1036, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 3978240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1040.safetensors b/ppo_v9/policy_update1040.safetensors deleted file mode 100644 index ac52799425452176f7e371e652ffe54274f73918..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1040.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f04ad62e85d093f98694a667b7a636cbaad333c1a5e26824d98642145283568b -size 48494336 diff --git a/ppo_v9/policy_update1040.state.json b/ppo_v9/policy_update1040.state.json deleted file mode 100644 index fa337acf8da97dd1ad0b0cf3e1aff0a6e5875de4..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1040.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1041, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 3997440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1045.safetensors b/ppo_v9/policy_update1045.safetensors deleted file mode 100644 index 8d406ac63ac0661cb2e8e73c1360c2ad7340b00c..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1045.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c46a7f154614e0fe119800a8a224259614b90a68c9a752b1a48a451893a099c2 -size 48494336 diff --git a/ppo_v9/policy_update1045.state.json b/ppo_v9/policy_update1045.state.json deleted file mode 100644 index 8f5618b767ee6012d25158088c3f59c07ba7ca6a..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1045.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1046, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4016640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update105.safetensors b/ppo_v9/policy_update105.safetensors deleted file mode 100644 index 92df8031ce6672974ea1740a825aa30ab3f7dea3..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update105.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:32cb1b1e859a3880f18d9f745f44c0582fd2d828c6dbbd41ce50c7f5d2d7a56f -size 48494336 diff --git a/ppo_v9/policy_update105.state.json b/ppo_v9/policy_update105.state.json deleted file mode 100644 index fc80dc6c29ff08f6542fb892b09f80eec7d2c597..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update105.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 106, - "stage": 0, - "ent_scale": 1.0, - "lr_now": 0.00025, - "total_env_steps": 407040, - "recent_wins": [ - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1050.safetensors b/ppo_v9/policy_update1050.safetensors deleted file mode 100644 index 5a9593d4106dce79fe38c78fa4577d084cabb458..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1050.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:705fa89a5af1bf7c504450be2cd71c890de418f3bf860391a2d914b66e574a20 -size 48494336 diff --git a/ppo_v9/policy_update1050.state.json b/ppo_v9/policy_update1050.state.json deleted file mode 100644 index 3015678b4f36b27496b0cac8809837c25c26e72f..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1050.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1051, - "stage": 2, - "ent_scale": 2.1970000000000005, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4035840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1055.safetensors b/ppo_v9/policy_update1055.safetensors deleted file mode 100644 index 2141f6096b1d7f3ffb4f0700b52e5b720e33ffa2..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1055.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:530ab959468c2c1acf36e4ad045e90fe84a5d01413d7f767356bce2f3456a3de -size 48494336 diff --git a/ppo_v9/policy_update1055.state.json b/ppo_v9/policy_update1055.state.json deleted file mode 100644 index 0ddc7fc606ad26c698b48703258c5fc35069f7af..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1055.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1056, - "stage": 2, - "ent_scale": 3.207368534715474, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4055040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1060.safetensors b/ppo_v9/policy_update1060.safetensors deleted file mode 100644 index 8841a0159a09703e39d50b2a9734e1c62e46ee08..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1060.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:065cf6e2d42573fe2148ace933c205e044c8b5465988f8de60ee8baf8be12082 -size 48494336 diff --git a/ppo_v9/policy_update1060.state.json b/ppo_v9/policy_update1060.state.json deleted file mode 100644 index b9d975e53d8f3d6803f4c5ffd5a968cdb0b8962e..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1060.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1061, - "stage": 2, - "ent_scale": 1.3241592213316957, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4074240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1065.safetensors b/ppo_v9/policy_update1065.safetensors deleted file mode 100644 index 2bff5454a346f2a4f85a02cf07fb051d1a89285e..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1065.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:99f62ede123155383d11db97e42b9d3cc98bed5c23ae72cb67be2cb047ff3270 -size 48494336 diff --git a/ppo_v9/policy_update1065.state.json b/ppo_v9/policy_update1065.state.json deleted file mode 100644 index 0b934801c3881c996a7769d02b4cd40726877e02..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1065.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1066, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4093440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1070.safetensors b/ppo_v9/policy_update1070.safetensors deleted file mode 100644 index 3717d2ffc8faaa6beec3124bd4b2fe06a8e48ef7..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1070.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c24f496fc5681006a90f5610e7ff9cb71a582c40d9e50ad70fa89b927021bbae -size 48494336 diff --git a/ppo_v9/policy_update1070.state.json b/ppo_v9/policy_update1070.state.json deleted file mode 100644 index 3de144a59d87b4464c4615c6a05bebe9a9c726f6..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1070.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1071, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4112640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1075.safetensors b/ppo_v9/policy_update1075.safetensors deleted file mode 100644 index 00cf7ac79d63d3eafe11cfacd22f67fcab2c87d9..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1075.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ece9a6ccfc2834cbe690443ba20c20d77adeaa0e028180a8bce2a7d5f71c8e06 -size 48494336 diff --git a/ppo_v9/policy_update1075.state.json b/ppo_v9/policy_update1075.state.json deleted file mode 100644 index 5e6721771fde8386bbee50796bf992b07b7ee172..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1075.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1076, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4131840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1080.safetensors b/ppo_v9/policy_update1080.safetensors deleted file mode 100644 index 529483f6c64d601d186e52c8b630a43867d5ec66..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1080.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2a165c2a81979ac8d4fd9e7d03335cfb47f5ca1e25f8273518b59d230a7358e9 -size 48494336 diff --git a/ppo_v9/policy_update1080.state.json b/ppo_v9/policy_update1080.state.json deleted file mode 100644 index 7dc8970b382b30942366e2b1cc108e54c4f0cf3f..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1080.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1081, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4151040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1085.safetensors b/ppo_v9/policy_update1085.safetensors deleted file mode 100644 index faab95f407835999347094a8bcd1a0e80ce9cba3..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1085.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b8b98226abc1f078356806dca570167206d89a779df66ad094ee180e89246eb4 -size 48494336 diff --git a/ppo_v9/policy_update1085.state.json b/ppo_v9/policy_update1085.state.json deleted file mode 100644 index dbff9d2e12e56a8690f5cad3250dfb9f4082183a..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1085.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1086, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4170240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1090.safetensors b/ppo_v9/policy_update1090.safetensors deleted file mode 100644 index 284b8b4090208194509d2b83fae157dd0e7a4bd8..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1090.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b766caf34cdc94137bf801f95c516f58ed55e9c1cad6a95b45d2449b9c38f4dc -size 48494336 diff --git a/ppo_v9/policy_update1090.state.json b/ppo_v9/policy_update1090.state.json deleted file mode 100644 index 15ac18cd634af2acb87031f8ddbb31aa15faeb80..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1090.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1091, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4189440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1095.safetensors b/ppo_v9/policy_update1095.safetensors deleted file mode 100644 index 313887e5e85233986830fbe14c847eae2dbc47d3..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1095.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c56434a7b7862f0ce00cb74d2fbdb554d78736030f067950eacfd7fe60b7391f -size 48494336 diff --git a/ppo_v9/policy_update1095.state.json b/ppo_v9/policy_update1095.state.json deleted file mode 100644 index 437911fdc67b38fb90473121d0c83185cd8ac000..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1095.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1096, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4208640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update110.safetensors b/ppo_v9/policy_update110.safetensors deleted file mode 100644 index e5d4ca3ddf5b90fcf6c7a2bc6338e50e7c718242..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update110.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:62b18f4d36c8b6f665e887656787df5b4e55702f24bd122d75a9a47504ae8b1c -size 48494336 diff --git a/ppo_v9/policy_update110.state.json b/ppo_v9/policy_update110.state.json deleted file mode 100644 index 5d85183a4bb1508533b4fc0dae64c9f457fa1bca..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update110.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 111, - "stage": 0, - "ent_scale": 1.0, - "lr_now": 0.00025, - "total_env_steps": 426240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1100.safetensors b/ppo_v9/policy_update1100.safetensors deleted file mode 100644 index 3e986622983e98ad3bbc58cde9d00dbf77e11332..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1100.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3e1e807ab34da14effa0e682f77c5e0e5d3ec5e7d5885e571d96e4dd84153695 -size 48494336 diff --git a/ppo_v9/policy_update1100.state.json b/ppo_v9/policy_update1100.state.json deleted file mode 100644 index 22866f2a90526e5f10a385a6dcf3353167d2d0fe..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1100.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1101, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4227840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1105.safetensors b/ppo_v9/policy_update1105.safetensors deleted file mode 100644 index b4e14a1c1aaa4b3b0d3882538061fe9ad35221e9..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1105.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:eb5a295769e27b2cb6eb00e3ba7e05eaaa8f5dec25e0181158c54fc70a1db9d4 -size 48494336 diff --git a/ppo_v9/policy_update1105.state.json b/ppo_v9/policy_update1105.state.json deleted file mode 100644 index 2c535d9fd7cde3fbcc9a5fded7d1113847dbd2dc..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1105.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1106, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4247040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1110.safetensors b/ppo_v9/policy_update1110.safetensors deleted file mode 100644 index 7fade05a767fbeb6f989a93294da2f7155abb229..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1110.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4c3f674b069d2aafe1dd65ea0a635b8cd1497a3b3a783addb150e923dae6d486 -size 48494336 diff --git a/ppo_v9/policy_update1110.state.json b/ppo_v9/policy_update1110.state.json deleted file mode 100644 index 8e0d574d923284597ba61df3372af4fa25532ad4..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1110.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1111, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4266240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1115.safetensors b/ppo_v9/policy_update1115.safetensors deleted file mode 100644 index 60f46a85d2627d34c4606627204b032ad69314a8..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1115.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e0b1dd678bf0763fe4bfce35754e5c14ba80959b0817705f21ca6afd39ddff09 -size 48494336 diff --git a/ppo_v9/policy_update1115.state.json b/ppo_v9/policy_update1115.state.json deleted file mode 100644 index 8d7cdd85b9fe45f81586e71c7827dc43894f98ea..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1115.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1116, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4285440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1120.safetensors b/ppo_v9/policy_update1120.safetensors deleted file mode 100644 index c062d9dc6251aa96d2a6873cac6a0ba2c96a3c0c..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1120.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bebad78cda863f65175bb7653dbc241c98e42e90499b30a8f213921dfe134a77 -size 48494336 diff --git a/ppo_v9/policy_update1120.state.json b/ppo_v9/policy_update1120.state.json deleted file mode 100644 index 4b9dbc6b9d4c2f86698aeefd8178735a61124289..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1120.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1121, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4304640, - "recent_wins": [ - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1125.safetensors b/ppo_v9/policy_update1125.safetensors deleted file mode 100644 index fa3be9d9f4144d9a293ef39fa08ae36bea11ad7d..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1125.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:94280b714a561e94404ed910a838041201bc6c1a013035707ab8cd738e904157 -size 48494336 diff --git a/ppo_v9/policy_update1125.state.json b/ppo_v9/policy_update1125.state.json deleted file mode 100644 index 8642ad34d3582708d02cc2cfa13707542a691f8d..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1125.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1126, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4323840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1130.safetensors b/ppo_v9/policy_update1130.safetensors deleted file mode 100644 index 2671279893acd0a62b6f1784a0ee9111a4fa3f43..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1130.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:42c847b2fb5c7d54ebe36fef74898127607479a65604c473c6bde4d8729f0008 -size 48494336 diff --git a/ppo_v9/policy_update1130.state.json b/ppo_v9/policy_update1130.state.json deleted file mode 100644 index 70c3e98d3f98c1f74d94592aa016ae2d58ead289..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1130.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1131, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4343040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1135.safetensors b/ppo_v9/policy_update1135.safetensors deleted file mode 100644 index 146682e96a2a11fdf8c5337e725a80db31d003d2..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1135.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:912b5d39c259f75df960f891f9539a5fc4ebcaa04f53709b9c59057b7ae7f10c -size 48494336 diff --git a/ppo_v9/policy_update1135.state.json b/ppo_v9/policy_update1135.state.json deleted file mode 100644 index 77b39f59c6198b66fc9a8be95be820904cfa37c3..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1135.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1136, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4362240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1140.safetensors b/ppo_v9/policy_update1140.safetensors deleted file mode 100644 index d2f33538a02325ce1715e3f6d6e441946eae52f1..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1140.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f931910dbf25f99e0ebc4d2aa0531e7444b7d87d97b125c6081a15f4c7770668 -size 48494336 diff --git a/ppo_v9/policy_update1140.state.json b/ppo_v9/policy_update1140.state.json deleted file mode 100644 index f1ee552f04150d71c413f35731d0850853185f85..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1140.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1141, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4381440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1145.safetensors b/ppo_v9/policy_update1145.safetensors deleted file mode 100644 index 1eb48e7ffe1011f7016e2a2967c0d05bd5c7763c..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1145.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:43652d69127ae234086a23e17fb51bda1a49bd530195dae9f34bbe8ba5116515 -size 48494336 diff --git a/ppo_v9/policy_update1145.state.json b/ppo_v9/policy_update1145.state.json deleted file mode 100644 index 2edb6b418570434625529977b15931ba52cf0671..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1145.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1146, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4400640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update115.safetensors b/ppo_v9/policy_update115.safetensors deleted file mode 100644 index 0a3f5f2ca3e89af195078a2a1b208a765cbb5b22..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update115.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c590e0895138c380cb37224d884e36c798f7b56af6e11b6f437def06209660da -size 48494336 diff --git a/ppo_v9/policy_update115.state.json b/ppo_v9/policy_update115.state.json deleted file mode 100644 index 6ff92150a5b712158aeeefbc44969b84440f7ac1..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update115.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 116, - "stage": 0, - "ent_scale": 1.0, - "lr_now": 0.00025, - "total_env_steps": 445440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1150.safetensors b/ppo_v9/policy_update1150.safetensors deleted file mode 100644 index 7069d062b6956406e574b27e401070347cc2e419..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1150.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:406b5757fd2a4f9a8007ec525c1e5963c25d6888b461a5644fe6b707230599e4 -size 48494336 diff --git a/ppo_v9/policy_update1150.state.json b/ppo_v9/policy_update1150.state.json deleted file mode 100644 index 001c2c920bddb23c84a8d4a46936e6bff3d4c8a2..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1150.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1151, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4419840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1155.safetensors b/ppo_v9/policy_update1155.safetensors deleted file mode 100644 index 0a07dc091222cc90ee15fcc73f98199d97f1bcc1..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1155.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:75af4abf1e1a1c3203bc9dc8fe4c06a2a64427b7549015b893720130c447a1ef -size 48494336 diff --git a/ppo_v9/policy_update1155.state.json b/ppo_v9/policy_update1155.state.json deleted file mode 100644 index 338b0f0b2f90e14e08303b8cd794b5879bdbb6f0..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1155.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1156, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4439040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1160.safetensors b/ppo_v9/policy_update1160.safetensors deleted file mode 100644 index 63f8f3e56b3586be419bb7e73d78d42e49a7eae6..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1160.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:67f3a1220f532fa620bb57e1d6001e10e78b4e71ff22279dc5bbb8f2f521d5bf -size 48494336 diff --git a/ppo_v9/policy_update1160.state.json b/ppo_v9/policy_update1160.state.json deleted file mode 100644 index f9657fd0ad0a1df63a6d516a104e1e9c6dab5518..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1160.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1161, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4458240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1165.safetensors b/ppo_v9/policy_update1165.safetensors deleted file mode 100644 index f5fe291262b8b0d282f19938fe3974571dc43162..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1165.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e9180ec1a9aaec4c16f983c0992df79c8ac3f7857c8579afc41ba72a7a4ad58f -size 48494336 diff --git a/ppo_v9/policy_update1165.state.json b/ppo_v9/policy_update1165.state.json deleted file mode 100644 index 4b501ca7bf7b8eacd6e7db514abf5eccaef2feb6..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1165.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1166, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4477440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1170.safetensors b/ppo_v9/policy_update1170.safetensors deleted file mode 100644 index f0318ffd9bd7abed5276734c74431f6743f38734..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1170.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fb6bedb7044668a7abc219d0adb0783b76f7793c903e422dc215a8880d4f1c86 -size 48494336 diff --git a/ppo_v9/policy_update1170.state.json b/ppo_v9/policy_update1170.state.json deleted file mode 100644 index 5febc949a9b2abd7773f88c857a141d0b192a130..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1170.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1171, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4496640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1175.safetensors b/ppo_v9/policy_update1175.safetensors deleted file mode 100644 index cf67db9aca34f1618c4d77db0b632dd081e5223f..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1175.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dfe0cea41e5abb69d1d095edc06d61cc53c6381bd47b4eebea443a13f6884449 -size 48494336 diff --git a/ppo_v9/policy_update1175.state.json b/ppo_v9/policy_update1175.state.json deleted file mode 100644 index 267b567b3bbd2dc7fdea91041be5ef3517942b9d..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1175.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1176, - "stage": 2, - "ent_scale": 1.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4515840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1180.safetensors b/ppo_v9/policy_update1180.safetensors deleted file mode 100644 index 53a17ed28b097d5a62e86ab609173019ef74f997..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1180.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:142982a4d08c692622afe6ce5f5ae24989c327e31b8d1d11b8910445c4f51841 -size 48494336 diff --git a/ppo_v9/policy_update1180.state.json b/ppo_v9/policy_update1180.state.json deleted file mode 100644 index 3b1c4b34f51c056d674efaa94fba65366da4bd68..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1180.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1181, - "stage": 2, - "ent_scale": 2.1970000000000005, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4535040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1185.safetensors b/ppo_v9/policy_update1185.safetensors deleted file mode 100644 index d7fb81161dc6ca73f84f5514295bf1cbb6b43266..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1185.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7eceb03e157124195ef398e15165a2a754acfdabd009490d3f207bd7f384cb86 -size 48494336 diff --git a/ppo_v9/policy_update1185.state.json b/ppo_v9/policy_update1185.state.json deleted file mode 100644 index 6941dc2be0f202f962bdcd881e27cf6ad306bb4e..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1185.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1186, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4554240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1190.safetensors b/ppo_v9/policy_update1190.safetensors deleted file mode 100644 index 9ce93dffc855cff398334aa6505657cf366c1e26..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1190.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5fe8349480a48a7d64522dc00ccd5e370e448d2e5cff6f9c563779664cc78a0a -size 48494336 diff --git a/ppo_v9/policy_update1190.state.json b/ppo_v9/policy_update1190.state.json deleted file mode 100644 index 627b260b59dc6ec17db7199b59441a2ae297aab8..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1190.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1191, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4573440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1195.safetensors b/ppo_v9/policy_update1195.safetensors deleted file mode 100644 index f66ad42e43e3e86f17960bf56984d58686e99e03..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1195.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:094143d38b2bdae95ff2a6593c026fa52acb645d13f36200a08a8b368590d2e8 -size 48494336 diff --git a/ppo_v9/policy_update1195.state.json b/ppo_v9/policy_update1195.state.json deleted file mode 100644 index 64c4cef7930cfe63f2530f9b533a23223db4048e..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1195.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1196, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4592640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update120.safetensors b/ppo_v9/policy_update120.safetensors deleted file mode 100644 index 7fe1dbeee3a5f4ee101295c64420ad996a45aabd..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update120.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:892ff2d176175293596751ef6de0bd2bc77727abb14ccb740ce78814ae949a81 -size 48494336 diff --git a/ppo_v9/policy_update120.state.json b/ppo_v9/policy_update120.state.json deleted file mode 100644 index 9b93864ad8e89f464ad181d6e2bdd0213fb6d754..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update120.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 121, - "stage": 0, - "ent_scale": 1.0, - "lr_now": 0.00025, - "total_env_steps": 464640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1200.safetensors b/ppo_v9/policy_update1200.safetensors deleted file mode 100644 index 2c2e0fe1d1d544cb83ebcc26074958a4cb482e3b..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1200.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f1354fec8905527dd819f6eff3a6ffb5d85e6b0a54d7dc5facd8568c3b66abac -size 48494336 diff --git a/ppo_v9/policy_update1200.state.json b/ppo_v9/policy_update1200.state.json deleted file mode 100644 index 4580575d350b27f2c8845c5cc138712a0b933803..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1200.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1201, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4611840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1205.safetensors b/ppo_v9/policy_update1205.safetensors deleted file mode 100644 index ef682e4f09eed343832b843c1c6e3bdbf6684bd4..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1205.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8e2456d378f5cb66308b443ac3b6188503ce4aa3edc4aca8c37d95a16da88c71 -size 48494336 diff --git a/ppo_v9/policy_update1205.state.json b/ppo_v9/policy_update1205.state.json deleted file mode 100644 index 08db3456799edd7e30314c9d4ac3248f3672dd9b..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1205.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1206, - "stage": 2, - "ent_scale": 3.917630832342295, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4631040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1210.safetensors b/ppo_v9/policy_update1210.safetensors deleted file mode 100644 index dbfa69d194a8da4595317c3a3dc4a6b15f020995..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1210.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2d37b552588f2496ca4b755275899672215d7b6bbaae6b12f1e6199af7a1280a -size 48494336 diff --git a/ppo_v9/policy_update1210.state.json b/ppo_v9/policy_update1210.state.json deleted file mode 100644 index d32243346109431af04df605bcd6f0f7c9d695e1..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1210.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1211, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4650240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1215.safetensors b/ppo_v9/policy_update1215.safetensors deleted file mode 100644 index 4ffe78b4aa06bb226f7ffd658143568f8c931a1b..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1215.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c53e99787fe21960969e328122efcac8dc0164ae101d6ee352811da5b075ed38 -size 48494336 diff --git a/ppo_v9/policy_update1215.state.json b/ppo_v9/policy_update1215.state.json deleted file mode 100644 index f3de93d83bb2aa78fc41c943051d221985e0afbe..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1215.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1216, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4669440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1220.safetensors b/ppo_v9/policy_update1220.safetensors deleted file mode 100644 index f3908d045dd6b9afeedaf9694ab0679a474d9374..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1220.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:333c5cf7a1c795b5c3cb1e5b5e28454bd63865767de8c229310d2c359810bf94 -size 48494336 diff --git a/ppo_v9/policy_update1220.state.json b/ppo_v9/policy_update1220.state.json deleted file mode 100644 index 7d6a24415c4f5089ee4991d7fb3bd0efc5585129..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1220.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1221, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4688640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1225.safetensors b/ppo_v9/policy_update1225.safetensors deleted file mode 100644 index 6451e75529f6ea5ccf9607ce68a7a8975d44c1e3..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1225.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a45698b718877c92f76012109213b6c5a1a819b5c6416e22f98433093c7a1d09 -size 48494336 diff --git a/ppo_v9/policy_update1225.state.json b/ppo_v9/policy_update1225.state.json deleted file mode 100644 index ec4dcf0480e0eb38c8c0e41b61f811bf36e85a07..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1225.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1226, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4707840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1230.safetensors b/ppo_v9/policy_update1230.safetensors deleted file mode 100644 index b8cf0f8e0a5dd37378ac1061053de6cf3f8896e5..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1230.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:33b4acd9195b7ddd504ce503787d6e8e8c1b1793a489fdc4ce836d28de64d95c -size 48494336 diff --git a/ppo_v9/policy_update1230.state.json b/ppo_v9/policy_update1230.state.json deleted file mode 100644 index f4f121bc18a22f681ac07e46e0991b938bd82f3c..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1230.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1231, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4727040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1235.safetensors b/ppo_v9/policy_update1235.safetensors deleted file mode 100644 index 676e6dbdbd61137315569eb4b6a86b9a59e33a21..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1235.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3af65af828fce4c361a4625dd37eac3d9b232398c50cf9652718731ce8a7807c -size 48494336 diff --git a/ppo_v9/policy_update1235.state.json b/ppo_v9/policy_update1235.state.json deleted file mode 100644 index 0ffe1706d144f20973ade89504e6003cd2e9334d..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1235.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1236, - "stage": 2, - "ent_scale": 4.761904761904762, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4746240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1240.safetensors b/ppo_v9/policy_update1240.safetensors deleted file mode 100644 index 156b789b42dfb5a71415fa00287d92980bb846d4..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1240.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3a32803ee5f225cf12a0c6694565cb7863ad3e7b1a82f93a46f62319f126b36d -size 48494336 diff --git a/ppo_v9/policy_update1240.state.json b/ppo_v9/policy_update1240.state.json deleted file mode 100644 index cffc135343712febc76a2dad74622e0a77d6251e..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1240.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1241, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4765440, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1245.safetensors b/ppo_v9/policy_update1245.safetensors deleted file mode 100644 index 479fd8fd34c8d43be88b1d4cb7ccaf303eb4e519..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1245.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e2a5620b5be09abd5bcc50c97f71ae888322b033ef0f716917e248cec37b25ad -size 48494336 diff --git a/ppo_v9/policy_update1245.state.json b/ppo_v9/policy_update1245.state.json deleted file mode 100644 index 14a1693fbc825039e97ac6f54f4612a7fc01c33f..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1245.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1246, - "stage": 2, - "ent_scale": 4.761904761904762, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4784640, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update125.safetensors b/ppo_v9/policy_update125.safetensors deleted file mode 100644 index e05cc4a8a71f8a08682085621400f3423d7d7a5e..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update125.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4978cb6c51802ceb8533f8e2671d297199f72dc46fe3c5b9fb3e268e11537667 -size 48494336 diff --git a/ppo_v9/policy_update125.state.json b/ppo_v9/policy_update125.state.json deleted file mode 100644 index f537daa8153a28497f8af7742bce103af1f014de..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update125.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 126, - "stage": 0, - "ent_scale": 1.0, - "lr_now": 0.00025, - "total_env_steps": 483840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 1.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1250.safetensors b/ppo_v9/policy_update1250.safetensors deleted file mode 100644 index d2221e25f1f7f2735305053d98119dd1f0985fe3..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1250.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8208687690511e1545c848667d91b143a9566828681767114305b8a7cbd9f6ff -size 48494336 diff --git a/ppo_v9/policy_update1250.state.json b/ppo_v9/policy_update1250.state.json deleted file mode 100644 index e18077d5561e9910d0394ce5b33d43473525140d..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1250.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1251, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4803840, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1255.safetensors b/ppo_v9/policy_update1255.safetensors deleted file mode 100644 index fd9b1245066888d19bc02ce67c3fde8a27ae4a82..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1255.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6680c5d4cf71dd6fed679fc3878d07dda1afd73dace340e34e3997907b711c83 -size 48494336 diff --git a/ppo_v9/policy_update1255.state.json b/ppo_v9/policy_update1255.state.json deleted file mode 100644 index c7f6325ecef4d45831fd78bd38da66c6d1e70690..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1255.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1256, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4823040, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1260.safetensors b/ppo_v9/policy_update1260.safetensors deleted file mode 100644 index 987f9cb4b535eafec213486384f170b31b16667f..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1260.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:753f03202e142d3aaed42d850e2e291991d74645fdc2fb5ea6270770bbee2c4f -size 48494336 diff --git a/ppo_v9/policy_update1260.state.json b/ppo_v9/policy_update1260.state.json deleted file mode 100644 index 622f411cbfcdcb4b06dfcf92bcbe5bc7c23fd794..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1260.state.json +++ /dev/null @@ -1,87 +0,0 @@ -{ - "checkpoint_schema_version": 2, - "hidden_reset_policy": "episode_done", - "update": 1261, - "stage": 2, - "ent_scale": 5.0, - "lr_now": 0.00018062499999999999, - "total_env_steps": 4842240, - "recent_wins": [ - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0, - 0.0 - ], - "recent_conversions": [], - "best_eval_win": null, - "best_eval_score": null, - "v81_curriculum": true, - "curriculum_schedule": "v9", - "reward_profile": "v9-sparse-win-v1", - "return_stats": null, - "stage_env_targets": [ - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 24, - 20, - 20, - 16, - 16, - 12, - 12, - 10, - 10, - 10, - 8, - 8, - 10, - 8, - 8, - 8, - 8, - 8 - ], - "envs_per_shard": 20, - "requested_env_target": null -} \ No newline at end of file diff --git a/ppo_v9/policy_update1265.safetensors b/ppo_v9/policy_update1265.safetensors deleted file mode 100644 index e3c1bef1bcef6a7c4c7935095d92705d86a62573..0000000000000000000000000000000000000000 --- a/ppo_v9/policy_update1265.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:11d301dd0071a354be834fd1beef6182341dbbde02467b2cd38369c19650fa8e -size 48494336