Upload mouse-run-run-1: trained agents, rollouts, evaluation, cross-architecture study
a0ebc13 verified | { | |
| "config": { | |
| "batch_size": 40, | |
| "checkpoint_every": 1000, | |
| "checkpoint_every_seconds": 1800.0, | |
| "clip_epsilon": 0.2, | |
| "concurrency": 10, | |
| "cuda_tf32": true, | |
| "device": "cuda", | |
| "entropy_coef": 0.01, | |
| "finite_guard": true, | |
| "fused_agent_rollout": true, | |
| "grad_clip": 1.0, | |
| "hidden_size": 256, | |
| "learning_rate": 0.0003, | |
| "max_steps": 100, | |
| "ppo_epochs": 4, | |
| "preset": "paper_text", | |
| "recurrent_l2_coef": 0.3, | |
| "status_every_seconds": 1800.0, | |
| "subspace_metric_period": 10, | |
| "triton_env_step": true, | |
| "updates": 20000, | |
| "value_clip": 10.0, | |
| "value_coef": 0.5 | |
| }, | |
| "config_sha256": "e6d90872991aaef38f2c75721962f18331fbc0ea1005a69c80e187db292ed2b5", | |
| "created_at": "2026-07-01T22:05:23.201137+00:00", | |
| "experiment": "mouse-run-run-1", | |
| "experiment_spec": "experiments/paper_marl_2026/SPEC.md", | |
| "experiment_spec_sha256": "084debd3db4ffe44b144a488d73febc090f4af1ec3d68d674dcbb51dcc788088", | |
| "initial_attempts": [ | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0000/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0000_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0000/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0000.attempt_01", | |
| "seed": 0, | |
| "task": "social", | |
| "unit_id": "social/seed_0000" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0000/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0000_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0000/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0000.attempt_01", | |
| "seed": 0, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0000" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0001/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0001_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0001/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0001.attempt_01", | |
| "seed": 1, | |
| "task": "social", | |
| "unit_id": "social/seed_0001" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0001/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0001_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0001/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0001.attempt_01", | |
| "seed": 1, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0001" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0002/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0002_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0002/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0002.attempt_01", | |
| "seed": 2, | |
| "task": "social", | |
| "unit_id": "social/seed_0002" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0002/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0002_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0002/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0002.attempt_01", | |
| "seed": 2, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0002" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0003/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0003_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0003/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0003.attempt_01", | |
| "seed": 3, | |
| "task": "social", | |
| "unit_id": "social/seed_0003" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0003/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0003_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0003/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0003.attempt_01", | |
| "seed": 3, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0003" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0004/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0004_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0004/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0004.attempt_01", | |
| "seed": 4, | |
| "task": "social", | |
| "unit_id": "social/seed_0004" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0004/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0004_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0004/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0004.attempt_01", | |
| "seed": 4, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0004" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0005/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0005_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0005/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0005.attempt_01", | |
| "seed": 5, | |
| "task": "social", | |
| "unit_id": "social/seed_0005" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0005/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0005_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0005/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0005.attempt_01", | |
| "seed": 5, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0005" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0006/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0006_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0006/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0006.attempt_01", | |
| "seed": 6, | |
| "task": "social", | |
| "unit_id": "social/seed_0006" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0006/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0006_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0006/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0006.attempt_01", | |
| "seed": 6, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0006" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0007/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0007_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0007/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0007.attempt_01", | |
| "seed": 7, | |
| "task": "social", | |
| "unit_id": "social/seed_0007" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0007/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0007_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0007/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0007.attempt_01", | |
| "seed": 7, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0007" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0008/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0008_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0008/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0008.attempt_01", | |
| "seed": 8, | |
| "task": "social", | |
| "unit_id": "social/seed_0008" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0008/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0008_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0008/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0008.attempt_01", | |
| "seed": 8, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0008" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/social/seed_0009/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/social_seed_0009_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/social/seed_0009/attempt_01", | |
| "run_id": "mouse-run-run-1.social.seed_0009.attempt_01", | |
| "seed": 9, | |
| "task": "social", | |
| "unit_id": "social/seed_0009" | |
| }, | |
| { | |
| "attempt": 1, | |
| "attempt_id": "attempt_01", | |
| "checkpoint": "runs/mouse-run-run-1/non_social/seed_0009/attempt_01/checkpoints/latest.safetensors", | |
| "log": "runs/mouse-run-run-1/logs/non_social_seed_0009_attempt_01.log", | |
| "resume_from": null, | |
| "run_dir": "runs/mouse-run-run-1/non_social/seed_0009/attempt_01", | |
| "run_id": "mouse-run-run-1.non_social.seed_0009.attempt_01", | |
| "seed": 9, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0009" | |
| } | |
| ], | |
| "max_attempts": 2, | |
| "provenance": { | |
| "command": "scripts/run_local_experiment.py --config experiments/paper_marl_2026/configs/primary.json", | |
| "created_at": "2026-07-01T22:05:23.201235+00:00", | |
| "dependencies": { | |
| "huggingface_hub": "1.21.0", | |
| "numpy": "2.5.0", | |
| "safetensors": "0.8.0", | |
| "tensorboard": "2.21.0", | |
| "torch": "2.12.1", | |
| "triton": "3.7.1" | |
| }, | |
| "executable": "/root/mouse-run-run-perf/.venv/bin/python3", | |
| "git": { | |
| "branch": "main", | |
| "diff_sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", | |
| "dirty": false, | |
| "sha": "685f46eb83cad06b6caa3b5dcdd869f2f3c4ac46", | |
| "short_sha": "685f46e", | |
| "status_short": "" | |
| }, | |
| "platform": "Linux-6.8.0-117-generic-x86_64-with-glibc2.39", | |
| "python": "3.14.5 (main, Jun 2 2026, 22:25:17) [Clang 22.1.3 ]", | |
| "schema_version": 1, | |
| "torch": { | |
| "cuda_available": true, | |
| "cuda_device_count": 1, | |
| "cuda_devices": [ | |
| { | |
| "index": 0, | |
| "major": 8, | |
| "minor": 9, | |
| "multi_processor_count": 66, | |
| "name": "NVIDIA GeForce RTX 4070 Ti SUPER", | |
| "total_memory_bytes": 16717578240 | |
| } | |
| ], | |
| "cuda_version": "13.0", | |
| "cudnn_version": 92000, | |
| "mps_available": false, | |
| "version": "2.12.1+cu130" | |
| } | |
| }, | |
| "schema_version": 2, | |
| "total_environment_steps": 1600000000, | |
| "total_units": 20, | |
| "units": [ | |
| { | |
| "seed": 0, | |
| "task": "social", | |
| "unit_id": "social/seed_0000" | |
| }, | |
| { | |
| "seed": 0, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0000" | |
| }, | |
| { | |
| "seed": 1, | |
| "task": "social", | |
| "unit_id": "social/seed_0001" | |
| }, | |
| { | |
| "seed": 1, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0001" | |
| }, | |
| { | |
| "seed": 2, | |
| "task": "social", | |
| "unit_id": "social/seed_0002" | |
| }, | |
| { | |
| "seed": 2, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0002" | |
| }, | |
| { | |
| "seed": 3, | |
| "task": "social", | |
| "unit_id": "social/seed_0003" | |
| }, | |
| { | |
| "seed": 3, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0003" | |
| }, | |
| { | |
| "seed": 4, | |
| "task": "social", | |
| "unit_id": "social/seed_0004" | |
| }, | |
| { | |
| "seed": 4, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0004" | |
| }, | |
| { | |
| "seed": 5, | |
| "task": "social", | |
| "unit_id": "social/seed_0005" | |
| }, | |
| { | |
| "seed": 5, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0005" | |
| }, | |
| { | |
| "seed": 6, | |
| "task": "social", | |
| "unit_id": "social/seed_0006" | |
| }, | |
| { | |
| "seed": 6, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0006" | |
| }, | |
| { | |
| "seed": 7, | |
| "task": "social", | |
| "unit_id": "social/seed_0007" | |
| }, | |
| { | |
| "seed": 7, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0007" | |
| }, | |
| { | |
| "seed": 8, | |
| "task": "social", | |
| "unit_id": "social/seed_0008" | |
| }, | |
| { | |
| "seed": 8, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0008" | |
| }, | |
| { | |
| "seed": 9, | |
| "task": "social", | |
| "unit_id": "social/seed_0009" | |
| }, | |
| { | |
| "seed": 9, | |
| "task": "non_social", | |
| "unit_id": "non_social/seed_0009" | |
| } | |
| ] | |
| } | |