Upload folder using huggingface_hub

al_0.47_g_0.99_106/action_logprobs.pth.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9069e34e1868ecd34aa62c095151fa5e3d0a632619a4c30ed539e46858016f88
+size 63325170

al_0.47_g_0.99_106/action_probs.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09cc0c025903aba26adebdd1496ba8513ba57fbfe5ea6dd6150ceb7b809c300
+size 29047763

al_0.47_g_0.99_106/checkpoints.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4c7ba8c01026808a60ad979c58b92632714e00075d70cb6ebfaf1776298491
+size 644710776

al_0.47_g_0.99_106/config.cfg

@@ -0,0 +1,57 @@
+rl_action=train
+num_rollout_steps=64
+lr=5e-05
+discount_rate=0.99
+eff_horizon=None
+eval_every=1
+use_wandb=True
+use_hf=True
+use_log=True
+num_total_env_steps=5000000000
+checkpoint=al_0.47_g_0.99_106
+render_sixel=False
+sixel_idx=60
+seed=106
+mask_type=first_episode
+penalize_time=False
+optim=adam
+live_monitor=False
+use_bf16=False
+deterministic=True
+eval_schedule=0:1,250:2,500:5,1000:10,2000:20
+grad_acc_per_chunk=5
+num_rollout_chunks=1
+cheese_loc=any
+env_layout=open
+alpha=0.47
+env_size=13
+num_levels=9600
+f_str_ckpt=al_{alpha}_g_{discount_rate}_{seed}
+wandb_project=jaxgmg2_3phase_seed
+ckpt_dir=jaxgmg2_3phase_seed
+duplication_factor=-1
+smoke=False
+compile=True
+num_chains=6
+num_draws=3000
+num_steps_bw_draws=1
+on_policy=True
+llc_nbeta=3000
+localization=10
+exact_solver_each_draw=False
+llc_optimizer=sgld
+iw_clip_eps=None
+rmsprop_burnin_steps=20
+llc_data_file=llc_scan_open_reinforce.pkl
+llc_checkpoint_index=None
+llc_checkpoint_number=None
+sink=None
+repo_id=davidquarel/jaxgmg_ckpt_zip
+use_shuffled_checkpoints=False
+force_re_download=False
+off_distribution_data=False
+weight_restrictions=None
+weight_restrictions_invert=False
+evaluate_every_position=False
+use_prev_action=False
+num_prev_actions=1

al_0.47_g_0.99_106/config.json

@@ -0,0 +1,59 @@
+{
+  "alpha": 0.47,
+  "checkpoint": "al_0.47_g_0.99_106",
+  "cheese_loc": "any",
+  "ckpt_dir": "jaxgmg2_3phase_seed",
+  "compile": true,
+  "deterministic": true,
+  "discount_rate": 0.99,
+  "duplication_factor": -1,
+  "eff_horizon": null,
+  "env_layout": "open",
+  "env_size": 13,
+  "eval_every": 1,
+  "eval_schedule": "0:1,250:2,500:5,1000:10,2000:20",
+  "evaluate_every_position": false,
+  "exact_solver_each_draw": false,
+  "f_str_ckpt": "al_{alpha}_g_{discount_rate}_{seed}",
+  "force_re_download": false,
+  "grad_acc_per_chunk": 5,
+  "iw_clip_eps": null,
+  "live_monitor": false,
+  "llc_checkpoint_index": null,
+  "llc_checkpoint_number": null,
+  "llc_data_file": "llc_scan_open_reinforce.pkl",
+  "llc_nbeta": 3000,
+  "llc_optimizer": "sgld",
+  "localization": 10,
+  "lr": 5e-05,
+  "mask_type": "first_episode",
+  "num_chains": 6,
+  "num_draws": 3000,
+  "num_levels": 9600,
+  "num_prev_actions": 1,
+  "num_rollout_chunks": 1,
+  "num_rollout_steps": 64,
+  "num_steps_bw_draws": 1,
+  "num_total_env_steps": 5000000000,
+  "off_distribution_data": false,
+  "on_policy": true,
+  "optim": "adam",
+  "penalize_time": false,
+  "render_sixel": false,
+  "repo_id": "davidquarel/jaxgmg_ckpt_zip",
+  "rl_action": "train",
+  "rmsprop_burnin_steps": 20,
+  "seed": 106,
+  "sink": null,
+  "sixel_idx": 60,
+  "smoke": false,
+  "use_bf16": false,
+  "use_hf": true,
+  "use_log": true,
+  "use_prev_action": false,
+  "use_shuffled_checkpoints": false,
+  "use_wandb": true,
+  "wandb_project": "jaxgmg2_3phase_seed",
+  "weight_restrictions": null,
+  "weight_restrictions_invert": false
+}

al_0.47_g_0.99_106/latest_train.json

@@ -0,0 +1,12 @@
+{
+  "ts": "2026-01-24T02:46:54.698660Z",
+  "loop": 8137,
+  "env_steps": 4999987199,
+  "loss": 0.019173111766576767,
+  "avg_return": 0.9238110780715942,
+  "regret": 0.6239526271820068,
+  "entropy": 0.11560589075088501,
+  "lr": 5e-05,
+  "discount_rate": 0.99,
+  "num_rollout_steps": 64
+}

al_0.47_g_0.99_106/setup.json

@@ -0,0 +1,74 @@
+{
+  "config": {
+    "rl_action": "train",
+    "num_rollout_steps": 64,
+    "lr": 5e-05,
+    "discount_rate": 0.99,
+    "eff_horizon": null,
+    "eval_every": 1,
+    "use_wandb": true,
+    "use_hf": true,
+    "use_log": true,
+    "num_total_env_steps": 5000000000,
+    "checkpoint": "al_0.47_g_0.99_106",
+    "render_sixel": false,
+    "sixel_idx": 60,
+    "seed": 106,
+    "mask_type": "first_episode",
+    "penalize_time": false,
+    "optim": "adam",
+    "live_monitor": false,
+    "use_bf16": false,
+    "deterministic": true,
+    "eval_schedule": "0:1,250:2,500:5,1000:10,2000:20",
+    "grad_acc_per_chunk": 5,
+    "num_rollout_chunks": 1,
+    "cheese_loc": "any",
+    "env_layout": "open",
+    "alpha": 0.47,
+    "env_size": 13,
+    "num_levels": 9600,
+    "f_str_ckpt": "al_{alpha}_g_{discount_rate}_{seed}",
+    "wandb_project": "jaxgmg2_3phase_seed",
+    "ckpt_dir": "jaxgmg2_3phase_seed",
+    "duplication_factor": -1,
+    "smoke": false,
+    "compile": true,
+    "num_chains": 6,
+    "num_draws": 3000,
+    "num_steps_bw_draws": 1,
+    "on_policy": true,
+    "llc_nbeta": 3000,
+    "localization": 10,
+    "exact_solver_each_draw": false,
+    "llc_optimizer": "sgld",
+    "iw_clip_eps": null,
+    "rmsprop_burnin_steps": 20,
+    "llc_data_file": "llc_scan_open_reinforce.pkl",
+    "llc_checkpoint_index": null,
+    "llc_checkpoint_number": null,
+    "sink": null,
+    "repo_id": "davidquarel/jaxgmg_ckpt_zip",
+    "use_shuffled_checkpoints": false,
+    "force_re_download": false,
+    "off_distribution_data": false,
+    "weight_restrictions": null,
+    "weight_restrictions_invert": false,
+    "evaluate_every_position": false,
+    "use_prev_action": false,
+    "num_prev_actions": 1
+  },
+  "setup": {
+    "start_time_utc": "2026-01-24T00:50:40.971473Z",
+    "seed": 106,
+    "device": "cuda",
+    "python_version": "3.11.11",
+    "torch_version": "2.10.0+cu128",
+    "jax_version": "0.6.2",
+    "hostname": "5a72857b6734",
+    "platform": "Linux-5.15.0-164-generic-x86_64-with-glibc2.35",
+    "git_sha": null,
+    "git_branch": null,
+    "use_wandb": true
+  }
+}

al_0.47_g_0.99_106/setup.txt

@@ -0,0 +1,8 @@
+Start: 2026-01-24T00:50:40.971473Z
+Seed: 106
+Device: cuda
+Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
+Host: 5a72857b6734
+Platform: Linux-5.15.0-164-generic-x86_64-with-glibc2.35
+Git: branch=None sha=None
+use_wandb: True