Upload folder using huggingface_hub

al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/action_logprobs.pth.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80beb8d0a7dbce073f547b4be3bcfbfe0299a3233c46de602b06c7bfcd1e287
+size 74283292

al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/action_probs.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6172a5d7d793ca0e8b77532394cc86eb426244e0c908f69f66f99a2ca1aad88
+size 30764341

al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/checkpoints.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572cbb4cce533804edf23f02d2cf3b12936fe74580794852e08b56624f1ca9eb
+size 676855671

al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/config.cfg

@@ -0,0 +1,66 @@
+rl_action=train
+num_rollout_steps=64
+lr=5e-05
+discount_rate=0.975
+eff_horizon=None
+eval_every=1
+use_wandb=True
+use_hf=True
+use_log=True
+num_total_env_steps=2000000000
+checkpoint=al_0.227_g_0.975_seed_100_pa_1_lr_5e-05
+render_sixel=False
+sixel_idx=60
+seed=100
+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
+grad_acc_per_chunk=5
+num_rollout_chunks=1
+cheese_loc=any
+env_rule=None
+env_layout=open
+alpha=0.2267664087148158
+env_size=13
+num_levels=9600
+f_str_ckpt=al_{alpha:.3f}_g_{discount_rate}_seed_{seed}_pa_{num_prev_actions}_lr_{lr:.0e}
+wandb_project=jaxgmg2_3phase_fast
+ckpt_dir=jaxgmg2_3phase_fast
+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
+num_prev_actions=1
+ntfy=david_jaxgmg
+vis_average_state=False
+use_prev_action=False
+ckpt_path=jaxgmg2_3phase_fast/al_0.227_g_0.975_seed_100_pa_1_lr_5e-05
+env_steps_per_loop=614400
+total_loops=3255
+eff_acc_steps=5
+env_steps_per_microbatch=122880
+chunk_size=9600

al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/config.json

@@ -0,0 +1,68 @@
+{
+  "alpha": 0.2267664087148158,
+  "checkpoint": "al_0.227_g_0.975_seed_100_pa_1_lr_5e-05",
+  "cheese_loc": "any",
+  "chunk_size": 9600,
+  "ckpt_dir": "jaxgmg2_3phase_fast",
+  "ckpt_path": "jaxgmg2_3phase_fast/al_0.227_g_0.975_seed_100_pa_1_lr_5e-05",
+  "compile": true,
+  "deterministic": true,
+  "discount_rate": 0.975,
+  "duplication_factor": -1,
+  "eff_acc_steps": 5,
+  "eff_horizon": null,
+  "env_layout": "open",
+  "env_rule": null,
+  "env_size": 13,
+  "env_steps_per_loop": 614400,
+  "env_steps_per_microbatch": 122880,
+  "eval_every": 1,
+  "eval_schedule": "0:1,250:2,500:5",
+  "evaluate_every_position": false,
+  "exact_solver_each_draw": false,
+  "f_str_ckpt": "al_{alpha:.3f}_g_{discount_rate}_seed_{seed}_pa_{num_prev_actions}_lr_{lr:.0e}",
+  "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",
+  "ntfy": "david_jaxgmg",
+  "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": 2000000000,
+  "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": 100,
+  "sink": null,
+  "sixel_idx": 60,
+  "smoke": false,
+  "total_loops": 3255,
+  "use_bf16": false,
+  "use_hf": true,
+  "use_log": true,
+  "use_prev_action": false,
+  "use_shuffled_checkpoints": false,
+  "use_wandb": true,
+  "vis_average_state": false,
+  "wandb_project": "jaxgmg2_3phase_fast",
+  "weight_restrictions": null,
+  "weight_restrictions_invert": false
+}

al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/latest_train.json

@@ -0,0 +1,12 @@
+{
+  "ts": "2026-01-28T07:28:13.914167Z",
+  "loop": 3254,
+  "env_steps": 1999871999,
+  "loss": 0.009787608869373798,
+  "avg_return": 0.6671315431594849,
+  "regret": 0.14531025290489197,
+  "entropy": 0.14323128759860992,
+  "lr": 5e-05,
+  "discount_rate": 0.975,
+  "num_rollout_steps": 64
+}

al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/setup.json

@@ -0,0 +1,83 @@
+{
+  "config": {
+    "rl_action": "train",
+    "num_rollout_steps": 64,
+    "lr": 5e-05,
+    "discount_rate": 0.975,
+    "eff_horizon": null,
+    "eval_every": 1,
+    "use_wandb": true,
+    "use_hf": true,
+    "use_log": true,
+    "num_total_env_steps": 2000000000,
+    "checkpoint": "al_0.227_g_0.975_seed_100_pa_1_lr_5e-05",
+    "render_sixel": false,
+    "sixel_idx": 60,
+    "seed": 100,
+    "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",
+    "grad_acc_per_chunk": 5,
+    "num_rollout_chunks": 1,
+    "cheese_loc": "any",
+    "env_rule": null,
+    "env_layout": "open",
+    "alpha": 0.2267664087148158,
+    "env_size": 13,
+    "num_levels": 9600,
+    "f_str_ckpt": "al_{alpha:.3f}_g_{discount_rate}_seed_{seed}_pa_{num_prev_actions}_lr_{lr:.0e}",
+    "wandb_project": "jaxgmg2_3phase_fast",
+    "ckpt_dir": "jaxgmg2_3phase_fast",
+    "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,
+    "num_prev_actions": 1,
+    "ntfy": "david_jaxgmg",
+    "vis_average_state": false,
+    "use_prev_action": false,
+    "ckpt_path": "jaxgmg2_3phase_fast/al_0.227_g_0.975_seed_100_pa_1_lr_5e-05",
+    "env_steps_per_loop": 614400,
+    "total_loops": 3255,
+    "eff_acc_steps": 5,
+    "env_steps_per_microbatch": 122880,
+    "chunk_size": 9600
+  },
+  "setup": {
+    "start_time_utc": "2026-01-28T06:38:52.862251Z",
+    "seed": 100,
+    "device": "cuda",
+    "python_version": "3.11.11",
+    "torch_version": "2.10.0+cu128",
+    "jax_version": "0.6.2",
+    "hostname": "6cee14fefde0",
+    "platform": "Linux-6.8.0-59-generic-x86_64-with-glibc2.35",
+    "git_sha": null,
+    "git_branch": null,
+    "use_wandb": true
+  }
+}

al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/setup.txt

@@ -0,0 +1,8 @@
+Start: 2026-01-28T06:38:52.862251Z
+Seed: 100
+Device: cuda
+Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
+Host: 6cee14fefde0
+Platform: Linux-6.8.0-59-generic-x86_64-with-glibc2.35
+Git: branch=None sha=None
+use_wandb: True