davidquarel commited on
Commit
b352d73
·
verified ·
1 Parent(s): f7c7d01

Upload folder using huggingface_hub

Browse files
al_0.4_g_0.98_id_14_seed_980414/action_logprobs.pth.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eeafbb4dce5059e98d9fccbb04788c3be6f0d0fa40f3c58e9da7203fea409b6
3
+ size 214535804
al_0.4_g_0.98_id_14_seed_980414/action_probs.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823507521012ada2017bf8aae90876b9a56b8727b5bfd1a4d43dc44cfd955b11
3
+ size 96475169
al_0.4_g_0.98_id_14_seed_980414/checkpoints.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e15f57f1434dfb71397c13cda4fb4ee9016f6871de28888ca197b9c465d5151
3
+ size 1538434657
al_0.4_g_0.98_id_14_seed_980414/config.cfg ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ rl_action=train
2
+ num_rollout_steps=64
3
+ lr=5e-05
4
+ discount_rate=0.98
5
+ eff_horizon=None
6
+ eval_every=1
7
+ use_wandb=True
8
+ use_hf=True
9
+ use_log=True
10
+ num_total_env_steps=10000000000
11
+ checkpoint=al_0.4_g_0.98_id_14_seed_980414
12
+ render_sixel=False
13
+ sixel_idx=60
14
+ seed=980414
15
+ run_id=14
16
+ seed_formula={int(discount_rate*100):02d}{int(alpha*10):02d}{run_id:02d}
17
+ mask_type=first_episode
18
+ penalize_time=False
19
+ optim=adam
20
+ live_monitor=False
21
+ use_bf16=False
22
+ deterministic=True
23
+ eval_schedule=0:1,250:2,500:5,2000:10
24
+ grad_acc_per_chunk=5
25
+ num_rollout_chunks=1
26
+ cheese_loc=any
27
+ env_rule=None
28
+ env_layout=open
29
+ alpha=0.4
30
+ env_size=13
31
+ num_levels=9600
32
+ f_str_ckpt=al_{alpha}_g_{discount_rate}_id_{run_id}_seed_{seed}
33
+ wandb_project=jaxgmg2_3phase_unique
34
+ ckpt_dir=jaxgmg2_3phase_unique
35
+ duplication_factor=-1
36
+ smoke=False
37
+ compile=True
38
+ num_chains=6
39
+ num_draws=3000
40
+ num_steps_bw_draws=1
41
+ on_policy=True
42
+ llc_nbeta=3000
43
+ localization=10
44
+ exact_solver_each_draw=False
45
+ llc_optimizer=sgld
46
+ iw_clip_eps=None
47
+ rmsprop_burnin_steps=20
48
+ llc_data_file=llc_scan_open_reinforce.pkl
49
+ llc_checkpoint_index=None
50
+ llc_checkpoint_number=None
51
+ sink=None
52
+ repo_id=davidquarel/jaxgmg_ckpt_zip
53
+ use_shuffled_checkpoints=False
54
+ force_re_download=False
55
+ off_distribution_data=False
56
+ weight_restrictions=None
57
+ weight_restrictions_invert=False
58
+ evaluate_every_position=False
59
+ num_prev_actions=1
60
+ ntfy=david_jaxgmg
61
+ vis_average_state=False
62
+ trim_episodes=True
63
+ use_prev_action=False
64
+ ckpt_path=jaxgmg2_3phase_unique/al_0.4_g_0.98_id_14_seed_980414
65
+ env_steps_per_loop=614400
66
+ total_loops=16276
67
+ eff_acc_steps=5
68
+ env_steps_per_microbatch=122880
69
+ chunk_size=9600
al_0.4_g_0.98_id_14_seed_980414/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha": 0.4,
3
+ "checkpoint": "al_0.4_g_0.98_id_14_seed_980414",
4
+ "cheese_loc": "any",
5
+ "chunk_size": 9600,
6
+ "ckpt_dir": "jaxgmg2_3phase_unique",
7
+ "ckpt_path": "jaxgmg2_3phase_unique/al_0.4_g_0.98_id_14_seed_980414",
8
+ "compile": true,
9
+ "deterministic": true,
10
+ "discount_rate": 0.98,
11
+ "duplication_factor": -1,
12
+ "eff_acc_steps": 5,
13
+ "eff_horizon": null,
14
+ "env_layout": "open",
15
+ "env_rule": null,
16
+ "env_size": 13,
17
+ "env_steps_per_loop": 614400,
18
+ "env_steps_per_microbatch": 122880,
19
+ "eval_every": 1,
20
+ "eval_schedule": "0:1,250:2,500:5,2000:10",
21
+ "evaluate_every_position": false,
22
+ "exact_solver_each_draw": false,
23
+ "f_str_ckpt": "al_{alpha}_g_{discount_rate}_id_{run_id}_seed_{seed}",
24
+ "force_re_download": false,
25
+ "grad_acc_per_chunk": 5,
26
+ "iw_clip_eps": null,
27
+ "live_monitor": false,
28
+ "llc_checkpoint_index": null,
29
+ "llc_checkpoint_number": null,
30
+ "llc_data_file": "llc_scan_open_reinforce.pkl",
31
+ "llc_nbeta": 3000,
32
+ "llc_optimizer": "sgld",
33
+ "localization": 10,
34
+ "lr": 5e-05,
35
+ "mask_type": "first_episode",
36
+ "ntfy": "david_jaxgmg",
37
+ "num_chains": 6,
38
+ "num_draws": 3000,
39
+ "num_levels": 9600,
40
+ "num_prev_actions": 1,
41
+ "num_rollout_chunks": 1,
42
+ "num_rollout_steps": 64,
43
+ "num_steps_bw_draws": 1,
44
+ "num_total_env_steps": 10000000000,
45
+ "off_distribution_data": false,
46
+ "on_policy": true,
47
+ "optim": "adam",
48
+ "penalize_time": false,
49
+ "render_sixel": false,
50
+ "repo_id": "davidquarel/jaxgmg_ckpt_zip",
51
+ "rl_action": "train",
52
+ "rmsprop_burnin_steps": 20,
53
+ "run_id": 14,
54
+ "seed": 980414,
55
+ "seed_formula": "{int(discount_rate*100):02d}{int(alpha*10):02d}{run_id:02d}",
56
+ "sink": null,
57
+ "sixel_idx": 60,
58
+ "smoke": false,
59
+ "total_loops": 16276,
60
+ "trim_episodes": true,
61
+ "use_bf16": false,
62
+ "use_hf": true,
63
+ "use_log": true,
64
+ "use_prev_action": false,
65
+ "use_shuffled_checkpoints": false,
66
+ "use_wandb": true,
67
+ "vis_average_state": false,
68
+ "wandb_project": "jaxgmg2_3phase_unique",
69
+ "weight_restrictions": null,
70
+ "weight_restrictions_invert": false
71
+ }
al_0.4_g_0.98_id_14_seed_980414/eval.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
al_0.4_g_0.98_id_14_seed_980414/eval.log ADDED
The diff for this file is too large to render. See raw diff
 
al_0.4_g_0.98_id_14_seed_980414/latest_train.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ts": "2026-01-29T19:56:39.968383Z",
3
+ "loop": 16275,
4
+ "env_steps": 9999979333,
5
+ "loss": 0.012728332541882992,
6
+ "avg_return": 0.8534187078475952,
7
+ "regret": 0.0006138527533039451,
8
+ "entropy": 0.06381583213806152,
9
+ "lr": 5e-05,
10
+ "discount_rate": 0.98,
11
+ "num_rollout_steps": 64
12
+ }
al_0.4_g_0.98_id_14_seed_980414/setup.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "rl_action": "train",
4
+ "num_rollout_steps": 64,
5
+ "lr": 5e-05,
6
+ "discount_rate": 0.98,
7
+ "eff_horizon": null,
8
+ "eval_every": 1,
9
+ "use_wandb": true,
10
+ "use_hf": true,
11
+ "use_log": true,
12
+ "num_total_env_steps": 10000000000,
13
+ "checkpoint": "al_0.4_g_0.98_id_14_seed_980414",
14
+ "render_sixel": false,
15
+ "sixel_idx": 60,
16
+ "seed": 980414,
17
+ "run_id": 14,
18
+ "seed_formula": "{int(discount_rate*100):02d}{int(alpha*10):02d}{run_id:02d}",
19
+ "mask_type": "first_episode",
20
+ "penalize_time": false,
21
+ "optim": "adam",
22
+ "live_monitor": false,
23
+ "use_bf16": false,
24
+ "deterministic": true,
25
+ "eval_schedule": "0:1,250:2,500:5,2000:10",
26
+ "grad_acc_per_chunk": 5,
27
+ "num_rollout_chunks": 1,
28
+ "cheese_loc": "any",
29
+ "env_rule": null,
30
+ "env_layout": "open",
31
+ "alpha": 0.4,
32
+ "env_size": 13,
33
+ "num_levels": 9600,
34
+ "f_str_ckpt": "al_{alpha}_g_{discount_rate}_id_{run_id}_seed_{seed}",
35
+ "wandb_project": "jaxgmg2_3phase_unique",
36
+ "ckpt_dir": "jaxgmg2_3phase_unique",
37
+ "duplication_factor": -1,
38
+ "smoke": false,
39
+ "compile": true,
40
+ "num_chains": 6,
41
+ "num_draws": 3000,
42
+ "num_steps_bw_draws": 1,
43
+ "on_policy": true,
44
+ "llc_nbeta": 3000,
45
+ "localization": 10,
46
+ "exact_solver_each_draw": false,
47
+ "llc_optimizer": "sgld",
48
+ "iw_clip_eps": null,
49
+ "rmsprop_burnin_steps": 20,
50
+ "llc_data_file": "llc_scan_open_reinforce.pkl",
51
+ "llc_checkpoint_index": null,
52
+ "llc_checkpoint_number": null,
53
+ "sink": null,
54
+ "repo_id": "davidquarel/jaxgmg_ckpt_zip",
55
+ "use_shuffled_checkpoints": false,
56
+ "force_re_download": false,
57
+ "off_distribution_data": false,
58
+ "weight_restrictions": null,
59
+ "weight_restrictions_invert": false,
60
+ "evaluate_every_position": false,
61
+ "num_prev_actions": 1,
62
+ "ntfy": "david_jaxgmg",
63
+ "vis_average_state": false,
64
+ "trim_episodes": true,
65
+ "use_prev_action": false,
66
+ "ckpt_path": "jaxgmg2_3phase_unique/al_0.4_g_0.98_id_14_seed_980414",
67
+ "env_steps_per_loop": 614400,
68
+ "total_loops": 16276,
69
+ "eff_acc_steps": 5,
70
+ "env_steps_per_microbatch": 122880,
71
+ "chunk_size": 9600
72
+ },
73
+ "setup": {
74
+ "start_time_utc": "2026-01-29T15:43:21.392271Z",
75
+ "seed": 980414,
76
+ "device": "cuda",
77
+ "python_version": "3.11.11",
78
+ "torch_version": "2.10.0+cu128",
79
+ "jax_version": "0.6.2",
80
+ "hostname": "5b5108ece7a1",
81
+ "platform": "Linux-5.4.0-216-generic-x86_64-with-glibc2.35",
82
+ "git_sha": null,
83
+ "git_branch": null,
84
+ "use_wandb": true
85
+ }
86
+ }
al_0.4_g_0.98_id_14_seed_980414/setup.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ Start: 2026-01-29T15:43:21.392271Z
2
+ Seed: 980414
3
+ Device: cuda
4
+ Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
5
+ Host: 5b5108ece7a1
6
+ Platform: Linux-5.4.0-216-generic-x86_64-with-glibc2.35
7
+ Git: branch=None sha=None
8
+ use_wandb: True
al_0.4_g_0.98_id_14_seed_980414/train.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
al_0.4_g_0.98_id_14_seed_980414/train.log ADDED
The diff for this file is too large to render. See raw diff