davidquarel commited on
Commit
303fe81
·
verified ·
1 Parent(s): 6b7043a

Upload folder using huggingface_hub

Browse files
al_1.0_g_0.98_id_22_seed_981022/action_logprobs.pth.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f58377666912c6d80a2f48cdba50ff3240246901bd53c5d9d240a71b657668
3
+ size 254164652
al_1.0_g_0.98_id_22_seed_981022/action_probs.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0e2a17744d336e0434169120f4717a0f8f784a6d8802db78911cfd6d177bb2
3
+ size 167520828
al_1.0_g_0.98_id_22_seed_981022/checkpoints.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb09c3034d027a920e7ce6e34efc8094e44b56c155aefe3b293daaea39fbd0c3
3
+ size 1538487424
al_1.0_g_0.98_id_22_seed_981022/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
+ log_optimizer_state=True
11
+ num_total_env_steps=10000000000
12
+ checkpoint=al_1.0_g_0.98_id_22_seed_981022
13
+ render_sixel=False
14
+ sixel_idx=60
15
+ seed=981022
16
+ run_id=22
17
+ seed_formula={int(discount_rate*100):02d}{int(alpha*10):02d}{run_id:02d}
18
+ mask_type=first_episode
19
+ penalize_time=False
20
+ optim=adam
21
+ live_monitor=False
22
+ use_bf16=False
23
+ deterministic=True
24
+ eval_schedule=0:1,250:2,500:5,2000:10
25
+ grad_acc_per_chunk=5
26
+ num_rollout_chunks=1
27
+ cheese_loc=any
28
+ env_rule=None
29
+ env_layout=open
30
+ alpha=1.0
31
+ env_size=13
32
+ num_levels=9600
33
+ f_str_ckpt=al_{alpha}_g_{discount_rate}_id_{run_id}_seed_{seed}
34
+ wandb_project=jaxgmg2_3phase_optim_state
35
+ ckpt_dir=jaxgmg2_3phase_optim_state
36
+ duplication_factor=-1
37
+ smoke=False
38
+ compile=True
39
+ num_chains=6
40
+ num_draws=3000
41
+ num_steps_bw_draws=1
42
+ on_policy=True
43
+ llc_nbeta=3000
44
+ localization=10
45
+ exact_solver_each_draw=False
46
+ llc_optimizer=sgld
47
+ iw_clip_eps=None
48
+ rmsprop_burnin_steps=20
49
+ llc_data_file=llc_scan_open_reinforce.pkl
50
+ llc_checkpoint_index=None
51
+ llc_checkpoint_number=None
52
+ sink=None
53
+ repo_id=davidquarel/jaxgmg_ckpt_zip
54
+ use_shuffled_checkpoints=False
55
+ force_re_download=False
56
+ off_distribution_data=False
57
+ weight_restrictions=None
58
+ weight_restrictions_invert=False
59
+ evaluate_every_position=False
60
+ num_prev_actions=1
61
+ ntfy=david_jaxgmg
62
+ vis_average_state=False
63
+ use_prev_action=False
64
+ ckpt_path=jaxgmg2_3phase_optim_state/al_1.0_g_0.98_id_22_seed_981022
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_1.0_g_0.98_id_22_seed_981022/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha": 1.0,
3
+ "checkpoint": "al_1.0_g_0.98_id_22_seed_981022",
4
+ "cheese_loc": "any",
5
+ "chunk_size": 9600,
6
+ "ckpt_dir": "jaxgmg2_3phase_optim_state",
7
+ "ckpt_path": "jaxgmg2_3phase_optim_state/al_1.0_g_0.98_id_22_seed_981022",
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
+ "log_optimizer_state": true,
35
+ "lr": 5e-05,
36
+ "mask_type": "first_episode",
37
+ "ntfy": "david_jaxgmg",
38
+ "num_chains": 6,
39
+ "num_draws": 3000,
40
+ "num_levels": 9600,
41
+ "num_prev_actions": 1,
42
+ "num_rollout_chunks": 1,
43
+ "num_rollout_steps": 64,
44
+ "num_steps_bw_draws": 1,
45
+ "num_total_env_steps": 10000000000,
46
+ "off_distribution_data": false,
47
+ "on_policy": true,
48
+ "optim": "adam",
49
+ "penalize_time": false,
50
+ "render_sixel": false,
51
+ "repo_id": "davidquarel/jaxgmg_ckpt_zip",
52
+ "rl_action": "train",
53
+ "rmsprop_burnin_steps": 20,
54
+ "run_id": 22,
55
+ "seed": 981022,
56
+ "seed_formula": "{int(discount_rate*100):02d}{int(alpha*10):02d}{run_id:02d}",
57
+ "sink": null,
58
+ "sixel_idx": 60,
59
+ "smoke": false,
60
+ "total_loops": 16276,
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_optim_state",
69
+ "weight_restrictions": null,
70
+ "weight_restrictions_invert": false
71
+ }
al_1.0_g_0.98_id_22_seed_981022/eval.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
al_1.0_g_0.98_id_22_seed_981022/eval.log ADDED
The diff for this file is too large to render. See raw diff
 
al_1.0_g_0.98_id_22_seed_981022/latest_train.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ts": "2026-02-10T23:02:04.914919Z",
3
+ "loop": 16275,
4
+ "env_steps": 9999974399,
5
+ "loss": 0.020371336489915848,
6
+ "avg_return": 0.8817136883735657,
7
+ "regret": 0.0003295690403319895,
8
+ "entropy": 0.09712334722280502,
9
+ "lr": 5e-05,
10
+ "discount_rate": 0.98,
11
+ "num_rollout_steps": 64
12
+ }
al_1.0_g_0.98_id_22_seed_981022/optimizer_state.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc81bb71cb1482de26eb3f286cfa64dcd94298872f41aa0f669e51203bb37676
3
+ size 2673509450
al_1.0_g_0.98_id_22_seed_981022/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
+ "log_optimizer_state": true,
13
+ "num_total_env_steps": 10000000000,
14
+ "checkpoint": "al_1.0_g_0.98_id_22_seed_981022",
15
+ "render_sixel": false,
16
+ "sixel_idx": 60,
17
+ "seed": 981022,
18
+ "run_id": 22,
19
+ "seed_formula": "{int(discount_rate*100):02d}{int(alpha*10):02d}{run_id:02d}",
20
+ "mask_type": "first_episode",
21
+ "penalize_time": false,
22
+ "optim": "adam",
23
+ "live_monitor": false,
24
+ "use_bf16": false,
25
+ "deterministic": true,
26
+ "eval_schedule": "0:1,250:2,500:5,2000:10",
27
+ "grad_acc_per_chunk": 5,
28
+ "num_rollout_chunks": 1,
29
+ "cheese_loc": "any",
30
+ "env_rule": null,
31
+ "env_layout": "open",
32
+ "alpha": 1.0,
33
+ "env_size": 13,
34
+ "num_levels": 9600,
35
+ "f_str_ckpt": "al_{alpha}_g_{discount_rate}_id_{run_id}_seed_{seed}",
36
+ "wandb_project": "jaxgmg2_3phase_optim_state",
37
+ "ckpt_dir": "jaxgmg2_3phase_optim_state",
38
+ "duplication_factor": -1,
39
+ "smoke": false,
40
+ "compile": true,
41
+ "num_chains": 6,
42
+ "num_draws": 3000,
43
+ "num_steps_bw_draws": 1,
44
+ "on_policy": true,
45
+ "llc_nbeta": 3000,
46
+ "localization": 10,
47
+ "exact_solver_each_draw": false,
48
+ "llc_optimizer": "sgld",
49
+ "iw_clip_eps": null,
50
+ "rmsprop_burnin_steps": 20,
51
+ "llc_data_file": "llc_scan_open_reinforce.pkl",
52
+ "llc_checkpoint_index": null,
53
+ "llc_checkpoint_number": null,
54
+ "sink": null,
55
+ "repo_id": "davidquarel/jaxgmg_ckpt_zip",
56
+ "use_shuffled_checkpoints": false,
57
+ "force_re_download": false,
58
+ "off_distribution_data": false,
59
+ "weight_restrictions": null,
60
+ "weight_restrictions_invert": false,
61
+ "evaluate_every_position": false,
62
+ "num_prev_actions": 1,
63
+ "ntfy": "david_jaxgmg",
64
+ "vis_average_state": false,
65
+ "use_prev_action": false,
66
+ "ckpt_path": "jaxgmg2_3phase_optim_state/al_1.0_g_0.98_id_22_seed_981022",
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": "2026-02-10T18:24:06.654318Z",
75
+ "seed": 981022,
76
+ "device": "cuda",
77
+ "python_version": "3.11.11",
78
+ "torch_version": "2.10.0+cu128",
79
+ "jax_version": "0.6.2",
80
+ "hostname": "dc260bdb8b83",
81
+ "platform": "Linux-6.8.0-90-generic-x86_64-with-glibc2.35",
82
+ "git_sha": null,
83
+ "git_branch": null,
84
+ "use_wandb": true
85
+ }
86
+ }
al_1.0_g_0.98_id_22_seed_981022/setup.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ Start: 2026-02-10T18:24:06.654318Z
2
+ Seed: 981022
3
+ Device: cuda
4
+ Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
5
+ Host: dc260bdb8b83
6
+ Platform: Linux-6.8.0-90-generic-x86_64-with-glibc2.35
7
+ Git: branch=None sha=None
8
+ use_wandb: True
al_1.0_g_0.98_id_22_seed_981022/train.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
al_1.0_g_0.98_id_22_seed_981022/train.log ADDED
The diff for this file is too large to render. See raw diff