davidquarel commited on
Commit
3df809d
·
verified ·
1 Parent(s): 3815889

Upload folder using huggingface_hub

Browse files
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/action_logprobs.pth.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b80beb8d0a7dbce073f547b4be3bcfbfe0299a3233c46de602b06c7bfcd1e287
3
+ size 74283292
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/action_probs.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6172a5d7d793ca0e8b77532394cc86eb426244e0c908f69f66f99a2ca1aad88
3
+ size 30764341
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/checkpoints.tar.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572cbb4cce533804edf23f02d2cf3b12936fe74580794852e08b56624f1ca9eb
3
+ size 676855671
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/config.cfg ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ rl_action=train
2
+ num_rollout_steps=64
3
+ lr=5e-05
4
+ discount_rate=0.975
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=2000000000
11
+ checkpoint=al_0.227_g_0.975_seed_100_pa_1_lr_5e-05
12
+ render_sixel=False
13
+ sixel_idx=60
14
+ seed=100
15
+ mask_type=first_episode
16
+ penalize_time=False
17
+ optim=adam
18
+ live_monitor=False
19
+ use_bf16=False
20
+ deterministic=True
21
+ eval_schedule=0:1,250:2,500:5
22
+ grad_acc_per_chunk=5
23
+ num_rollout_chunks=1
24
+ cheese_loc=any
25
+ env_rule=None
26
+ env_layout=open
27
+ alpha=0.2267664087148158
28
+ env_size=13
29
+ num_levels=9600
30
+ f_str_ckpt=al_{alpha:.3f}_g_{discount_rate}_seed_{seed}_pa_{num_prev_actions}_lr_{lr:.0e}
31
+ wandb_project=jaxgmg2_3phase_fast
32
+ ckpt_dir=jaxgmg2_3phase_fast
33
+ duplication_factor=-1
34
+ smoke=False
35
+ compile=True
36
+ num_chains=6
37
+ num_draws=3000
38
+ num_steps_bw_draws=1
39
+ on_policy=True
40
+ llc_nbeta=3000
41
+ localization=10
42
+ exact_solver_each_draw=False
43
+ llc_optimizer=sgld
44
+ iw_clip_eps=None
45
+ rmsprop_burnin_steps=20
46
+ llc_data_file=llc_scan_open_reinforce.pkl
47
+ llc_checkpoint_index=None
48
+ llc_checkpoint_number=None
49
+ sink=None
50
+ repo_id=davidquarel/jaxgmg_ckpt_zip
51
+ use_shuffled_checkpoints=False
52
+ force_re_download=False
53
+ off_distribution_data=False
54
+ weight_restrictions=None
55
+ weight_restrictions_invert=False
56
+ evaluate_every_position=False
57
+ num_prev_actions=1
58
+ ntfy=david_jaxgmg
59
+ vis_average_state=False
60
+ use_prev_action=False
61
+ ckpt_path=jaxgmg2_3phase_fast/al_0.227_g_0.975_seed_100_pa_1_lr_5e-05
62
+ env_steps_per_loop=614400
63
+ total_loops=3255
64
+ eff_acc_steps=5
65
+ env_steps_per_microbatch=122880
66
+ chunk_size=9600
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha": 0.2267664087148158,
3
+ "checkpoint": "al_0.227_g_0.975_seed_100_pa_1_lr_5e-05",
4
+ "cheese_loc": "any",
5
+ "chunk_size": 9600,
6
+ "ckpt_dir": "jaxgmg2_3phase_fast",
7
+ "ckpt_path": "jaxgmg2_3phase_fast/al_0.227_g_0.975_seed_100_pa_1_lr_5e-05",
8
+ "compile": true,
9
+ "deterministic": true,
10
+ "discount_rate": 0.975,
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",
21
+ "evaluate_every_position": false,
22
+ "exact_solver_each_draw": false,
23
+ "f_str_ckpt": "al_{alpha:.3f}_g_{discount_rate}_seed_{seed}_pa_{num_prev_actions}_lr_{lr:.0e}",
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": 2000000000,
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
+ "seed": 100,
54
+ "sink": null,
55
+ "sixel_idx": 60,
56
+ "smoke": false,
57
+ "total_loops": 3255,
58
+ "use_bf16": false,
59
+ "use_hf": true,
60
+ "use_log": true,
61
+ "use_prev_action": false,
62
+ "use_shuffled_checkpoints": false,
63
+ "use_wandb": true,
64
+ "vis_average_state": false,
65
+ "wandb_project": "jaxgmg2_3phase_fast",
66
+ "weight_restrictions": null,
67
+ "weight_restrictions_invert": false
68
+ }
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/eval.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/eval.log ADDED
The diff for this file is too large to render. See raw diff
 
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/latest_train.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ts": "2026-01-28T07:28:13.914167Z",
3
+ "loop": 3254,
4
+ "env_steps": 1999871999,
5
+ "loss": 0.009787608869373798,
6
+ "avg_return": 0.6671315431594849,
7
+ "regret": 0.14531025290489197,
8
+ "entropy": 0.14323128759860992,
9
+ "lr": 5e-05,
10
+ "discount_rate": 0.975,
11
+ "num_rollout_steps": 64
12
+ }
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/setup.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "rl_action": "train",
4
+ "num_rollout_steps": 64,
5
+ "lr": 5e-05,
6
+ "discount_rate": 0.975,
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": 2000000000,
13
+ "checkpoint": "al_0.227_g_0.975_seed_100_pa_1_lr_5e-05",
14
+ "render_sixel": false,
15
+ "sixel_idx": 60,
16
+ "seed": 100,
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",
24
+ "grad_acc_per_chunk": 5,
25
+ "num_rollout_chunks": 1,
26
+ "cheese_loc": "any",
27
+ "env_rule": null,
28
+ "env_layout": "open",
29
+ "alpha": 0.2267664087148158,
30
+ "env_size": 13,
31
+ "num_levels": 9600,
32
+ "f_str_ckpt": "al_{alpha:.3f}_g_{discount_rate}_seed_{seed}_pa_{num_prev_actions}_lr_{lr:.0e}",
33
+ "wandb_project": "jaxgmg2_3phase_fast",
34
+ "ckpt_dir": "jaxgmg2_3phase_fast",
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": null,
47
+ "rmsprop_burnin_steps": 20,
48
+ "llc_data_file": "llc_scan_open_reinforce.pkl",
49
+ "llc_checkpoint_index": null,
50
+ "llc_checkpoint_number": null,
51
+ "sink": null,
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": null,
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
+ "use_prev_action": false,
63
+ "ckpt_path": "jaxgmg2_3phase_fast/al_0.227_g_0.975_seed_100_pa_1_lr_5e-05",
64
+ "env_steps_per_loop": 614400,
65
+ "total_loops": 3255,
66
+ "eff_acc_steps": 5,
67
+ "env_steps_per_microbatch": 122880,
68
+ "chunk_size": 9600
69
+ },
70
+ "setup": {
71
+ "start_time_utc": "2026-01-28T06:38:52.862251Z",
72
+ "seed": 100,
73
+ "device": "cuda",
74
+ "python_version": "3.11.11",
75
+ "torch_version": "2.10.0+cu128",
76
+ "jax_version": "0.6.2",
77
+ "hostname": "6cee14fefde0",
78
+ "platform": "Linux-6.8.0-59-generic-x86_64-with-glibc2.35",
79
+ "git_sha": null,
80
+ "git_branch": null,
81
+ "use_wandb": true
82
+ }
83
+ }
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/setup.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ Start: 2026-01-28T06:38:52.862251Z
2
+ Seed: 100
3
+ Device: cuda
4
+ Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
5
+ Host: 6cee14fefde0
6
+ Platform: Linux-6.8.0-59-generic-x86_64-with-glibc2.35
7
+ Git: branch=None sha=None
8
+ use_wandb: True
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/train.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
al_0.227_g_0.975_seed_100_pa_1_lr_5e-05/train.log ADDED
The diff for this file is too large to render. See raw diff