Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- al_0.47_g_0.975_105/action_logprobs.pth.gz +3 -0
- al_0.47_g_0.975_105/action_probs.tar.gz +3 -0
- al_0.47_g_0.975_105/checkpoints.tar.gz +3 -0
- al_0.47_g_0.975_105/config.cfg +57 -0
- al_0.47_g_0.975_105/config.json +59 -0
- al_0.47_g_0.975_105/eval.jsonl +0 -0
- al_0.47_g_0.975_105/eval.log +0 -0
- al_0.47_g_0.975_105/latest_train.json +12 -0
- al_0.47_g_0.975_105/setup.json +74 -0
- al_0.47_g_0.975_105/setup.txt +8 -0
- al_0.47_g_0.975_105/train.jsonl +0 -0
- al_0.47_g_0.975_105/train.log +0 -0
- al_0.47_g_0.975_seed_105_pa_1/action_logprobs.pth.gz +2 -2
- al_0.47_g_0.975_seed_105_pa_1/action_probs.tar.gz +2 -2
- al_0.47_g_0.975_seed_105_pa_1/checkpoints.tar.gz +2 -2
- al_0.47_g_0.975_seed_105_pa_1/config.cfg +1 -1
- al_0.47_g_0.975_seed_105_pa_1/config.json +1 -1
- al_0.47_g_0.975_seed_105_pa_1/eval.jsonl +0 -0
- al_0.47_g_0.975_seed_105_pa_1/eval.log +0 -0
- al_0.47_g_0.975_seed_105_pa_1/latest_train.json +5 -5
- al_0.47_g_0.975_seed_105_pa_1/setup.json +4 -4
- al_0.47_g_0.975_seed_105_pa_1/setup.txt +3 -3
- al_0.47_g_0.975_seed_105_pa_1/train.jsonl +0 -0
- al_0.47_g_0.975_seed_105_pa_1/train.log +0 -0
- al_0.47_g_0.975_seed_106_pa_1/action_probs.tar.gz +2 -2
- al_0.47_g_0.975_seed_106_pa_1/checkpoints.tar.gz +2 -2
- al_0.47_g_0.975_seed_106_pa_1/eval.jsonl +0 -0
- al_0.47_g_0.975_seed_106_pa_1/eval.log +0 -0
- al_0.47_g_0.975_seed_106_pa_1/latest_train.json +2 -2
- al_0.47_g_0.975_seed_106_pa_1/setup.json +3 -3
- al_0.47_g_0.975_seed_106_pa_1/setup.txt +3 -3
- al_0.47_g_0.975_seed_106_pa_1/train.jsonl +0 -0
- al_0.47_g_0.975_seed_106_pa_1/train.log +0 -0
- al_0.47_g_0.975_seed_107_pa_1/action_probs.tar.gz +2 -2
- al_0.47_g_0.975_seed_107_pa_1/checkpoints.tar.gz +2 -2
- al_0.47_g_0.975_seed_107_pa_1/eval.jsonl +0 -0
- al_0.47_g_0.975_seed_107_pa_1/eval.log +0 -0
- al_0.47_g_0.975_seed_107_pa_1/latest_train.json +3 -3
- al_0.47_g_0.975_seed_107_pa_1/setup.json +3 -3
- al_0.47_g_0.975_seed_107_pa_1/setup.txt +3 -3
- al_0.47_g_0.975_seed_107_pa_1/train.jsonl +0 -0
- al_0.47_g_0.975_seed_107_pa_1/train.log +0 -0
- al_0.47_g_0.975_seed_108_pa_1/action_probs.tar.gz +2 -2
- al_0.47_g_0.975_seed_108_pa_1/checkpoints.tar.gz +2 -2
- al_0.47_g_0.975_seed_108_pa_1/eval.jsonl +0 -0
- al_0.47_g_0.975_seed_108_pa_1/eval.log +0 -0
- al_0.47_g_0.975_seed_108_pa_1/latest_train.json +2 -2
- al_0.47_g_0.975_seed_108_pa_1/setup.json +3 -3
- al_0.47_g_0.975_seed_108_pa_1/setup.txt +3 -3
- al_0.47_g_0.975_seed_108_pa_1/train.jsonl +0 -0
al_0.47_g_0.975_105/action_logprobs.pth.gz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d405d20a0faada114ff16cb25d72430fc443c724665c0595fe55afcd57240dde
|
| 3 |
+
size 66812271
|
al_0.47_g_0.975_105/action_probs.tar.gz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c00fcab158938c363c7f16c6050b75ecfe7f73badbed7f7d3bef61f857a6d1a5
|
| 3 |
+
size 26112435
|
al_0.47_g_0.975_105/checkpoints.tar.gz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10ee0dfe6e4aac93b25e389945f63c8c77028d3014af9ed18afc71f34c9e58a2
|
| 3 |
+
size 644916740
|
al_0.47_g_0.975_105/config.cfg
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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=5000000000
|
| 11 |
+
checkpoint=al_0.47_g_0.975_105
|
| 12 |
+
render_sixel=False
|
| 13 |
+
sixel_idx=60
|
| 14 |
+
seed=105
|
| 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=0:1,250:2,500:5,1000:10,2000:20
|
| 22 |
+
grad_acc_per_chunk=5
|
| 23 |
+
num_rollout_chunks=1
|
| 24 |
+
cheese_loc=any
|
| 25 |
+
env_layout=open
|
| 26 |
+
alpha=0.47
|
| 27 |
+
env_size=13
|
| 28 |
+
num_levels=9600
|
| 29 |
+
f_str_ckpt=al_{alpha}_g_{discount_rate}_{seed}
|
| 30 |
+
wandb_project=jaxgmg2_3phase_seed
|
| 31 |
+
ckpt_dir=jaxgmg2_3phase_seed
|
| 32 |
+
duplication_factor=-1
|
| 33 |
+
smoke=False
|
| 34 |
+
compile=True
|
| 35 |
+
num_chains=6
|
| 36 |
+
num_draws=3000
|
| 37 |
+
num_steps_bw_draws=1
|
| 38 |
+
on_policy=True
|
| 39 |
+
llc_nbeta=3000
|
| 40 |
+
localization=10
|
| 41 |
+
exact_solver_each_draw=False
|
| 42 |
+
llc_optimizer=sgld
|
| 43 |
+
iw_clip_eps=None
|
| 44 |
+
rmsprop_burnin_steps=20
|
| 45 |
+
llc_data_file=llc_scan_open_reinforce.pkl
|
| 46 |
+
llc_checkpoint_index=None
|
| 47 |
+
llc_checkpoint_number=None
|
| 48 |
+
sink=None
|
| 49 |
+
repo_id=davidquarel/jaxgmg_ckpt_zip
|
| 50 |
+
use_shuffled_checkpoints=False
|
| 51 |
+
force_re_download=False
|
| 52 |
+
off_distribution_data=False
|
| 53 |
+
weight_restrictions=None
|
| 54 |
+
weight_restrictions_invert=False
|
| 55 |
+
evaluate_every_position=False
|
| 56 |
+
use_prev_action=False
|
| 57 |
+
num_prev_actions=1
|
al_0.47_g_0.975_105/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha": 0.47,
|
| 3 |
+
"checkpoint": "al_0.47_g_0.975_105",
|
| 4 |
+
"cheese_loc": "any",
|
| 5 |
+
"ckpt_dir": "jaxgmg2_3phase_seed",
|
| 6 |
+
"compile": true,
|
| 7 |
+
"deterministic": true,
|
| 8 |
+
"discount_rate": 0.975,
|
| 9 |
+
"duplication_factor": -1,
|
| 10 |
+
"eff_horizon": null,
|
| 11 |
+
"env_layout": "open",
|
| 12 |
+
"env_size": 13,
|
| 13 |
+
"eval_every": 1,
|
| 14 |
+
"eval_schedule": "0:1,250:2,500:5,1000:10,2000:20",
|
| 15 |
+
"evaluate_every_position": false,
|
| 16 |
+
"exact_solver_each_draw": false,
|
| 17 |
+
"f_str_ckpt": "al_{alpha}_g_{discount_rate}_{seed}",
|
| 18 |
+
"force_re_download": false,
|
| 19 |
+
"grad_acc_per_chunk": 5,
|
| 20 |
+
"iw_clip_eps": null,
|
| 21 |
+
"live_monitor": false,
|
| 22 |
+
"llc_checkpoint_index": null,
|
| 23 |
+
"llc_checkpoint_number": null,
|
| 24 |
+
"llc_data_file": "llc_scan_open_reinforce.pkl",
|
| 25 |
+
"llc_nbeta": 3000,
|
| 26 |
+
"llc_optimizer": "sgld",
|
| 27 |
+
"localization": 10,
|
| 28 |
+
"lr": 5e-05,
|
| 29 |
+
"mask_type": "first_episode",
|
| 30 |
+
"num_chains": 6,
|
| 31 |
+
"num_draws": 3000,
|
| 32 |
+
"num_levels": 9600,
|
| 33 |
+
"num_prev_actions": 1,
|
| 34 |
+
"num_rollout_chunks": 1,
|
| 35 |
+
"num_rollout_steps": 64,
|
| 36 |
+
"num_steps_bw_draws": 1,
|
| 37 |
+
"num_total_env_steps": 5000000000,
|
| 38 |
+
"off_distribution_data": false,
|
| 39 |
+
"on_policy": true,
|
| 40 |
+
"optim": "adam",
|
| 41 |
+
"penalize_time": false,
|
| 42 |
+
"render_sixel": false,
|
| 43 |
+
"repo_id": "davidquarel/jaxgmg_ckpt_zip",
|
| 44 |
+
"rl_action": "train",
|
| 45 |
+
"rmsprop_burnin_steps": 20,
|
| 46 |
+
"seed": 105,
|
| 47 |
+
"sink": null,
|
| 48 |
+
"sixel_idx": 60,
|
| 49 |
+
"smoke": false,
|
| 50 |
+
"use_bf16": false,
|
| 51 |
+
"use_hf": true,
|
| 52 |
+
"use_log": true,
|
| 53 |
+
"use_prev_action": false,
|
| 54 |
+
"use_shuffled_checkpoints": false,
|
| 55 |
+
"use_wandb": true,
|
| 56 |
+
"wandb_project": "jaxgmg2_3phase_seed",
|
| 57 |
+
"weight_restrictions": null,
|
| 58 |
+
"weight_restrictions_invert": false
|
| 59 |
+
}
|
al_0.47_g_0.975_105/eval.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_105/eval.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_105/latest_train.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ts": "2026-01-24T10:34:16.910677Z",
|
| 3 |
+
"loop": 8137,
|
| 4 |
+
"env_steps": 4999987199,
|
| 5 |
+
"loss": 0.002025768393650651,
|
| 6 |
+
"avg_return": 0.5442076325416565,
|
| 7 |
+
"regret": 0.7529319524765015,
|
| 8 |
+
"entropy": 0.04175533726811409,
|
| 9 |
+
"lr": 5e-05,
|
| 10 |
+
"discount_rate": 0.975,
|
| 11 |
+
"num_rollout_steps": 64
|
| 12 |
+
}
|
al_0.47_g_0.975_105/setup.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 5000000000,
|
| 13 |
+
"checkpoint": "al_0.47_g_0.975_105",
|
| 14 |
+
"render_sixel": false,
|
| 15 |
+
"sixel_idx": 60,
|
| 16 |
+
"seed": 105,
|
| 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": "0:1,250:2,500:5,1000:10,2000:20",
|
| 24 |
+
"grad_acc_per_chunk": 5,
|
| 25 |
+
"num_rollout_chunks": 1,
|
| 26 |
+
"cheese_loc": "any",
|
| 27 |
+
"env_layout": "open",
|
| 28 |
+
"alpha": 0.47,
|
| 29 |
+
"env_size": 13,
|
| 30 |
+
"num_levels": 9600,
|
| 31 |
+
"f_str_ckpt": "al_{alpha}_g_{discount_rate}_{seed}",
|
| 32 |
+
"wandb_project": "jaxgmg2_3phase_seed",
|
| 33 |
+
"ckpt_dir": "jaxgmg2_3phase_seed",
|
| 34 |
+
"duplication_factor": -1,
|
| 35 |
+
"smoke": false,
|
| 36 |
+
"compile": true,
|
| 37 |
+
"num_chains": 6,
|
| 38 |
+
"num_draws": 3000,
|
| 39 |
+
"num_steps_bw_draws": 1,
|
| 40 |
+
"on_policy": true,
|
| 41 |
+
"llc_nbeta": 3000,
|
| 42 |
+
"localization": 10,
|
| 43 |
+
"exact_solver_each_draw": false,
|
| 44 |
+
"llc_optimizer": "sgld",
|
| 45 |
+
"iw_clip_eps": null,
|
| 46 |
+
"rmsprop_burnin_steps": 20,
|
| 47 |
+
"llc_data_file": "llc_scan_open_reinforce.pkl",
|
| 48 |
+
"llc_checkpoint_index": null,
|
| 49 |
+
"llc_checkpoint_number": null,
|
| 50 |
+
"sink": null,
|
| 51 |
+
"repo_id": "davidquarel/jaxgmg_ckpt_zip",
|
| 52 |
+
"use_shuffled_checkpoints": false,
|
| 53 |
+
"force_re_download": false,
|
| 54 |
+
"off_distribution_data": false,
|
| 55 |
+
"weight_restrictions": null,
|
| 56 |
+
"weight_restrictions_invert": false,
|
| 57 |
+
"evaluate_every_position": false,
|
| 58 |
+
"use_prev_action": false,
|
| 59 |
+
"num_prev_actions": 1
|
| 60 |
+
},
|
| 61 |
+
"setup": {
|
| 62 |
+
"start_time_utc": "2026-01-24T08:37:56.174273Z",
|
| 63 |
+
"seed": 105,
|
| 64 |
+
"device": "cuda",
|
| 65 |
+
"python_version": "3.11.11",
|
| 66 |
+
"torch_version": "2.10.0+cu128",
|
| 67 |
+
"jax_version": "0.6.2",
|
| 68 |
+
"hostname": "5a72857b6734",
|
| 69 |
+
"platform": "Linux-5.15.0-164-generic-x86_64-with-glibc2.35",
|
| 70 |
+
"git_sha": null,
|
| 71 |
+
"git_branch": null,
|
| 72 |
+
"use_wandb": true
|
| 73 |
+
}
|
| 74 |
+
}
|
al_0.47_g_0.975_105/setup.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Start: 2026-01-24T08:37:56.174273Z
|
| 2 |
+
Seed: 105
|
| 3 |
+
Device: cuda
|
| 4 |
+
Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
|
| 5 |
+
Host: 5a72857b6734
|
| 6 |
+
Platform: Linux-5.15.0-164-generic-x86_64-with-glibc2.35
|
| 7 |
+
Git: branch=None sha=None
|
| 8 |
+
use_wandb: True
|
al_0.47_g_0.975_105/train.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_105/train.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_105_pa_1/action_logprobs.pth.gz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c12bf031269eccf077d2a7fada5a08b538abca881cbe3e1785b49f84d88a747c
|
| 3 |
+
size 66773090
|
al_0.47_g_0.975_seed_105_pa_1/action_probs.tar.gz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f73fb2d9efd72751a655ac27712e76c009cb8419a3d22836f021f32d77037a84
|
| 3 |
+
size 26112336
|
al_0.47_g_0.975_seed_105_pa_1/checkpoints.tar.gz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:805fb7c15ee8c42c3e649f0a0ef52af4f0c09565e6c4dd9d8fca04d141fbca27
|
| 3 |
+
size 644916792
|
al_0.47_g_0.975_seed_105_pa_1/config.cfg
CHANGED
|
@@ -53,6 +53,6 @@ off_distribution_data=False
|
|
| 53 |
weight_restrictions=None
|
| 54 |
weight_restrictions_invert=False
|
| 55 |
evaluate_every_position=False
|
| 56 |
-
use_prev_action=
|
| 57 |
num_prev_actions=1
|
| 58 |
ntfy=david_jaxgmg
|
|
|
|
| 53 |
weight_restrictions=None
|
| 54 |
weight_restrictions_invert=False
|
| 55 |
evaluate_every_position=False
|
| 56 |
+
use_prev_action=False
|
| 57 |
num_prev_actions=1
|
| 58 |
ntfy=david_jaxgmg
|
al_0.47_g_0.975_seed_105_pa_1/config.json
CHANGED
|
@@ -51,7 +51,7 @@
|
|
| 51 |
"use_bf16": false,
|
| 52 |
"use_hf": true,
|
| 53 |
"use_log": true,
|
| 54 |
-
"use_prev_action":
|
| 55 |
"use_shuffled_checkpoints": false,
|
| 56 |
"use_wandb": true,
|
| 57 |
"wandb_project": "jaxgmg2_3phase_seed",
|
|
|
|
| 51 |
"use_bf16": false,
|
| 52 |
"use_hf": true,
|
| 53 |
"use_log": true,
|
| 54 |
+
"use_prev_action": false,
|
| 55 |
"use_shuffled_checkpoints": false,
|
| 56 |
"use_wandb": true,
|
| 57 |
"wandb_project": "jaxgmg2_3phase_seed",
|
al_0.47_g_0.975_seed_105_pa_1/eval.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_105_pa_1/eval.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_105_pa_1/latest_train.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"ts": "2026-01-
|
| 3 |
"loop": 8137,
|
| 4 |
"env_steps": 4999987199,
|
| 5 |
-
"loss": 0.
|
| 6 |
-
"avg_return": 0.
|
| 7 |
-
"regret": 0.
|
| 8 |
-
"entropy": 0.
|
| 9 |
"lr": 5e-05,
|
| 10 |
"discount_rate": 0.975,
|
| 11 |
"num_rollout_steps": 64
|
|
|
|
| 1 |
{
|
| 2 |
+
"ts": "2026-01-25T10:23:43.652843Z",
|
| 3 |
"loop": 8137,
|
| 4 |
"env_steps": 4999987199,
|
| 5 |
+
"loss": 0.002025768393650651,
|
| 6 |
+
"avg_return": 0.5442076325416565,
|
| 7 |
+
"regret": 0.7529319524765015,
|
| 8 |
+
"entropy": 0.04175533726811409,
|
| 9 |
"lr": 5e-05,
|
| 10 |
"discount_rate": 0.975,
|
| 11 |
"num_rollout_steps": 64
|
al_0.47_g_0.975_seed_105_pa_1/setup.json
CHANGED
|
@@ -55,19 +55,19 @@
|
|
| 55 |
"weight_restrictions": null,
|
| 56 |
"weight_restrictions_invert": false,
|
| 57 |
"evaluate_every_position": false,
|
| 58 |
-
"use_prev_action":
|
| 59 |
"num_prev_actions": 1,
|
| 60 |
"ntfy": "david_jaxgmg"
|
| 61 |
},
|
| 62 |
"setup": {
|
| 63 |
-
"start_time_utc": "2026-01-
|
| 64 |
"seed": 105,
|
| 65 |
"device": "cuda",
|
| 66 |
"python_version": "3.11.11",
|
| 67 |
"torch_version": "2.10.0+cu128",
|
| 68 |
"jax_version": "0.6.2",
|
| 69 |
-
"hostname": "
|
| 70 |
-
"platform": "Linux-
|
| 71 |
"git_sha": null,
|
| 72 |
"git_branch": null,
|
| 73 |
"use_wandb": true
|
|
|
|
| 55 |
"weight_restrictions": null,
|
| 56 |
"weight_restrictions_invert": false,
|
| 57 |
"evaluate_every_position": false,
|
| 58 |
+
"use_prev_action": false,
|
| 59 |
"num_prev_actions": 1,
|
| 60 |
"ntfy": "david_jaxgmg"
|
| 61 |
},
|
| 62 |
"setup": {
|
| 63 |
+
"start_time_utc": "2026-01-25T08:26:35.661617Z",
|
| 64 |
"seed": 105,
|
| 65 |
"device": "cuda",
|
| 66 |
"python_version": "3.11.11",
|
| 67 |
"torch_version": "2.10.0+cu128",
|
| 68 |
"jax_version": "0.6.2",
|
| 69 |
+
"hostname": "5a72857b6734",
|
| 70 |
+
"platform": "Linux-5.15.0-164-generic-x86_64-with-glibc2.35",
|
| 71 |
"git_sha": null,
|
| 72 |
"git_branch": null,
|
| 73 |
"use_wandb": true
|
al_0.47_g_0.975_seed_105_pa_1/setup.txt
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
-
Start: 2026-01-
|
| 2 |
Seed: 105
|
| 3 |
Device: cuda
|
| 4 |
Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
|
| 5 |
-
Host:
|
| 6 |
-
Platform: Linux-
|
| 7 |
Git: branch=None sha=None
|
| 8 |
use_wandb: True
|
|
|
|
| 1 |
+
Start: 2026-01-25T08:26:35.661617Z
|
| 2 |
Seed: 105
|
| 3 |
Device: cuda
|
| 4 |
Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
|
| 5 |
+
Host: 5a72857b6734
|
| 6 |
+
Platform: Linux-5.15.0-164-generic-x86_64-with-glibc2.35
|
| 7 |
Git: branch=None sha=None
|
| 8 |
use_wandb: True
|
al_0.47_g_0.975_seed_105_pa_1/train.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_105_pa_1/train.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_106_pa_1/action_probs.tar.gz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa2ae6e5c80257c15769f34429161c88655aad5bf652c4956f3c2566b0e845d5
|
| 3 |
+
size 27173631
|
al_0.47_g_0.975_seed_106_pa_1/checkpoints.tar.gz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14bb57262110aa0cbe3b6349f3608087068083723ab51e60909313663c69c5b4
|
| 3 |
+
size 644696492
|
al_0.47_g_0.975_seed_106_pa_1/eval.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_106_pa_1/eval.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_106_pa_1/latest_train.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"ts": "2026-01-
|
| 3 |
"loop": 8137,
|
| 4 |
"env_steps": 4999987199,
|
| 5 |
"loss": 0.00011000235099345446,
|
| 6 |
"avg_return": 0.5428342819213867,
|
| 7 |
-
"regret": 0.
|
| 8 |
"entropy": 0.009456370957195759,
|
| 9 |
"lr": 5e-05,
|
| 10 |
"discount_rate": 0.975,
|
|
|
|
| 1 |
{
|
| 2 |
+
"ts": "2026-01-25T12:21:46.846635Z",
|
| 3 |
"loop": 8137,
|
| 4 |
"env_steps": 4999987199,
|
| 5 |
"loss": 0.00011000235099345446,
|
| 6 |
"avg_return": 0.5428342819213867,
|
| 7 |
+
"regret": 0.7053660154342651,
|
| 8 |
"entropy": 0.009456370957195759,
|
| 9 |
"lr": 5e-05,
|
| 10 |
"discount_rate": 0.975,
|
al_0.47_g_0.975_seed_106_pa_1/setup.json
CHANGED
|
@@ -60,14 +60,14 @@
|
|
| 60 |
"ntfy": "david_jaxgmg"
|
| 61 |
},
|
| 62 |
"setup": {
|
| 63 |
-
"start_time_utc": "2026-01-
|
| 64 |
"seed": 106,
|
| 65 |
"device": "cuda",
|
| 66 |
"python_version": "3.11.11",
|
| 67 |
"torch_version": "2.10.0+cu128",
|
| 68 |
"jax_version": "0.6.2",
|
| 69 |
-
"hostname": "
|
| 70 |
-
"platform": "Linux-
|
| 71 |
"git_sha": null,
|
| 72 |
"git_branch": null,
|
| 73 |
"use_wandb": true
|
|
|
|
| 60 |
"ntfy": "david_jaxgmg"
|
| 61 |
},
|
| 62 |
"setup": {
|
| 63 |
+
"start_time_utc": "2026-01-25T10:24:47.727928Z",
|
| 64 |
"seed": 106,
|
| 65 |
"device": "cuda",
|
| 66 |
"python_version": "3.11.11",
|
| 67 |
"torch_version": "2.10.0+cu128",
|
| 68 |
"jax_version": "0.6.2",
|
| 69 |
+
"hostname": "5a72857b6734",
|
| 70 |
+
"platform": "Linux-5.15.0-164-generic-x86_64-with-glibc2.35",
|
| 71 |
"git_sha": null,
|
| 72 |
"git_branch": null,
|
| 73 |
"use_wandb": true
|
al_0.47_g_0.975_seed_106_pa_1/setup.txt
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
-
Start: 2026-01-
|
| 2 |
Seed: 106
|
| 3 |
Device: cuda
|
| 4 |
Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
|
| 5 |
-
Host:
|
| 6 |
-
Platform: Linux-
|
| 7 |
Git: branch=None sha=None
|
| 8 |
use_wandb: True
|
|
|
|
| 1 |
+
Start: 2026-01-25T10:24:47.727928Z
|
| 2 |
Seed: 106
|
| 3 |
Device: cuda
|
| 4 |
Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
|
| 5 |
+
Host: 5a72857b6734
|
| 6 |
+
Platform: Linux-5.15.0-164-generic-x86_64-with-glibc2.35
|
| 7 |
Git: branch=None sha=None
|
| 8 |
use_wandb: True
|
al_0.47_g_0.975_seed_106_pa_1/train.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_106_pa_1/train.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_107_pa_1/action_probs.tar.gz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21d7aca17d31b2951bf49fa48d5e9a07eaa244fd39faf51b68553560fb1fbf36
|
| 3 |
+
size 22889683
|
al_0.47_g_0.975_seed_107_pa_1/checkpoints.tar.gz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b912ccedc6dcc47c155f694305fc9f042f28fd830d6c7b660d07df3afcd1dc64
|
| 3 |
+
size 644704197
|
al_0.47_g_0.975_seed_107_pa_1/eval.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_107_pa_1/eval.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_107_pa_1/latest_train.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"ts": "2026-01-
|
| 3 |
"loop": 8137,
|
| 4 |
-
"env_steps":
|
| 5 |
"loss": 0.0006763355922885239,
|
| 6 |
"avg_return": 0.5420774221420288,
|
| 7 |
-
"regret": 0.
|
| 8 |
"entropy": 0.039437636733055115,
|
| 9 |
"lr": 5e-05,
|
| 10 |
"discount_rate": 0.975,
|
|
|
|
| 1 |
{
|
| 2 |
+
"ts": "2026-01-25T14:19:46.782534Z",
|
| 3 |
"loop": 8137,
|
| 4 |
+
"env_steps": 4999987199,
|
| 5 |
"loss": 0.0006763355922885239,
|
| 6 |
"avg_return": 0.5420774221420288,
|
| 7 |
+
"regret": 0.706595778465271,
|
| 8 |
"entropy": 0.039437636733055115,
|
| 9 |
"lr": 5e-05,
|
| 10 |
"discount_rate": 0.975,
|
al_0.47_g_0.975_seed_107_pa_1/setup.json
CHANGED
|
@@ -60,14 +60,14 @@
|
|
| 60 |
"ntfy": "david_jaxgmg"
|
| 61 |
},
|
| 62 |
"setup": {
|
| 63 |
-
"start_time_utc": "2026-01-
|
| 64 |
"seed": 107,
|
| 65 |
"device": "cuda",
|
| 66 |
"python_version": "3.11.11",
|
| 67 |
"torch_version": "2.10.0+cu128",
|
| 68 |
"jax_version": "0.6.2",
|
| 69 |
-
"hostname": "
|
| 70 |
-
"platform": "Linux-5.15.0-
|
| 71 |
"git_sha": null,
|
| 72 |
"git_branch": null,
|
| 73 |
"use_wandb": true
|
|
|
|
| 60 |
"ntfy": "david_jaxgmg"
|
| 61 |
},
|
| 62 |
"setup": {
|
| 63 |
+
"start_time_utc": "2026-01-25T12:22:45.119462Z",
|
| 64 |
"seed": 107,
|
| 65 |
"device": "cuda",
|
| 66 |
"python_version": "3.11.11",
|
| 67 |
"torch_version": "2.10.0+cu128",
|
| 68 |
"jax_version": "0.6.2",
|
| 69 |
+
"hostname": "5a72857b6734",
|
| 70 |
+
"platform": "Linux-5.15.0-164-generic-x86_64-with-glibc2.35",
|
| 71 |
"git_sha": null,
|
| 72 |
"git_branch": null,
|
| 73 |
"use_wandb": true
|
al_0.47_g_0.975_seed_107_pa_1/setup.txt
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
-
Start: 2026-01-
|
| 2 |
Seed: 107
|
| 3 |
Device: cuda
|
| 4 |
Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
|
| 5 |
-
Host:
|
| 6 |
-
Platform: Linux-5.15.0-
|
| 7 |
Git: branch=None sha=None
|
| 8 |
use_wandb: True
|
|
|
|
| 1 |
+
Start: 2026-01-25T12:22:45.119462Z
|
| 2 |
Seed: 107
|
| 3 |
Device: cuda
|
| 4 |
Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
|
| 5 |
+
Host: 5a72857b6734
|
| 6 |
+
Platform: Linux-5.15.0-164-generic-x86_64-with-glibc2.35
|
| 7 |
Git: branch=None sha=None
|
| 8 |
use_wandb: True
|
al_0.47_g_0.975_seed_107_pa_1/train.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_107_pa_1/train.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_108_pa_1/action_probs.tar.gz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:070ace0b70e1cf353488122d379bcd8c529e88297720b20c436716e32664a75e
|
| 3 |
+
size 23538427
|
al_0.47_g_0.975_seed_108_pa_1/checkpoints.tar.gz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86aab2294e20e77a430dc954deb5a2334531cc4140c465b969523c669f445391
|
| 3 |
+
size 644838058
|
al_0.47_g_0.975_seed_108_pa_1/eval.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_108_pa_1/eval.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
al_0.47_g_0.975_seed_108_pa_1/latest_train.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"ts": "2026-01-
|
| 3 |
"loop": 8137,
|
| 4 |
"env_steps": 4999987199,
|
| 5 |
"loss": 0.001199210062623024,
|
| 6 |
"avg_return": 0.5378735661506653,
|
| 7 |
-
"regret": 0.
|
| 8 |
"entropy": 0.031318098306655884,
|
| 9 |
"lr": 5e-05,
|
| 10 |
"discount_rate": 0.975,
|
|
|
|
| 1 |
{
|
| 2 |
+
"ts": "2026-01-25T16:19:56.697944Z",
|
| 3 |
"loop": 8137,
|
| 4 |
"env_steps": 4999987199,
|
| 5 |
"loss": 0.001199210062623024,
|
| 6 |
"avg_return": 0.5378735661506653,
|
| 7 |
+
"regret": 0.7057788372039795,
|
| 8 |
"entropy": 0.031318098306655884,
|
| 9 |
"lr": 5e-05,
|
| 10 |
"discount_rate": 0.975,
|
al_0.47_g_0.975_seed_108_pa_1/setup.json
CHANGED
|
@@ -60,14 +60,14 @@
|
|
| 60 |
"ntfy": "david_jaxgmg"
|
| 61 |
},
|
| 62 |
"setup": {
|
| 63 |
-
"start_time_utc": "2026-01-
|
| 64 |
"seed": 108,
|
| 65 |
"device": "cuda",
|
| 66 |
"python_version": "3.11.11",
|
| 67 |
"torch_version": "2.10.0+cu128",
|
| 68 |
"jax_version": "0.6.2",
|
| 69 |
-
"hostname": "
|
| 70 |
-
"platform": "Linux-
|
| 71 |
"git_sha": null,
|
| 72 |
"git_branch": null,
|
| 73 |
"use_wandb": true
|
|
|
|
| 60 |
"ntfy": "david_jaxgmg"
|
| 61 |
},
|
| 62 |
"setup": {
|
| 63 |
+
"start_time_utc": "2026-01-25T14:21:38.612709Z",
|
| 64 |
"seed": 108,
|
| 65 |
"device": "cuda",
|
| 66 |
"python_version": "3.11.11",
|
| 67 |
"torch_version": "2.10.0+cu128",
|
| 68 |
"jax_version": "0.6.2",
|
| 69 |
+
"hostname": "5a72857b6734",
|
| 70 |
+
"platform": "Linux-5.15.0-164-generic-x86_64-with-glibc2.35",
|
| 71 |
"git_sha": null,
|
| 72 |
"git_branch": null,
|
| 73 |
"use_wandb": true
|
al_0.47_g_0.975_seed_108_pa_1/setup.txt
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
-
Start: 2026-01-
|
| 2 |
Seed: 108
|
| 3 |
Device: cuda
|
| 4 |
Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
|
| 5 |
-
Host:
|
| 6 |
-
Platform: Linux-
|
| 7 |
Git: branch=None sha=None
|
| 8 |
use_wandb: True
|
|
|
|
| 1 |
+
Start: 2026-01-25T14:21:38.612709Z
|
| 2 |
Seed: 108
|
| 3 |
Device: cuda
|
| 4 |
Python: 3.11.11 | Torch: 2.10.0+cu128 | JAX: 0.6.2
|
| 5 |
+
Host: 5a72857b6734
|
| 6 |
+
Platform: Linux-5.15.0-164-generic-x86_64-with-glibc2.35
|
| 7 |
Git: branch=None sha=None
|
| 8 |
use_wandb: True
|
al_0.47_g_0.975_seed_108_pa_1/train.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|