Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/.hydra/config.yaml +161 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/.hydra/hydra.yaml +155 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/.hydra/overrides.yaml +1 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=2600-test_success_rate=0.620.ckpt +3 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=2950-test_success_rate=0.620.ckpt +3 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=3300-test_success_rate=0.620.ckpt +3 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=3550-test_success_rate=0.600.ckpt +3 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=3650-test_success_rate=0.600.ckpt +3 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/latest.ckpt +3 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/logs.json.txt +3 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/train.log +8 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/debug-internal.log +162 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/debug.log +27 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/files/config.yaml +244 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/files/output.log +3 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/files/wandb-metadata.json +56 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/files/wandb-summary.json +1 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug-core.log +14 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug-internal.log +162 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug.log +27 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/run-a0y1jzsf.wandb +3 -0
- 2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/wandb-resume.json +1 -0
.gitattributes
CHANGED
|
@@ -45,3 +45,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 45 |
2026.10.04/17.15.34_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261004_171543-pnv1tivo/run-pnv1tivo.wandb filter=lfs diff=lfs merge=lfs -text
|
| 46 |
2026.10.05/14.05.16_train_diffusion_unet_lowdim_FrankaKitchen-v1/logs.json.txt filter=lfs diff=lfs merge=lfs -text
|
| 47 |
2026.10.05/14.05.16_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_140524-0iejtsht/run-0iejtsht.wandb filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 45 |
2026.10.04/17.15.34_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261004_171543-pnv1tivo/run-pnv1tivo.wandb filter=lfs diff=lfs merge=lfs -text
|
| 46 |
2026.10.05/14.05.16_train_diffusion_unet_lowdim_FrankaKitchen-v1/logs.json.txt filter=lfs diff=lfs merge=lfs -text
|
| 47 |
2026.10.05/14.05.16_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_140524-0iejtsht/run-0iejtsht.wandb filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/logs.json.txt filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/run-a0y1jzsf.wandb filter=lfs diff=lfs merge=lfs -text
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/.hydra/config.yaml
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
name: train_diffusion_unet_lowdim
|
| 2 |
+
_target_: llmbc.workspace.train_diffusion_unet_lowdim_workspace.TrainDiffusionUnetLowdimWorkspace
|
| 3 |
+
obs_dim: ${task.obs_dim}
|
| 4 |
+
action_dim: ${task.action_dim}
|
| 5 |
+
task_name: ${task.name}
|
| 6 |
+
exp_name: default
|
| 7 |
+
horizon: 16
|
| 8 |
+
n_obs_steps: 2
|
| 9 |
+
n_action_steps: 8
|
| 10 |
+
n_latency_steps: 0
|
| 11 |
+
past_action_visible: false
|
| 12 |
+
keypoint_visible_rate: 1.0
|
| 13 |
+
obs_as_local_cond: false
|
| 14 |
+
obs_as_global_cond: true
|
| 15 |
+
pred_action_steps_only: false
|
| 16 |
+
policy:
|
| 17 |
+
_target_: llmbc.policy.diffusion_unet_lowdim_policy.DiffusionUnetLowdimPolicy
|
| 18 |
+
model:
|
| 19 |
+
_target_: llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D
|
| 20 |
+
input_dim: '${eval: ${task.action_dim} if ${obs_as_local_cond} or ${obs_as_global_cond}
|
| 21 |
+
else ${task.obs_dim} + ${task.action_dim}}'
|
| 22 |
+
local_cond_dim: '${eval: ${task.obs_dim} if ${obs_as_local_cond} else None}'
|
| 23 |
+
global_cond_dim: '${eval: ${task.obs_dim}*${n_obs_steps} if ${obs_as_global_cond}
|
| 24 |
+
else None}'
|
| 25 |
+
diffusion_step_embed_dim: 256
|
| 26 |
+
down_dims:
|
| 27 |
+
- 256
|
| 28 |
+
- 512
|
| 29 |
+
- 1024
|
| 30 |
+
kernel_size: 5
|
| 31 |
+
upsample_kernel_size: 4
|
| 32 |
+
n_groups: 8
|
| 33 |
+
cond_predict_scale: true
|
| 34 |
+
noise_scheduler:
|
| 35 |
+
_target_: diffusers.schedulers.scheduling_ddpm.DDPMScheduler
|
| 36 |
+
num_train_timesteps: 100
|
| 37 |
+
beta_start: 0.0001
|
| 38 |
+
beta_end: 0.02
|
| 39 |
+
beta_schedule: squaredcos_cap_v2
|
| 40 |
+
variance_type: fixed_small
|
| 41 |
+
clip_sample: true
|
| 42 |
+
prediction_type: epsilon
|
| 43 |
+
horizon: ${horizon}
|
| 44 |
+
obs_dim: ${obs_dim}
|
| 45 |
+
action_dim: ${action_dim}
|
| 46 |
+
n_action_steps: ${eval:'${n_action_steps}+${n_latency_steps}'}
|
| 47 |
+
n_obs_steps: ${n_obs_steps}
|
| 48 |
+
num_inference_steps: 10
|
| 49 |
+
obs_as_local_cond: ${obs_as_local_cond}
|
| 50 |
+
obs_as_global_cond: ${obs_as_global_cond}
|
| 51 |
+
pred_action_steps_only: ${pred_action_steps_only}
|
| 52 |
+
oa_step_convention: true
|
| 53 |
+
ema:
|
| 54 |
+
_target_: llmbc.model.diffusion.ema_model.EMAModel
|
| 55 |
+
update_after_step: 0
|
| 56 |
+
inv_gamma: 1.0
|
| 57 |
+
power: 0.75
|
| 58 |
+
min_value: 0.0
|
| 59 |
+
max_value: 0.9999
|
| 60 |
+
dataloader:
|
| 61 |
+
batch_size: 256
|
| 62 |
+
num_workers: 0
|
| 63 |
+
shuffle: true
|
| 64 |
+
pin_memory: false
|
| 65 |
+
persistent_workers: false
|
| 66 |
+
val_dataloader:
|
| 67 |
+
batch_size: 256
|
| 68 |
+
num_workers: 0
|
| 69 |
+
shuffle: false
|
| 70 |
+
pin_memory: false
|
| 71 |
+
persistent_workers: false
|
| 72 |
+
optimizer:
|
| 73 |
+
_target_: torch.optim.AdamW
|
| 74 |
+
lr: 0.0001
|
| 75 |
+
betas:
|
| 76 |
+
- 0.95
|
| 77 |
+
- 0.999
|
| 78 |
+
eps: 1.0e-08
|
| 79 |
+
weight_decay: 1.0e-06
|
| 80 |
+
training:
|
| 81 |
+
device: cuda:0
|
| 82 |
+
seed: 45
|
| 83 |
+
debug: false
|
| 84 |
+
resume: true
|
| 85 |
+
lr_scheduler: cosine
|
| 86 |
+
lr_warmup_steps: 500
|
| 87 |
+
num_epochs: 5001
|
| 88 |
+
gradient_accumulate_every: 1
|
| 89 |
+
use_ema: true
|
| 90 |
+
rollout_every: 50
|
| 91 |
+
checkpoint_every: 50
|
| 92 |
+
val_every: 1
|
| 93 |
+
sample_every: 50
|
| 94 |
+
max_train_steps: null
|
| 95 |
+
max_val_steps: null
|
| 96 |
+
tqdm_interval_sec: 1.0
|
| 97 |
+
logging:
|
| 98 |
+
project: ${task.name}-training
|
| 99 |
+
resume: true
|
| 100 |
+
mode: online
|
| 101 |
+
name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name}
|
| 102 |
+
tags:
|
| 103 |
+
- ${name}
|
| 104 |
+
- ${task_name}
|
| 105 |
+
- ${exp_name}
|
| 106 |
+
id: null
|
| 107 |
+
group: null
|
| 108 |
+
checkpoint:
|
| 109 |
+
topk:
|
| 110 |
+
monitor_key: test_success_rate
|
| 111 |
+
mode: max
|
| 112 |
+
k: 5
|
| 113 |
+
format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt
|
| 114 |
+
save_last_ckpt: true
|
| 115 |
+
save_last_snapshot: false
|
| 116 |
+
multi_run:
|
| 117 |
+
run_dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
|
| 118 |
+
wandb_name_base: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name}
|
| 119 |
+
task:
|
| 120 |
+
name: FrankaKitchen-v1
|
| 121 |
+
obs_dim: 59
|
| 122 |
+
action_dim: 9
|
| 123 |
+
lang_multistep_merger:
|
| 124 |
+
_target_: llfbench.envs.kitchen.multistep_merger.franka_kitchen_merger.KitchenMultistepMerger
|
| 125 |
+
env_runner:
|
| 126 |
+
_target_: llmbc.env_runner.kitchen_lowdim_runner.KitchenLowdimRunner
|
| 127 |
+
env_name: llf-kitchen-FrankaKitchen-v1
|
| 128 |
+
n_train: 10
|
| 129 |
+
n_test: 50
|
| 130 |
+
n_envs: 10
|
| 131 |
+
max_steps: 500
|
| 132 |
+
n_obs_steps: ${n_obs_steps}
|
| 133 |
+
n_action_steps: ${n_action_steps}
|
| 134 |
+
instruction_type: b
|
| 135 |
+
feedback_type:
|
| 136 |
+
- hp
|
| 137 |
+
- hn
|
| 138 |
+
- fp
|
| 139 |
+
tasks_to_complete:
|
| 140 |
+
- microwave
|
| 141 |
+
- kettle
|
| 142 |
+
- light switch
|
| 143 |
+
- slide cabinet
|
| 144 |
+
visual: false
|
| 145 |
+
discount: 0.99
|
| 146 |
+
inference_expert_action: false
|
| 147 |
+
lang_multistep_merger:
|
| 148 |
+
_target_: llfbench.envs.kitchen.multistep_merger.franka_kitchen_merger.KitchenMultistepMerger
|
| 149 |
+
dataset:
|
| 150 |
+
_target_: llmbc.dataset.kitchen_lowdim_dataset.KitchenLowdimDataset
|
| 151 |
+
data_path: datasets/FrankaKitchen-v1.pt
|
| 152 |
+
data_path2: datasets/FrankaKitchen-v1.pt
|
| 153 |
+
horizon: ${horizon}
|
| 154 |
+
pad_before: ${eval:'${n_obs_steps}-1'}
|
| 155 |
+
pad_after: ${eval:'${n_action_steps}-1'}
|
| 156 |
+
obs_eef_target: true
|
| 157 |
+
use_manual_normalizer: false
|
| 158 |
+
val_ratio: 0.05
|
| 159 |
+
dummy_normalizer: false
|
| 160 |
+
instructor:
|
| 161 |
+
_target_: llmbc.translator.instructor.kitchen_instructor.FrankaKitchen_v1_instructor.FrankaKitchenV1Instructor
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/.hydra/hydra.yaml
ADDED
|
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
hydra:
|
| 2 |
+
run:
|
| 3 |
+
dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
|
| 4 |
+
sweep:
|
| 5 |
+
dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
|
| 6 |
+
subdir: ${hydra.job.num}
|
| 7 |
+
launcher:
|
| 8 |
+
_target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
|
| 9 |
+
sweeper:
|
| 10 |
+
_target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
|
| 11 |
+
max_batch_size: null
|
| 12 |
+
params: null
|
| 13 |
+
help:
|
| 14 |
+
app_name: ${hydra.job.name}
|
| 15 |
+
header: '${hydra.help.app_name} is powered by Hydra.
|
| 16 |
+
|
| 17 |
+
'
|
| 18 |
+
footer: 'Powered by Hydra (https://hydra.cc)
|
| 19 |
+
|
| 20 |
+
Use --hydra-help to view Hydra specific help
|
| 21 |
+
|
| 22 |
+
'
|
| 23 |
+
template: '${hydra.help.header}
|
| 24 |
+
|
| 25 |
+
== Configuration groups ==
|
| 26 |
+
|
| 27 |
+
Compose your configuration from those groups (group=option)
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
$APP_CONFIG_GROUPS
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
== Config ==
|
| 34 |
+
|
| 35 |
+
Override anything in the config (foo.bar=value)
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
$CONFIG
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
${hydra.help.footer}
|
| 42 |
+
|
| 43 |
+
'
|
| 44 |
+
hydra_help:
|
| 45 |
+
template: 'Hydra (${hydra.runtime.version})
|
| 46 |
+
|
| 47 |
+
See https://hydra.cc for more info.
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
== Flags ==
|
| 51 |
+
|
| 52 |
+
$FLAGS_HELP
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
== Configuration groups ==
|
| 56 |
+
|
| 57 |
+
Compose your configuration from those groups (For example, append hydra/job_logging=disabled
|
| 58 |
+
to command line)
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
$HYDRA_CONFIG_GROUPS
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
Use ''--cfg hydra'' to Show the Hydra config.
|
| 65 |
+
|
| 66 |
+
'
|
| 67 |
+
hydra_help: ???
|
| 68 |
+
hydra_logging:
|
| 69 |
+
version: 1
|
| 70 |
+
formatters:
|
| 71 |
+
simple:
|
| 72 |
+
format: '[%(asctime)s][HYDRA] %(message)s'
|
| 73 |
+
handlers:
|
| 74 |
+
console:
|
| 75 |
+
class: logging.StreamHandler
|
| 76 |
+
formatter: simple
|
| 77 |
+
stream: ext://sys.stdout
|
| 78 |
+
root:
|
| 79 |
+
level: INFO
|
| 80 |
+
handlers:
|
| 81 |
+
- console
|
| 82 |
+
loggers:
|
| 83 |
+
logging_example:
|
| 84 |
+
level: DEBUG
|
| 85 |
+
disable_existing_loggers: false
|
| 86 |
+
job_logging:
|
| 87 |
+
version: 1
|
| 88 |
+
formatters:
|
| 89 |
+
simple:
|
| 90 |
+
format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
|
| 91 |
+
handlers:
|
| 92 |
+
console:
|
| 93 |
+
class: logging.StreamHandler
|
| 94 |
+
formatter: simple
|
| 95 |
+
stream: ext://sys.stdout
|
| 96 |
+
file:
|
| 97 |
+
class: logging.FileHandler
|
| 98 |
+
formatter: simple
|
| 99 |
+
filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
|
| 100 |
+
root:
|
| 101 |
+
level: INFO
|
| 102 |
+
handlers:
|
| 103 |
+
- console
|
| 104 |
+
- file
|
| 105 |
+
disable_existing_loggers: false
|
| 106 |
+
env: {}
|
| 107 |
+
mode: RUN
|
| 108 |
+
searchpath: []
|
| 109 |
+
callbacks: {}
|
| 110 |
+
output_subdir: .hydra
|
| 111 |
+
overrides:
|
| 112 |
+
hydra:
|
| 113 |
+
- hydra.mode=RUN
|
| 114 |
+
task:
|
| 115 |
+
- training.seed=45
|
| 116 |
+
job:
|
| 117 |
+
name: train
|
| 118 |
+
chdir: null
|
| 119 |
+
override_dirname: training.seed=45
|
| 120 |
+
id: ???
|
| 121 |
+
num: ???
|
| 122 |
+
config_name: dp_FrankaKitchen-v1.yaml
|
| 123 |
+
env_set: {}
|
| 124 |
+
env_copy: []
|
| 125 |
+
config:
|
| 126 |
+
override_dirname:
|
| 127 |
+
kv_sep: '='
|
| 128 |
+
item_sep: ','
|
| 129 |
+
exclude_keys: []
|
| 130 |
+
runtime:
|
| 131 |
+
version: 1.2.0
|
| 132 |
+
version_base: '1.2'
|
| 133 |
+
cwd: /tmp2/chyang/workspace/LLM-BC
|
| 134 |
+
config_sources:
|
| 135 |
+
- path: hydra.conf
|
| 136 |
+
schema: pkg
|
| 137 |
+
provider: hydra
|
| 138 |
+
- path: /tmp2/chyang/workspace/LLM-BC/config/main_table
|
| 139 |
+
schema: file
|
| 140 |
+
provider: main
|
| 141 |
+
- path: ''
|
| 142 |
+
schema: structured
|
| 143 |
+
provider: schema
|
| 144 |
+
output_dir: /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1
|
| 145 |
+
choices:
|
| 146 |
+
hydra/env: default
|
| 147 |
+
hydra/callbacks: null
|
| 148 |
+
hydra/job_logging: default
|
| 149 |
+
hydra/hydra_logging: default
|
| 150 |
+
hydra/hydra_help: default
|
| 151 |
+
hydra/help: default
|
| 152 |
+
hydra/sweeper: basic
|
| 153 |
+
hydra/launcher: basic
|
| 154 |
+
hydra/output: default
|
| 155 |
+
verbose: false
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/.hydra/overrides.yaml
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
- training.seed=45
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=2600-test_success_rate=0.620.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e7d09f74f7bc8c9e44e90fa2ebc49e74c4e81f2ffa06a57dab6ee6cb302907f
|
| 3 |
+
size 1070882738
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=2950-test_success_rate=0.620.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee01864556d3bb6bd4972d0f9068bb9bc2878aa766a67e188574c8a6c92d67f0
|
| 3 |
+
size 1070882738
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=3300-test_success_rate=0.620.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a0947bdd9b9b7bb8aaadac2b97de5e1b280f3967b23348f9b9d9c8f4d0d928a
|
| 3 |
+
size 1070882738
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=3550-test_success_rate=0.600.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59938386a3b42ad7ec9599787d983828a1f9c7167b498d8be1dd1ea7059b9e19
|
| 3 |
+
size 1070882738
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/epoch=3650-test_success_rate=0.600.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:923324641399655346ba3234eedb67111d614c9121a9b5f111354a7a8d99744e
|
| 3 |
+
size 1070882738
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/checkpoints/latest.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:632a2f7de62d98ea5d73cecf4b00991223f46becafc40b08fe8e26a9e096477f
|
| 3 |
+
size 1070882738
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/logs.json.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31f8f843a5fc1fb35478b8b06ad2bba9cd4924c22ee879c5b022dc6662d3bb2c
|
| 3 |
+
size 261639513
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/train.log
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[2026-10-05 13:45:51,044][numexpr.utils][INFO] - Note: NumExpr detected 40 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 16.
|
| 2 |
+
[2026-10-05 13:45:51,045][numexpr.utils][INFO] - NumExpr defaulting to 16 threads.
|
| 3 |
+
[2026-10-05 13:45:53,584][llmbc.model.diffusion.conditional_unet1d][INFO] - number of parameters: 6.691406e+07
|
| 4 |
+
[2026-10-05 13:45:58,157][absl][INFO] - MUJOCO_GL=osmesa, attempting to import specified OpenGL backend.
|
| 5 |
+
[2026-10-05 13:45:58,161][absl][INFO] - MuJoCo library version is: 2.3.7
|
| 6 |
+
[2026-10-05 13:45:58,232][datasets][INFO] - PyTorch version 2.2.2 available.
|
| 7 |
+
[2026-10-05 13:45:58,232][datasets][INFO] - TensorFlow version 2.15.1 available.
|
| 8 |
+
[2026-10-05 13:45:58,233][datasets][INFO] - JAX version 0.4.30 available.
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/debug-internal.log
ADDED
|
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"time":"2026-10-05T13:45:59.163355915+08:00","level":"INFO","msg":"using version","core version":"0.18.6"}
|
| 2 |
+
{"time":"2026-10-05T13:45:59.163364924+08:00","level":"INFO","msg":"created symlink","path":"/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug-core.log"}
|
| 3 |
+
{"time":"2026-10-05T13:45:59.269047163+08:00","level":"INFO","msg":"created new stream","id":"a0y1jzsf"}
|
| 4 |
+
{"time":"2026-10-05T13:45:59.269111886+08:00","level":"INFO","msg":"stream: started","id":"a0y1jzsf"}
|
| 5 |
+
{"time":"2026-10-05T13:45:59.269178689+08:00","level":"INFO","msg":"handler: started","stream_id":{"value":"a0y1jzsf"}}
|
| 6 |
+
{"time":"2026-10-05T13:45:59.269379864+08:00","level":"INFO","msg":"sender: started","stream_id":"a0y1jzsf"}
|
| 7 |
+
{"time":"2026-10-05T13:45:59.269168469+08:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"a0y1jzsf"}}
|
| 8 |
+
{"time":"2026-10-05T13:46:00.434351743+08:00","level":"INFO","msg":"Starting system monitor"}
|
| 9 |
+
{"time":"2026-10-06T00:55:17.233211224+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": read tcp 192.168.11.41:58154->34.8.250.101:443: read: connection reset by peer"}
|
| 10 |
+
{"time":"2026-10-06T09:25:04.216906944+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 11 |
+
{"time":"2026-10-06T09:25:15.252828409+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp 34.8.250.101:443: connect: no route to host"}
|
| 12 |
+
{"time":"2026-10-06T09:25:26.397707765+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:39419->127.0.0.53:53: i/o timeout"}
|
| 13 |
+
{"time":"2026-10-06T09:25:36.667141225+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 14 |
+
{"time":"2026-10-06T09:25:36.756524289+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 15 |
+
{"time":"2026-10-06T09:25:54.045717582+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:60142->127.0.0.53:53: i/o timeout"}
|
| 16 |
+
{"time":"2026-10-06T09:26:10.833705525+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 17 |
+
{"time":"2026-10-06T09:26:19.764617144+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 18 |
+
{"time":"2026-10-06T09:26:50.502002568+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 19 |
+
{"time":"2026-10-06T09:26:57.698292324+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 20 |
+
{"time":"2026-10-06T09:27:39.461033137+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 21 |
+
{"time":"2026-10-06T09:28:07.699959385+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:50452->127.0.0.53:53: i/o timeout"}
|
| 22 |
+
{"time":"2026-10-06T09:28:43.153942633+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 23 |
+
{"time":"2026-10-06T09:29:17.703107112+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:36665->127.0.0.53:53: i/o timeout"}
|
| 24 |
+
{"time":"2026-10-06T09:30:13.15448044+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 25 |
+
{"time":"2026-10-06T09:30:27.705770185+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:42721->127.0.0.53:53: i/o timeout"}
|
| 26 |
+
{"time":"2026-10-06T09:31:37.708864611+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:43878->127.0.0.53:53: i/o timeout"}
|
| 27 |
+
{"time":"2026-10-06T09:31:43.15597339+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 28 |
+
{"time":"2026-10-06T09:32:47.710960866+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:46731->127.0.0.53:53: i/o timeout"}
|
| 29 |
+
{"time":"2026-10-06T09:33:13.157227823+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 30 |
+
{"time":"2026-10-06T09:33:57.71429012+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:38521->127.0.0.53:53: i/o timeout"}
|
| 31 |
+
{"time":"2026-10-06T09:34:34.218070669+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000912319,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"8lx8hbxpiv60\" connection_id:\"127.0.0.1:51142\")"}
|
| 32 |
+
{"time":"2026-10-06T09:34:35.701292599+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000212389,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 33 |
+
{"time":"2026-10-06T09:34:40.436056895+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000583931,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 34 |
+
{"time":"2026-10-06T09:34:40.436161283+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000713944,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 35 |
+
{"time":"2026-10-06T09:34:40.438335724+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000227179,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 36 |
+
{"time":"2026-10-06T09:34:40.439452019+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000451924,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 37 |
+
{"time":"2026-10-06T09:34:40.4395116+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000070491,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 38 |
+
{"time":"2026-10-06T09:34:43.158026918+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 39 |
+
{"time":"2026-10-06T09:35:07.716961743+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:57595->127.0.0.53:53: i/o timeout"}
|
| 40 |
+
{"time":"2026-10-06T09:36:13.159016826+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 41 |
+
{"time":"2026-10-06T09:36:17.72009588+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:37109->127.0.0.53:53: i/o timeout"}
|
| 42 |
+
{"time":"2026-10-06T09:37:27.722522334+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34984->127.0.0.53:53: i/o timeout"}
|
| 43 |
+
{"time":"2026-10-06T09:37:43.161342328+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 44 |
+
{"time":"2026-10-06T09:38:37.726080975+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:57156->127.0.0.53:53: i/o timeout"}
|
| 45 |
+
{"time":"2026-10-06T09:39:13.162840088+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 46 |
+
{"time":"2026-10-06T09:39:47.728677821+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59728->127.0.0.53:53: i/o timeout"}
|
| 47 |
+
{"time":"2026-10-06T09:40:43.164031242+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 48 |
+
{"time":"2026-10-06T09:40:57.730952264+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:42114->127.0.0.53:53: i/o timeout"}
|
| 49 |
+
{"time":"2026-10-06T09:41:53.16702903+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54374->127.0.0.53:53: i/o timeout"}
|
| 50 |
+
{"time":"2026-10-06T09:42:07.73436387+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:50668->127.0.0.53:53: i/o timeout"}
|
| 51 |
+
{"time":"2026-10-06T09:43:03.16922781+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54076->127.0.0.53:53: i/o timeout"}
|
| 52 |
+
{"time":"2026-10-06T09:43:17.736868037+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:55535->127.0.0.53:53: i/o timeout"}
|
| 53 |
+
{"time":"2026-10-06T09:44:13.171973988+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:36098->127.0.0.53:53: i/o timeout"}
|
| 54 |
+
{"time":"2026-10-06T09:44:27.739336521+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54781->127.0.0.53:53: i/o timeout"}
|
| 55 |
+
{"time":"2026-10-06T09:44:34.239471319+08:00","level":"WARN","msg":"sender: taking a long time","seconds":1200.022912721,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"8lx8hbxpiv60\" connection_id:\"127.0.0.1:51142\")"}
|
| 56 |
+
{"time":"2026-10-06T09:44:35.70342383+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.002371121,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 57 |
+
{"time":"2026-10-06T09:44:40.436779533+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.001288564,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 58 |
+
{"time":"2026-10-06T09:44:40.436895391+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.001441669,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 59 |
+
{"time":"2026-10-06T09:44:40.439087859+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.00097571,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 60 |
+
{"time":"2026-10-06T09:44:40.440188055+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.000730352,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 61 |
+
{"time":"2026-10-06T09:44:40.440189578+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.001201081,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 62 |
+
{"time":"2026-10-06T09:45:23.174036006+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:32808->127.0.0.53:53: i/o timeout"}
|
| 63 |
+
{"time":"2026-10-06T09:45:37.74262234+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:57118->127.0.0.53:53: i/o timeout"}
|
| 64 |
+
{"time":"2026-10-06T09:46:33.175647107+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34142->127.0.0.53:53: i/o timeout"}
|
| 65 |
+
{"time":"2026-10-06T09:46:47.744827673+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:38788->127.0.0.53:53: i/o timeout"}
|
| 66 |
+
{"time":"2026-10-06T09:47:43.178129417+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:51485->127.0.0.53:53: i/o timeout"}
|
| 67 |
+
{"time":"2026-10-06T09:47:57.747348679+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:41227->127.0.0.53:53: i/o timeout"}
|
| 68 |
+
{"time":"2026-10-06T09:48:53.180282859+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58661->127.0.0.53:53: i/o timeout"}
|
| 69 |
+
{"time":"2026-10-06T09:48:53.180492936+08:00","level":"ERROR","msg":"sender: sendStopStatus: failed to get run stopped status: api: failed sending: POST https://api.wandb.ai/graphql giving up after 21 attempt(s): Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58661->127.0.0.53:53: i/o timeout"}
|
| 70 |
+
{"time":"2026-10-06T09:48:53.182181928+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":1458.965629728,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"8lx8hbxpiv60\" connection_id:\"127.0.0.1:51142\")"}
|
| 71 |
+
{"time":"2026-10-06T09:48:53.182330263+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1457.481319991,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 72 |
+
{"time":"2026-10-06T09:48:53.182428528+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.746976632,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 73 |
+
{"time":"2026-10-06T09:48:53.182475062+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.744278468,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 74 |
+
{"time":"2026-10-06T09:48:53.182446719+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.742950553,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 75 |
+
{"time":"2026-10-06T09:48:53.182566064+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.743523327,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 76 |
+
{"time":"2026-10-06T09:48:53.182440969+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.746942282,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 77 |
+
{"time":"2026-10-06T09:49:03.31098711+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:52560->127.0.0.53:53: i/o timeout"}
|
| 78 |
+
{"time":"2026-10-06T09:49:03.311014342+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:52560->127.0.0.53:53: i/o timeout"}
|
| 79 |
+
{"time":"2026-10-06T09:49:15.51000472+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:46088->127.0.0.53:53: i/o timeout"}
|
| 80 |
+
{"time":"2026-10-06T09:49:30.220917721+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:43837->127.0.0.53:53: i/o timeout"}
|
| 81 |
+
{"time":"2026-10-06T09:49:49.577054247+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:51242->127.0.0.53:53: i/o timeout"}
|
| 82 |
+
{"time":"2026-10-06T09:50:08.787118718+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 83 |
+
{"time":"2026-10-06T09:50:08.7871671+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 84 |
+
{"time":"2026-10-06T09:50:57.235008055+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59888->127.0.0.53:53: i/o timeout"}
|
| 85 |
+
{"time":"2026-10-06T09:51:18.790095596+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:45443->127.0.0.53:53: i/o timeout"}
|
| 86 |
+
{"time":"2026-10-06T09:52:07.238034763+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:60728->127.0.0.53:53: i/o timeout"}
|
| 87 |
+
{"time":"2026-10-06T09:52:28.793223924+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54344->127.0.0.53:53: i/o timeout"}
|
| 88 |
+
{"time":"2026-10-06T09:53:17.241303288+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59484->127.0.0.53:53: i/o timeout"}
|
| 89 |
+
{"time":"2026-10-06T09:53:38.795011432+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:50171->127.0.0.53:53: i/o timeout"}
|
| 90 |
+
{"time":"2026-10-06T09:54:27.244118673+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59227->127.0.0.53:53: i/o timeout"}
|
| 91 |
+
{"time":"2026-10-06T09:54:48.797972117+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:45997->127.0.0.53:53: i/o timeout"}
|
| 92 |
+
{"time":"2026-10-06T09:55:37.247023164+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34908->127.0.0.53:53: i/o timeout"}
|
| 93 |
+
{"time":"2026-10-06T09:55:58.800364514+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:49683->127.0.0.53:53: i/o timeout"}
|
| 94 |
+
{"time":"2026-10-06T09:56:47.249888902+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:60992->127.0.0.53:53: i/o timeout"}
|
| 95 |
+
{"time":"2026-10-06T09:57:08.802311113+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:53471->127.0.0.53:53: i/o timeout"}
|
| 96 |
+
{"time":"2026-10-06T09:57:57.252954476+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:40719->127.0.0.53:53: i/o timeout"}
|
| 97 |
+
{"time":"2026-10-06T09:58:17.085117628+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59879->127.0.0.53:53: i/o timeout"}
|
| 98 |
+
{"time":"2026-10-06T09:58:23.228954725+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:48731->127.0.0.53:53: i/o timeout"}
|
| 99 |
+
{"time":"2026-10-06T09:58:53.310509872+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000650079,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"gplclwr5yrv3\" connection_id:\"127.0.0.1:51142\")"}
|
| 100 |
+
{"time":"2026-10-06T09:58:54.728910487+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000849739,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 101 |
+
{"time":"2026-10-06T09:59:00.435880525+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00045047,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 102 |
+
{"time":"2026-10-06T09:59:00.43601939+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000525846,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 103 |
+
{"time":"2026-10-06T09:59:00.438191073+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00039204,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 104 |
+
{"time":"2026-10-06T09:59:00.438198711+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000120136,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 105 |
+
{"time":"2026-10-06T09:59:00.439335822+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000417846,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 106 |
+
{"time":"2026-10-06T09:59:05.085657873+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:46257->127.0.0.53:53: i/o timeout"}
|
| 107 |
+
{"time":"2026-10-06T09:59:32.673067475+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:38517->127.0.0.53:53: i/o timeout"}
|
| 108 |
+
{"time":"2026-10-06T10:00:15.088446059+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:42397->127.0.0.53:53: i/o timeout"}
|
| 109 |
+
{"time":"2026-10-06T10:00:42.675974984+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:33976->127.0.0.53:53: i/o timeout"}
|
| 110 |
+
{"time":"2026-10-06T10:01:25.090369352+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:41435->127.0.0.53:53: i/o timeout"}
|
| 111 |
+
{"time":"2026-10-06T10:01:52.679257229+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:37099->127.0.0.53:53: i/o timeout"}
|
| 112 |
+
{"time":"2026-10-06T10:02:35.093533054+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:43216->127.0.0.53:53: i/o timeout"}
|
| 113 |
+
{"time":"2026-10-06T10:03:02.682033223+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58548->127.0.0.53:53: i/o timeout"}
|
| 114 |
+
{"time":"2026-10-06T10:03:45.095777469+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:50451->127.0.0.53:53: i/o timeout"}
|
| 115 |
+
{"time":"2026-10-06T10:04:12.685307219+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:56278->127.0.0.53:53: i/o timeout"}
|
| 116 |
+
{"time":"2026-10-06T10:04:55.099256898+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:48863->127.0.0.53:53: i/o timeout"}
|
| 117 |
+
{"time":"2026-10-06T10:05:22.688113437+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:49585->127.0.0.53:53: i/o timeout"}
|
| 118 |
+
{"time":"2026-10-06T10:06:05.101706688+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:40857->127.0.0.53:53: i/o timeout"}
|
| 119 |
+
{"time":"2026-10-06T10:06:30.469216735+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 120 |
+
{"time":"2026-10-06T10:07:05.891669426+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":1092.581635314,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"gplclwr5yrv3\" connection_id:\"127.0.0.1:51142\")"}
|
| 121 |
+
{"time":"2026-10-06T10:07:05.891847858+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1091.163881748,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 122 |
+
{"time":"2026-10-06T10:07:05.89194221+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.456543256,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 123 |
+
{"time":"2026-10-06T10:07:05.892005599+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.456550335,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 124 |
+
{"time":"2026-10-06T10:07:05.892078977+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.454229769,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 125 |
+
{"time":"2026-10-06T10:07:05.892165516+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.454052586,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 126 |
+
{"time":"2026-10-06T10:07:05.892249043+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.45331293,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 127 |
+
{"time":"2026-10-06T10:08:20.896007012+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
|
| 128 |
+
{"time":"2026-10-06T10:08:52.988732973+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 129 |
+
{"time":"2026-10-06T10:09:27.388072917+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 130 |
+
{"time":"2026-10-06T10:10:07.176838085+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 131 |
+
{"time":"2026-10-06T10:10:54.373793246+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 132 |
+
{"time":"2026-10-06T10:12:02.60384915+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 133 |
+
{"time":"2026-10-06T10:13:32.605053705+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 134 |
+
{"time":"2026-10-06T10:15:02.606602306+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 135 |
+
{"time":"2026-10-06T10:16:32.608834641+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 136 |
+
{"time":"2026-10-06T10:17:50.89575474+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000208414,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"ckfgj8ye2snm\" connection_id:\"127.0.0.1:51142\")"}
|
| 137 |
+
{"time":"2026-10-06T10:17:52.434840284+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000559945,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 138 |
+
{"time":"2026-10-06T10:18:00.43574907+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000133108,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 139 |
+
{"time":"2026-10-06T10:18:00.435792208+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000401175,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 140 |
+
{"time":"2026-10-06T10:18:00.438949663+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000530324,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 141 |
+
{"time":"2026-10-06T10:18:00.438965768+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000356572,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 142 |
+
{"time":"2026-10-06T10:18:00.439011938+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00004734,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 143 |
+
{"time":"2026-10-06T10:18:02.610833003+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 144 |
+
{"time":"2026-10-06T10:19:32.611778582+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 145 |
+
{"time":"2026-10-06T10:21:02.61382365+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 146 |
+
{"time":"2026-10-06T10:22:32.615544993+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 147 |
+
{"time":"2026-10-06T10:23:42.963766085+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": read tcp 192.168.11.41:41968->34.8.250.101:443: read: network is unreachable"}
|
| 148 |
+
{"time":"2026-10-06T10:24:43.875271386+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":1012.979744627,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"ckfgj8ye2snm\" connection_id:\"127.0.0.1:51142\")"}
|
| 149 |
+
{"time":"2026-10-06T10:24:43.875689942+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1011.441443372,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 150 |
+
{"time":"2026-10-06T10:24:43.875721175+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.440111468,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 151 |
+
{"time":"2026-10-06T10:24:43.875814017+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.437401986,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 152 |
+
{"time":"2026-10-06T10:24:43.875746082+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.440385756,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 153 |
+
{"time":"2026-10-06T10:24:43.875852672+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.436850157,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 154 |
+
{"time":"2026-10-06T10:24:43.876036242+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.437415844,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 155 |
+
{"time":"2026-10-06T13:19:59.039120309+08:00","level":"INFO","msg":"stream: closing","id":"a0y1jzsf"}
|
| 156 |
+
{"time":"2026-10-06T13:19:59.039154305+08:00","level":"INFO","msg":"Stopping system monitor"}
|
| 157 |
+
{"time":"2026-10-06T13:19:59.111492217+08:00","level":"INFO","msg":"Stopped system monitor"}
|
| 158 |
+
{"time":"2026-10-06T13:20:00.866016279+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
|
| 159 |
+
{"time":"2026-10-06T13:20:01.218067036+08:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"a0y1jzsf"}}
|
| 160 |
+
{"time":"2026-10-06T13:20:01.21814782+08:00","level":"INFO","msg":"sender: closed","stream_id":"a0y1jzsf"}
|
| 161 |
+
{"time":"2026-10-06T13:20:01.218137984+08:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"a0y1jzsf"}}
|
| 162 |
+
{"time":"2026-10-06T13:20:01.218298956+08:00","level":"INFO","msg":"stream: closed","id":"a0y1jzsf"}
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/debug.log
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Current SDK version is 0.18.6
|
| 2 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Configure stats pid to 1342604
|
| 3 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/.config/wandb/settings
|
| 4 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Loading settings from /tmp2/chyang/workspace/LLM-BC/wandb/settings
|
| 5 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
|
| 6 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': 'online', '_disable_service': None}
|
| 7 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train.py', 'program_abspath': '/tmp2/chyang/workspace/LLM-BC/train.py', 'program': '/tmp2/chyang/workspace/LLM-BC/./train.py'}
|
| 8 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Applying login settings: {}
|
| 9 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:_log_setup():533] Logging user logs to /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug.log
|
| 10 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:_log_setup():534] Logging internal logs to /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug-internal.log
|
| 11 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:init():619] calling init triggers
|
| 12 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
|
| 13 |
+
config: {'name': 'train_diffusion_unet_lowdim', '_target_': 'llmbc.workspace.train_diffusion_unet_lowdim_workspace.TrainDiffusionUnetLowdimWorkspace', 'obs_dim': 59, 'action_dim': 9, 'task_name': 'FrankaKitchen-v1', 'exp_name': 'default', 'horizon': 16, 'n_obs_steps': 2, 'n_action_steps': 8, 'n_latency_steps': 0, 'past_action_visible': False, 'keypoint_visible_rate': 1.0, 'obs_as_local_cond': False, 'obs_as_global_cond': True, 'pred_action_steps_only': False, 'policy': {'_target_': 'llmbc.policy.diffusion_unet_lowdim_policy.DiffusionUnetLowdimPolicy', 'model': {'_target_': 'llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D', 'input_dim': 9, 'local_cond_dim': None, 'global_cond_dim': 118, 'diffusion_step_embed_dim': 256, 'down_dims': [256, 512, 1024], 'kernel_size': 5, 'upsample_kernel_size': 4, 'n_groups': 8, 'cond_predict_scale': True}, 'noise_scheduler': {'_target_': 'diffusers.schedulers.scheduling_ddpm.DDPMScheduler', 'num_train_timesteps': 100, 'beta_start': 0.0001, 'beta_end': 0.02, 'beta_schedule': 'squaredcos_cap_v2', 'variance_type': 'fixed_small', 'clip_sample': True, 'prediction_type': 'epsilon'}, 'horizon': 16, 'obs_dim': 59, 'action_dim': 9, 'n_action_steps': 8, 'n_obs_steps': 2, 'num_inference_steps': 10, 'obs_as_local_cond': False, 'obs_as_global_cond': True, 'pred_action_steps_only': False, 'oa_step_convention': True}, 'ema': {'_target_': 'llmbc.model.diffusion.ema_model.EMAModel', 'update_after_step': 0, 'inv_gamma': 1.0, 'power': 0.75, 'min_value': 0.0, 'max_value': 0.9999}, 'dataloader': {'batch_size': 256, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'val_dataloader': {'batch_size': 256, 'num_workers': 0, 'shuffle': False, 'pin_memory': False, 'persistent_workers': False}, 'optimizer': {'_target_': 'torch.optim.AdamW', 'lr': 0.0001, 'betas': [0.95, 0.999], 'eps': 1e-08, 'weight_decay': 1e-06}, 'training': {'device': 'cuda:0', 'seed': 45, 'debug': False, 'resume': True, 'lr_scheduler': 'cosine', 'lr_warmup_steps': 500, 'num_epochs': 5001, 'gradient_accumulate_every': 1, 'use_ema': True, 'rollout_every': 50, 'checkpoint_every': 50, 'val_every': 1, 'sample_every': 50, 'max_train_steps': None, 'max_val_steps': None, 'tqdm_interval_sec': 1.0}, 'logging': {'project': 'FrankaKitchen-v1-training', 'resume': True, 'mode': 'online', 'name': '2026.10.05-13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1', 'tags': ['train_diffusion_unet_lowdim', 'FrankaKitchen-v1', 'default'], 'id': None, 'group': None}, 'checkpoint': {'topk': {'monitor_key': 'test_success_rate', 'mode': 'max', 'k': 5, 'format_str': 'epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt'}, 'save_last_ckpt': True, 'save_last_snapshot': False}, 'multi_run': {'run_dir': 'data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1', 'wandb_name_base': '2026.10.05-13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1'}, 'task': {'name': 'FrankaKitchen-v1', 'obs_dim': 59, 'action_dim': 9, 'lang_multistep_merger': {'_target_': 'llfbench.envs.kitchen.multistep_merger.franka_kitchen_merger.KitchenMultistepMerger'}, 'env_runner': {'_target_': 'llmbc.env_runner.kitchen_lowdim_runner.KitchenLowdimRunner', 'env_name': 'llf-kitchen-FrankaKitchen-v1', 'n_train': 10, 'n_test': 50, 'n_envs': 10, 'max_steps': 500, 'n_obs_steps': 2, 'n_action_steps': 8, 'instruction_type': 'b', 'feedback_type': ['hp', 'hn', 'fp'], 'tasks_to_complete': ['microwave', 'kettle', 'light switch', 'slide cabinet'], 'visual': False, 'discount': 0.99, 'inference_expert_action': False, 'lang_multistep_merger': {'_target_': 'llfbench.envs.kitchen.multistep_merger.franka_kitchen_merger.KitchenMultistepMerger'}}, 'dataset': {'_target_': 'llmbc.dataset.kitchen_lowdim_dataset.KitchenLowdimDataset', 'data_path': 'datasets/FrankaKitchen-v1.pt', 'data_path2': 'datasets/FrankaKitchen-v1.pt', 'horizon': 16, 'pad_before': 1, 'pad_after': 7, 'obs_eef_target': True, 'use_manual_normalizer': False, 'val_ratio': 0.05, 'dummy_normalizer': False}, 'instructor': {'_target_': 'llmbc.translator.instructor.kitchen_instructor.FrankaKitchen_v1_instructor.FrankaKitchenV1Instructor'}}}
|
| 14 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:init():669] starting backend
|
| 15 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:init():673] sending inform_init request
|
| 16 |
+
2026-10-05 13:45:59,162 INFO MainThread:1342604 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
|
| 17 |
+
2026-10-05 13:45:59,162 INFO MainThread:1342604 [wandb_init.py:init():686] backend started and connected
|
| 18 |
+
2026-10-05 13:45:59,171 INFO MainThread:1342604 [wandb_init.py:init():781] updated telemetry
|
| 19 |
+
2026-10-05 13:45:59,287 INFO MainThread:1342604 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
|
| 20 |
+
2026-10-05 13:46:00,431 INFO MainThread:1342604 [wandb_init.py:init():867] starting run threads in backend
|
| 21 |
+
2026-10-05 13:46:00,735 INFO MainThread:1342604 [wandb_run.py:_console_start():2451] atexit reg
|
| 22 |
+
2026-10-05 13:46:00,735 INFO MainThread:1342604 [wandb_run.py:_redirect():2299] redirect: wrap_raw
|
| 23 |
+
2026-10-05 13:46:00,735 INFO MainThread:1342604 [wandb_run.py:_redirect():2364] Wrapping output streams.
|
| 24 |
+
2026-10-05 13:46:00,735 INFO MainThread:1342604 [wandb_run.py:_redirect():2389] Redirects installed.
|
| 25 |
+
2026-10-05 13:46:00,736 INFO MainThread:1342604 [wandb_init.py:init():911] run started, returning control to user process
|
| 26 |
+
2026-10-05 13:46:00,737 INFO MainThread:1342604 [wandb_run.py:_config_callback():1389] config_cb None None {'output_dir': '/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1'}
|
| 27 |
+
2026-10-06 13:19:59,039 WARNING MsgRouterThr:1342604 [router.py:message_loop():75] message_loop has been closed
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/files/config.yaml
ADDED
|
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_target_:
|
| 2 |
+
value: llmbc.workspace.train_diffusion_unet_lowdim_workspace.TrainDiffusionUnetLowdimWorkspace
|
| 3 |
+
_wandb:
|
| 4 |
+
value:
|
| 5 |
+
cli_version: 0.18.6
|
| 6 |
+
m: []
|
| 7 |
+
python_version: 3.9.23
|
| 8 |
+
t:
|
| 9 |
+
"1":
|
| 10 |
+
- 1
|
| 11 |
+
- 2
|
| 12 |
+
- 3
|
| 13 |
+
- 5
|
| 14 |
+
- 11
|
| 15 |
+
- 12
|
| 16 |
+
- 41
|
| 17 |
+
- 49
|
| 18 |
+
- 50
|
| 19 |
+
- 51
|
| 20 |
+
- 53
|
| 21 |
+
- 55
|
| 22 |
+
- 71
|
| 23 |
+
- 83
|
| 24 |
+
- 95
|
| 25 |
+
- 98
|
| 26 |
+
- 100
|
| 27 |
+
- 105
|
| 28 |
+
"2":
|
| 29 |
+
- 1
|
| 30 |
+
- 2
|
| 31 |
+
- 3
|
| 32 |
+
- 5
|
| 33 |
+
- 11
|
| 34 |
+
- 12
|
| 35 |
+
- 41
|
| 36 |
+
- 49
|
| 37 |
+
- 50
|
| 38 |
+
- 51
|
| 39 |
+
- 53
|
| 40 |
+
- 55
|
| 41 |
+
- 71
|
| 42 |
+
- 83
|
| 43 |
+
- 95
|
| 44 |
+
- 98
|
| 45 |
+
- 100
|
| 46 |
+
- 105
|
| 47 |
+
"3":
|
| 48 |
+
- 13
|
| 49 |
+
- 15
|
| 50 |
+
- 16
|
| 51 |
+
- 23
|
| 52 |
+
- 55
|
| 53 |
+
- 61
|
| 54 |
+
"4": 3.9.23
|
| 55 |
+
"5": 0.18.6
|
| 56 |
+
"6": 4.47.1
|
| 57 |
+
"8":
|
| 58 |
+
- 5
|
| 59 |
+
"12": 0.18.6
|
| 60 |
+
"13": linux-x86_64
|
| 61 |
+
action_dim:
|
| 62 |
+
value: 9
|
| 63 |
+
checkpoint:
|
| 64 |
+
value:
|
| 65 |
+
save_last_ckpt: true
|
| 66 |
+
save_last_snapshot: false
|
| 67 |
+
topk:
|
| 68 |
+
format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt
|
| 69 |
+
k: 5
|
| 70 |
+
mode: max
|
| 71 |
+
monitor_key: test_success_rate
|
| 72 |
+
dataloader:
|
| 73 |
+
value:
|
| 74 |
+
batch_size: 256
|
| 75 |
+
num_workers: 0
|
| 76 |
+
persistent_workers: false
|
| 77 |
+
pin_memory: false
|
| 78 |
+
shuffle: true
|
| 79 |
+
ema:
|
| 80 |
+
value:
|
| 81 |
+
_target_: llmbc.model.diffusion.ema_model.EMAModel
|
| 82 |
+
inv_gamma: 1
|
| 83 |
+
max_value: 0.9999
|
| 84 |
+
min_value: 0
|
| 85 |
+
power: 0.75
|
| 86 |
+
update_after_step: 0
|
| 87 |
+
exp_name:
|
| 88 |
+
value: default
|
| 89 |
+
horizon:
|
| 90 |
+
value: 16
|
| 91 |
+
keypoint_visible_rate:
|
| 92 |
+
value: 1
|
| 93 |
+
logging:
|
| 94 |
+
value:
|
| 95 |
+
group: null
|
| 96 |
+
id: null
|
| 97 |
+
mode: online
|
| 98 |
+
name: 2026.10.05-13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1
|
| 99 |
+
project: FrankaKitchen-v1-training
|
| 100 |
+
resume: true
|
| 101 |
+
tags:
|
| 102 |
+
- train_diffusion_unet_lowdim
|
| 103 |
+
- FrankaKitchen-v1
|
| 104 |
+
- default
|
| 105 |
+
multi_run:
|
| 106 |
+
value:
|
| 107 |
+
run_dir: data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1
|
| 108 |
+
wandb_name_base: 2026.10.05-13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1
|
| 109 |
+
n_action_steps:
|
| 110 |
+
value: 8
|
| 111 |
+
n_latency_steps:
|
| 112 |
+
value: 0
|
| 113 |
+
n_obs_steps:
|
| 114 |
+
value: 2
|
| 115 |
+
name:
|
| 116 |
+
value: train_diffusion_unet_lowdim
|
| 117 |
+
obs_as_global_cond:
|
| 118 |
+
value: true
|
| 119 |
+
obs_as_local_cond:
|
| 120 |
+
value: false
|
| 121 |
+
obs_dim:
|
| 122 |
+
value: 59
|
| 123 |
+
optimizer:
|
| 124 |
+
value:
|
| 125 |
+
_target_: torch.optim.AdamW
|
| 126 |
+
betas:
|
| 127 |
+
- 0.95
|
| 128 |
+
- 0.999
|
| 129 |
+
eps: 1e-08
|
| 130 |
+
lr: 0.0001
|
| 131 |
+
weight_decay: 1e-06
|
| 132 |
+
output_dir:
|
| 133 |
+
value: /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1
|
| 134 |
+
past_action_visible:
|
| 135 |
+
value: false
|
| 136 |
+
policy:
|
| 137 |
+
value:
|
| 138 |
+
_target_: llmbc.policy.diffusion_unet_lowdim_policy.DiffusionUnetLowdimPolicy
|
| 139 |
+
action_dim: 9
|
| 140 |
+
horizon: 16
|
| 141 |
+
model:
|
| 142 |
+
_target_: llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D
|
| 143 |
+
cond_predict_scale: true
|
| 144 |
+
diffusion_step_embed_dim: 256
|
| 145 |
+
down_dims:
|
| 146 |
+
- 256
|
| 147 |
+
- 512
|
| 148 |
+
- 1024
|
| 149 |
+
global_cond_dim: 118
|
| 150 |
+
input_dim: 9
|
| 151 |
+
kernel_size: 5
|
| 152 |
+
local_cond_dim: null
|
| 153 |
+
n_groups: 8
|
| 154 |
+
upsample_kernel_size: 4
|
| 155 |
+
n_action_steps: 8
|
| 156 |
+
n_obs_steps: 2
|
| 157 |
+
noise_scheduler:
|
| 158 |
+
_target_: diffusers.schedulers.scheduling_ddpm.DDPMScheduler
|
| 159 |
+
beta_end: 0.02
|
| 160 |
+
beta_schedule: squaredcos_cap_v2
|
| 161 |
+
beta_start: 0.0001
|
| 162 |
+
clip_sample: true
|
| 163 |
+
num_train_timesteps: 100
|
| 164 |
+
prediction_type: epsilon
|
| 165 |
+
variance_type: fixed_small
|
| 166 |
+
num_inference_steps: 10
|
| 167 |
+
oa_step_convention: true
|
| 168 |
+
obs_as_global_cond: true
|
| 169 |
+
obs_as_local_cond: false
|
| 170 |
+
obs_dim: 59
|
| 171 |
+
pred_action_steps_only: false
|
| 172 |
+
pred_action_steps_only:
|
| 173 |
+
value: false
|
| 174 |
+
task:
|
| 175 |
+
value:
|
| 176 |
+
action_dim: 9
|
| 177 |
+
dataset:
|
| 178 |
+
_target_: llmbc.dataset.kitchen_lowdim_dataset.KitchenLowdimDataset
|
| 179 |
+
data_path: datasets/FrankaKitchen-v1.pt
|
| 180 |
+
data_path2: datasets/FrankaKitchen-v1.pt
|
| 181 |
+
dummy_normalizer: false
|
| 182 |
+
horizon: 16
|
| 183 |
+
obs_eef_target: true
|
| 184 |
+
pad_after: 7
|
| 185 |
+
pad_before: 1
|
| 186 |
+
use_manual_normalizer: false
|
| 187 |
+
val_ratio: 0.05
|
| 188 |
+
env_runner:
|
| 189 |
+
_target_: llmbc.env_runner.kitchen_lowdim_runner.KitchenLowdimRunner
|
| 190 |
+
discount: 0.99
|
| 191 |
+
env_name: llf-kitchen-FrankaKitchen-v1
|
| 192 |
+
feedback_type:
|
| 193 |
+
- hp
|
| 194 |
+
- hn
|
| 195 |
+
- fp
|
| 196 |
+
inference_expert_action: false
|
| 197 |
+
instruction_type: b
|
| 198 |
+
lang_multistep_merger:
|
| 199 |
+
_target_: llfbench.envs.kitchen.multistep_merger.franka_kitchen_merger.KitchenMultistepMerger
|
| 200 |
+
max_steps: 500
|
| 201 |
+
n_action_steps: 8
|
| 202 |
+
n_envs: 10
|
| 203 |
+
n_obs_steps: 2
|
| 204 |
+
n_test: 50
|
| 205 |
+
n_train: 10
|
| 206 |
+
tasks_to_complete:
|
| 207 |
+
- microwave
|
| 208 |
+
- kettle
|
| 209 |
+
- light switch
|
| 210 |
+
- slide cabinet
|
| 211 |
+
visual: false
|
| 212 |
+
instructor:
|
| 213 |
+
_target_: llmbc.translator.instructor.kitchen_instructor.FrankaKitchen_v1_instructor.FrankaKitchenV1Instructor
|
| 214 |
+
lang_multistep_merger:
|
| 215 |
+
_target_: llfbench.envs.kitchen.multistep_merger.franka_kitchen_merger.KitchenMultistepMerger
|
| 216 |
+
name: FrankaKitchen-v1
|
| 217 |
+
obs_dim: 59
|
| 218 |
+
task_name:
|
| 219 |
+
value: FrankaKitchen-v1
|
| 220 |
+
training:
|
| 221 |
+
value:
|
| 222 |
+
checkpoint_every: 50
|
| 223 |
+
debug: false
|
| 224 |
+
device: cuda:0
|
| 225 |
+
gradient_accumulate_every: 1
|
| 226 |
+
lr_scheduler: cosine
|
| 227 |
+
lr_warmup_steps: 500
|
| 228 |
+
max_train_steps: null
|
| 229 |
+
max_val_steps: null
|
| 230 |
+
num_epochs: 5001
|
| 231 |
+
resume: true
|
| 232 |
+
rollout_every: 50
|
| 233 |
+
sample_every: 50
|
| 234 |
+
seed: 45
|
| 235 |
+
tqdm_interval_sec: 1
|
| 236 |
+
use_ema: true
|
| 237 |
+
val_every: 1
|
| 238 |
+
val_dataloader:
|
| 239 |
+
value:
|
| 240 |
+
batch_size: 256
|
| 241 |
+
num_workers: 0
|
| 242 |
+
persistent_workers: false
|
| 243 |
+
pin_memory: false
|
| 244 |
+
shuffle: false
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/files/output.log
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Eval KitchenLowdimRunner 1/6: 0%| | 0/500 [00:00<?, ?it/s]/tmp2/chyang/workspace/LLM-BC/llmbc/common/llfbench_util.py:43: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:275.)
|
| 2 |
+
obs = torch.tensor(obs, dtype=torch.float32).unsqueeze(dim=0).to(device)
|
| 3 |
+
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/files/wandb-metadata.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"os": "Linux-6.8.0-139-generic-x86_64-with-glibc2.39",
|
| 3 |
+
"python": "3.9.23",
|
| 4 |
+
"startedAt": "2026-10-05T05:45:59.163218Z",
|
| 5 |
+
"args": [
|
| 6 |
+
"--config-path",
|
| 7 |
+
"config/main_table",
|
| 8 |
+
"--config-name",
|
| 9 |
+
"dp_FrankaKitchen-v1.yaml",
|
| 10 |
+
"training.seed=45"
|
| 11 |
+
],
|
| 12 |
+
"program": "/tmp2/chyang/workspace/LLM-BC/./train.py",
|
| 13 |
+
"codePath": "train.py",
|
| 14 |
+
"git": {
|
| 15 |
+
"remote": "https://github.com/CHYang25/LLM-BC.git",
|
| 16 |
+
"commit": "0387ae9461c25cfb52eee0b8b2c4eaeca0f29642"
|
| 17 |
+
},
|
| 18 |
+
"email": "chris920325@gmail.com",
|
| 19 |
+
"root": "/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1",
|
| 20 |
+
"host": "rllab1015",
|
| 21 |
+
"username": "chyang",
|
| 22 |
+
"executable": "/home/chyang/miniconda3/envs/llm-bc/bin/python3",
|
| 23 |
+
"codePathLocal": "train.py",
|
| 24 |
+
"cpu_count": 20,
|
| 25 |
+
"cpu_count_logical": 40,
|
| 26 |
+
"gpu": "NVIDIA GeForce RTX 4090",
|
| 27 |
+
"gpu_count": 2,
|
| 28 |
+
"disk": {
|
| 29 |
+
"/": {
|
| 30 |
+
"total": "1967317549056",
|
| 31 |
+
"used": "1392980328448"
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"memory": {
|
| 35 |
+
"total": "66890878976"
|
| 36 |
+
},
|
| 37 |
+
"cpu": {
|
| 38 |
+
"count": 20,
|
| 39 |
+
"countLogical": 40
|
| 40 |
+
},
|
| 41 |
+
"gpu_nvidia": [
|
| 42 |
+
{
|
| 43 |
+
"name": "NVIDIA GeForce RTX 4090",
|
| 44 |
+
"memoryTotal": "25757220864",
|
| 45 |
+
"cudaCores": 16384,
|
| 46 |
+
"architecture": "Ada"
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"name": "NVIDIA GeForce RTX 4090",
|
| 50 |
+
"memoryTotal": "25757220864",
|
| 51 |
+
"cudaCores": 16384,
|
| 52 |
+
"architecture": "Ada"
|
| 53 |
+
}
|
| 54 |
+
],
|
| 55 |
+
"cudaVersion": "13.0"
|
| 56 |
+
}
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/files/wandb-summary.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"test/p3_score":0.72,"_runtime":84839.875924085,"_wandb":{"runtime":84839},"_timestamp":1.7912639913773453e+09,"train/p2_score":1,"global_step":2480495,"train_action_mse_error":0.00022003134654369205,"test/cumulative_reward":1.0155143312105646,"test/p1_score":1,"test/p4_score":0.5,"train/p4_score":0.7,"test/p2_score":0.86,"train/cumulative_reward":1.1194035906854443,"test/mean_score":0.77,"epoch":5000,"train/success_rate":0.7,"val_loss":0.052233316004276276,"train/mean_score":0.925,"lr":0,"test/success_rate":0.5,"train/p3_score":1,"train_loss":0.0001353582352426348,"_step":2480495,"train/p1_score":1}
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug-core.log
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"time":"2026-10-05T13:45:58.520988554+08:00","level":"INFO","msg":"started logging, with flags","port-filename":"/tmp/tmpxqdfhghl/port-1342604.txt","pid":1342604,"debug":false,"disable-analytics":false}
|
| 2 |
+
{"time":"2026-10-05T13:45:58.521011902+08:00","level":"INFO","msg":"FeatureState","shutdownOnParentExitEnabled":false}
|
| 3 |
+
{"time":"2026-10-05T13:45:58.522084677+08:00","level":"INFO","msg":"server is running","addr":{"IP":"127.0.0.1","Port":38729,"Zone":""}}
|
| 4 |
+
{"time":"2026-10-05T13:45:58.522156611+08:00","level":"INFO","msg":"Will exit if parent process dies.","ppid":1342604}
|
| 5 |
+
{"time":"2026-10-05T13:45:58.719068703+08:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"127.0.0.1:51142"}
|
| 6 |
+
{"time":"2026-10-05T13:45:59.163255832+08:00","level":"INFO","msg":"handleInformInit: received","streamId":"a0y1jzsf","id":"127.0.0.1:51142"}
|
| 7 |
+
{"time":"2026-10-05T13:45:59.269117398+08:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"a0y1jzsf","id":"127.0.0.1:51142"}
|
| 8 |
+
{"time":"2026-10-06T13:19:59.03889803+08:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"127.0.0.1:51142"}
|
| 9 |
+
{"time":"2026-10-06T13:19:59.039127777+08:00","level":"INFO","msg":"server is shutting down"}
|
| 10 |
+
{"time":"2026-10-06T13:19:59.039119149+08:00","level":"INFO","msg":"connection: Close: initiating connection closure","id":"127.0.0.1:51142"}
|
| 11 |
+
{"time":"2026-10-06T13:19:59.039243207+08:00","level":"INFO","msg":"connection: Close: connection successfully closed","id":"127.0.0.1:51142"}
|
| 12 |
+
{"time":"2026-10-06T13:20:01.218422377+08:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"127.0.0.1:51142"}
|
| 13 |
+
{"time":"2026-10-06T13:20:01.218453721+08:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"127.0.0.1:51142"}
|
| 14 |
+
{"time":"2026-10-06T13:20:01.218469605+08:00","level":"INFO","msg":"server is closed"}
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug-internal.log
ADDED
|
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"time":"2026-10-05T13:45:59.163355915+08:00","level":"INFO","msg":"using version","core version":"0.18.6"}
|
| 2 |
+
{"time":"2026-10-05T13:45:59.163364924+08:00","level":"INFO","msg":"created symlink","path":"/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug-core.log"}
|
| 3 |
+
{"time":"2026-10-05T13:45:59.269047163+08:00","level":"INFO","msg":"created new stream","id":"a0y1jzsf"}
|
| 4 |
+
{"time":"2026-10-05T13:45:59.269111886+08:00","level":"INFO","msg":"stream: started","id":"a0y1jzsf"}
|
| 5 |
+
{"time":"2026-10-05T13:45:59.269178689+08:00","level":"INFO","msg":"handler: started","stream_id":{"value":"a0y1jzsf"}}
|
| 6 |
+
{"time":"2026-10-05T13:45:59.269379864+08:00","level":"INFO","msg":"sender: started","stream_id":"a0y1jzsf"}
|
| 7 |
+
{"time":"2026-10-05T13:45:59.269168469+08:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"a0y1jzsf"}}
|
| 8 |
+
{"time":"2026-10-05T13:46:00.434351743+08:00","level":"INFO","msg":"Starting system monitor"}
|
| 9 |
+
{"time":"2026-10-06T00:55:17.233211224+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": read tcp 192.168.11.41:58154->34.8.250.101:443: read: connection reset by peer"}
|
| 10 |
+
{"time":"2026-10-06T09:25:04.216906944+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 11 |
+
{"time":"2026-10-06T09:25:15.252828409+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp 34.8.250.101:443: connect: no route to host"}
|
| 12 |
+
{"time":"2026-10-06T09:25:26.397707765+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:39419->127.0.0.53:53: i/o timeout"}
|
| 13 |
+
{"time":"2026-10-06T09:25:36.667141225+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 14 |
+
{"time":"2026-10-06T09:25:36.756524289+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 15 |
+
{"time":"2026-10-06T09:25:54.045717582+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:60142->127.0.0.53:53: i/o timeout"}
|
| 16 |
+
{"time":"2026-10-06T09:26:10.833705525+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 17 |
+
{"time":"2026-10-06T09:26:19.764617144+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 18 |
+
{"time":"2026-10-06T09:26:50.502002568+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 19 |
+
{"time":"2026-10-06T09:26:57.698292324+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 20 |
+
{"time":"2026-10-06T09:27:39.461033137+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 21 |
+
{"time":"2026-10-06T09:28:07.699959385+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:50452->127.0.0.53:53: i/o timeout"}
|
| 22 |
+
{"time":"2026-10-06T09:28:43.153942633+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 23 |
+
{"time":"2026-10-06T09:29:17.703107112+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:36665->127.0.0.53:53: i/o timeout"}
|
| 24 |
+
{"time":"2026-10-06T09:30:13.15448044+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 25 |
+
{"time":"2026-10-06T09:30:27.705770185+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:42721->127.0.0.53:53: i/o timeout"}
|
| 26 |
+
{"time":"2026-10-06T09:31:37.708864611+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:43878->127.0.0.53:53: i/o timeout"}
|
| 27 |
+
{"time":"2026-10-06T09:31:43.15597339+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 28 |
+
{"time":"2026-10-06T09:32:47.710960866+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:46731->127.0.0.53:53: i/o timeout"}
|
| 29 |
+
{"time":"2026-10-06T09:33:13.157227823+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 30 |
+
{"time":"2026-10-06T09:33:57.71429012+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:38521->127.0.0.53:53: i/o timeout"}
|
| 31 |
+
{"time":"2026-10-06T09:34:34.218070669+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000912319,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"8lx8hbxpiv60\" connection_id:\"127.0.0.1:51142\")"}
|
| 32 |
+
{"time":"2026-10-06T09:34:35.701292599+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000212389,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 33 |
+
{"time":"2026-10-06T09:34:40.436056895+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000583931,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 34 |
+
{"time":"2026-10-06T09:34:40.436161283+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000713944,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 35 |
+
{"time":"2026-10-06T09:34:40.438335724+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000227179,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 36 |
+
{"time":"2026-10-06T09:34:40.439452019+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000451924,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 37 |
+
{"time":"2026-10-06T09:34:40.4395116+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000070491,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 38 |
+
{"time":"2026-10-06T09:34:43.158026918+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 39 |
+
{"time":"2026-10-06T09:35:07.716961743+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:57595->127.0.0.53:53: i/o timeout"}
|
| 40 |
+
{"time":"2026-10-06T09:36:13.159016826+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 41 |
+
{"time":"2026-10-06T09:36:17.72009588+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:37109->127.0.0.53:53: i/o timeout"}
|
| 42 |
+
{"time":"2026-10-06T09:37:27.722522334+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34984->127.0.0.53:53: i/o timeout"}
|
| 43 |
+
{"time":"2026-10-06T09:37:43.161342328+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 44 |
+
{"time":"2026-10-06T09:38:37.726080975+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:57156->127.0.0.53:53: i/o timeout"}
|
| 45 |
+
{"time":"2026-10-06T09:39:13.162840088+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 46 |
+
{"time":"2026-10-06T09:39:47.728677821+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59728->127.0.0.53:53: i/o timeout"}
|
| 47 |
+
{"time":"2026-10-06T09:40:43.164031242+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 48 |
+
{"time":"2026-10-06T09:40:57.730952264+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:42114->127.0.0.53:53: i/o timeout"}
|
| 49 |
+
{"time":"2026-10-06T09:41:53.16702903+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54374->127.0.0.53:53: i/o timeout"}
|
| 50 |
+
{"time":"2026-10-06T09:42:07.73436387+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:50668->127.0.0.53:53: i/o timeout"}
|
| 51 |
+
{"time":"2026-10-06T09:43:03.16922781+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54076->127.0.0.53:53: i/o timeout"}
|
| 52 |
+
{"time":"2026-10-06T09:43:17.736868037+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:55535->127.0.0.53:53: i/o timeout"}
|
| 53 |
+
{"time":"2026-10-06T09:44:13.171973988+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:36098->127.0.0.53:53: i/o timeout"}
|
| 54 |
+
{"time":"2026-10-06T09:44:27.739336521+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54781->127.0.0.53:53: i/o timeout"}
|
| 55 |
+
{"time":"2026-10-06T09:44:34.239471319+08:00","level":"WARN","msg":"sender: taking a long time","seconds":1200.022912721,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"8lx8hbxpiv60\" connection_id:\"127.0.0.1:51142\")"}
|
| 56 |
+
{"time":"2026-10-06T09:44:35.70342383+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.002371121,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 57 |
+
{"time":"2026-10-06T09:44:40.436779533+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.001288564,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 58 |
+
{"time":"2026-10-06T09:44:40.436895391+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.001441669,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 59 |
+
{"time":"2026-10-06T09:44:40.439087859+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.00097571,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 60 |
+
{"time":"2026-10-06T09:44:40.440188055+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.000730352,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 61 |
+
{"time":"2026-10-06T09:44:40.440189578+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":1200.001201081,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 62 |
+
{"time":"2026-10-06T09:45:23.174036006+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:32808->127.0.0.53:53: i/o timeout"}
|
| 63 |
+
{"time":"2026-10-06T09:45:37.74262234+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:57118->127.0.0.53:53: i/o timeout"}
|
| 64 |
+
{"time":"2026-10-06T09:46:33.175647107+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34142->127.0.0.53:53: i/o timeout"}
|
| 65 |
+
{"time":"2026-10-06T09:46:47.744827673+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:38788->127.0.0.53:53: i/o timeout"}
|
| 66 |
+
{"time":"2026-10-06T09:47:43.178129417+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:51485->127.0.0.53:53: i/o timeout"}
|
| 67 |
+
{"time":"2026-10-06T09:47:57.747348679+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:41227->127.0.0.53:53: i/o timeout"}
|
| 68 |
+
{"time":"2026-10-06T09:48:53.180282859+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58661->127.0.0.53:53: i/o timeout"}
|
| 69 |
+
{"time":"2026-10-06T09:48:53.180492936+08:00","level":"ERROR","msg":"sender: sendStopStatus: failed to get run stopped status: api: failed sending: POST https://api.wandb.ai/graphql giving up after 21 attempt(s): Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58661->127.0.0.53:53: i/o timeout"}
|
| 70 |
+
{"time":"2026-10-06T09:48:53.182181928+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":1458.965629728,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"8lx8hbxpiv60\" connection_id:\"127.0.0.1:51142\")"}
|
| 71 |
+
{"time":"2026-10-06T09:48:53.182330263+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1457.481319991,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 72 |
+
{"time":"2026-10-06T09:48:53.182428528+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.746976632,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 73 |
+
{"time":"2026-10-06T09:48:53.182475062+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.744278468,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 74 |
+
{"time":"2026-10-06T09:48:53.182446719+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.742950553,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 75 |
+
{"time":"2026-10-06T09:48:53.182566064+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.743523327,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 76 |
+
{"time":"2026-10-06T09:48:53.182440969+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1452.746942282,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 77 |
+
{"time":"2026-10-06T09:49:03.31098711+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:52560->127.0.0.53:53: i/o timeout"}
|
| 78 |
+
{"time":"2026-10-06T09:49:03.311014342+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:52560->127.0.0.53:53: i/o timeout"}
|
| 79 |
+
{"time":"2026-10-06T09:49:15.51000472+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:46088->127.0.0.53:53: i/o timeout"}
|
| 80 |
+
{"time":"2026-10-06T09:49:30.220917721+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:43837->127.0.0.53:53: i/o timeout"}
|
| 81 |
+
{"time":"2026-10-06T09:49:49.577054247+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:51242->127.0.0.53:53: i/o timeout"}
|
| 82 |
+
{"time":"2026-10-06T09:50:08.787118718+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 83 |
+
{"time":"2026-10-06T09:50:08.7871671+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 84 |
+
{"time":"2026-10-06T09:50:57.235008055+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59888->127.0.0.53:53: i/o timeout"}
|
| 85 |
+
{"time":"2026-10-06T09:51:18.790095596+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:45443->127.0.0.53:53: i/o timeout"}
|
| 86 |
+
{"time":"2026-10-06T09:52:07.238034763+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:60728->127.0.0.53:53: i/o timeout"}
|
| 87 |
+
{"time":"2026-10-06T09:52:28.793223924+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:54344->127.0.0.53:53: i/o timeout"}
|
| 88 |
+
{"time":"2026-10-06T09:53:17.241303288+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59484->127.0.0.53:53: i/o timeout"}
|
| 89 |
+
{"time":"2026-10-06T09:53:38.795011432+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:50171->127.0.0.53:53: i/o timeout"}
|
| 90 |
+
{"time":"2026-10-06T09:54:27.244118673+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59227->127.0.0.53:53: i/o timeout"}
|
| 91 |
+
{"time":"2026-10-06T09:54:48.797972117+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:45997->127.0.0.53:53: i/o timeout"}
|
| 92 |
+
{"time":"2026-10-06T09:55:37.247023164+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:34908->127.0.0.53:53: i/o timeout"}
|
| 93 |
+
{"time":"2026-10-06T09:55:58.800364514+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:49683->127.0.0.53:53: i/o timeout"}
|
| 94 |
+
{"time":"2026-10-06T09:56:47.249888902+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:60992->127.0.0.53:53: i/o timeout"}
|
| 95 |
+
{"time":"2026-10-06T09:57:08.802311113+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:53471->127.0.0.53:53: i/o timeout"}
|
| 96 |
+
{"time":"2026-10-06T09:57:57.252954476+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:40719->127.0.0.53:53: i/o timeout"}
|
| 97 |
+
{"time":"2026-10-06T09:58:17.085117628+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:59879->127.0.0.53:53: i/o timeout"}
|
| 98 |
+
{"time":"2026-10-06T09:58:23.228954725+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:48731->127.0.0.53:53: i/o timeout"}
|
| 99 |
+
{"time":"2026-10-06T09:58:53.310509872+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000650079,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"gplclwr5yrv3\" connection_id:\"127.0.0.1:51142\")"}
|
| 100 |
+
{"time":"2026-10-06T09:58:54.728910487+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000849739,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 101 |
+
{"time":"2026-10-06T09:59:00.435880525+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00045047,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 102 |
+
{"time":"2026-10-06T09:59:00.43601939+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000525846,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 103 |
+
{"time":"2026-10-06T09:59:00.438191073+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00039204,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 104 |
+
{"time":"2026-10-06T09:59:00.438198711+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000120136,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 105 |
+
{"time":"2026-10-06T09:59:00.439335822+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000417846,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 106 |
+
{"time":"2026-10-06T09:59:05.085657873+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:46257->127.0.0.53:53: i/o timeout"}
|
| 107 |
+
{"time":"2026-10-06T09:59:32.673067475+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:38517->127.0.0.53:53: i/o timeout"}
|
| 108 |
+
{"time":"2026-10-06T10:00:15.088446059+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:42397->127.0.0.53:53: i/o timeout"}
|
| 109 |
+
{"time":"2026-10-06T10:00:42.675974984+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:33976->127.0.0.53:53: i/o timeout"}
|
| 110 |
+
{"time":"2026-10-06T10:01:25.090369352+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:41435->127.0.0.53:53: i/o timeout"}
|
| 111 |
+
{"time":"2026-10-06T10:01:52.679257229+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:37099->127.0.0.53:53: i/o timeout"}
|
| 112 |
+
{"time":"2026-10-06T10:02:35.093533054+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:43216->127.0.0.53:53: i/o timeout"}
|
| 113 |
+
{"time":"2026-10-06T10:03:02.682033223+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:58548->127.0.0.53:53: i/o timeout"}
|
| 114 |
+
{"time":"2026-10-06T10:03:45.095777469+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:50451->127.0.0.53:53: i/o timeout"}
|
| 115 |
+
{"time":"2026-10-06T10:04:12.685307219+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:56278->127.0.0.53:53: i/o timeout"}
|
| 116 |
+
{"time":"2026-10-06T10:04:55.099256898+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:48863->127.0.0.53:53: i/o timeout"}
|
| 117 |
+
{"time":"2026-10-06T10:05:22.688113437+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:49585->127.0.0.53:53: i/o timeout"}
|
| 118 |
+
{"time":"2026-10-06T10:06:05.101706688+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: read udp 127.0.0.1:40857->127.0.0.53:53: i/o timeout"}
|
| 119 |
+
{"time":"2026-10-06T10:06:30.469216735+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/files/b10902069-national-taiwan-university/FrankaKitchen-v1-training/a0y1jzsf/file_stream\": dial tcp: lookup api.wandb.ai on 127.0.0.53:53: server misbehaving"}
|
| 120 |
+
{"time":"2026-10-06T10:07:05.891669426+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":1092.581635314,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"gplclwr5yrv3\" connection_id:\"127.0.0.1:51142\")"}
|
| 121 |
+
{"time":"2026-10-06T10:07:05.891847858+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1091.163881748,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 122 |
+
{"time":"2026-10-06T10:07:05.89194221+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.456543256,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 123 |
+
{"time":"2026-10-06T10:07:05.892005599+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.456550335,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 124 |
+
{"time":"2026-10-06T10:07:05.892078977+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.454229769,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 125 |
+
{"time":"2026-10-06T10:07:05.892165516+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.454052586,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 126 |
+
{"time":"2026-10-06T10:07:05.892249043+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1085.45331293,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 127 |
+
{"time":"2026-10-06T10:08:20.896007012+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
|
| 128 |
+
{"time":"2026-10-06T10:08:52.988732973+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 129 |
+
{"time":"2026-10-06T10:09:27.388072917+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 130 |
+
{"time":"2026-10-06T10:10:07.176838085+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 131 |
+
{"time":"2026-10-06T10:10:54.373793246+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 132 |
+
{"time":"2026-10-06T10:12:02.60384915+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 133 |
+
{"time":"2026-10-06T10:13:32.605053705+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 134 |
+
{"time":"2026-10-06T10:15:02.606602306+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 135 |
+
{"time":"2026-10-06T10:16:32.608834641+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 136 |
+
{"time":"2026-10-06T10:17:50.89575474+08:00","level":"WARN","msg":"sender: taking a long time","seconds":600.000208414,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"ckfgj8ye2snm\" connection_id:\"127.0.0.1:51142\")"}
|
| 137 |
+
{"time":"2026-10-06T10:17:52.434840284+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000559945,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 138 |
+
{"time":"2026-10-06T10:18:00.43574907+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000133108,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 139 |
+
{"time":"2026-10-06T10:18:00.435792208+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000401175,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 140 |
+
{"time":"2026-10-06T10:18:00.438949663+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000530324,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 141 |
+
{"time":"2026-10-06T10:18:00.438965768+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.000356572,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 142 |
+
{"time":"2026-10-06T10:18:00.439011938+08:00","level":"WARN","msg":"runwork: taking a long time","seconds":600.00004734,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 143 |
+
{"time":"2026-10-06T10:18:02.610833003+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 144 |
+
{"time":"2026-10-06T10:19:32.611778582+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded"}
|
| 145 |
+
{"time":"2026-10-06T10:21:02.61382365+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 146 |
+
{"time":"2026-10-06T10:22:32.615544993+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
|
| 147 |
+
{"time":"2026-10-06T10:23:42.963766085+08:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": read tcp 192.168.11.41:41968->34.8.250.101:443: read: network is unreachable"}
|
| 148 |
+
{"time":"2026-10-06T10:24:43.875271386+08:00","level":"INFO","msg":"sender: succeeded after taking longer than expected","seconds":1012.979744627,"work":"WorkRecord(*service_go_proto.Request_StopStatus); Control(local:true mailbox_slot:\"ckfgj8ye2snm\" connection_id:\"127.0.0.1:51142\")"}
|
| 149 |
+
{"time":"2026-10-06T10:24:43.875689942+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1011.441443372,"work":"WorkRecord(*service_go_proto.Request_PartialHistory); Control(local:true connection_id:\"127.0.0.1:51142\")"}
|
| 150 |
+
{"time":"2026-10-06T10:24:43.875721175+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.440111468,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 151 |
+
{"time":"2026-10-06T10:24:43.875814017+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.437401986,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 152 |
+
{"time":"2026-10-06T10:24:43.875746082+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.440385756,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 153 |
+
{"time":"2026-10-06T10:24:43.875852672+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.436850157,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 154 |
+
{"time":"2026-10-06T10:24:43.876036242+08:00","level":"INFO","msg":"runwork: succeeded after taking longer than expected","seconds":1003.437415844,"work":"WorkRecord(*service_go_proto.Record_Stats); Control(always_send:true)"}
|
| 155 |
+
{"time":"2026-10-06T13:19:59.039120309+08:00","level":"INFO","msg":"stream: closing","id":"a0y1jzsf"}
|
| 156 |
+
{"time":"2026-10-06T13:19:59.039154305+08:00","level":"INFO","msg":"Stopping system monitor"}
|
| 157 |
+
{"time":"2026-10-06T13:19:59.111492217+08:00","level":"INFO","msg":"Stopped system monitor"}
|
| 158 |
+
{"time":"2026-10-06T13:20:00.866016279+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
|
| 159 |
+
{"time":"2026-10-06T13:20:01.218067036+08:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"a0y1jzsf"}}
|
| 160 |
+
{"time":"2026-10-06T13:20:01.21814782+08:00","level":"INFO","msg":"sender: closed","stream_id":"a0y1jzsf"}
|
| 161 |
+
{"time":"2026-10-06T13:20:01.218137984+08:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"a0y1jzsf"}}
|
| 162 |
+
{"time":"2026-10-06T13:20:01.218298956+08:00","level":"INFO","msg":"stream: closed","id":"a0y1jzsf"}
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug.log
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Current SDK version is 0.18.6
|
| 2 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Configure stats pid to 1342604
|
| 3 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/.config/wandb/settings
|
| 4 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Loading settings from /tmp2/chyang/workspace/LLM-BC/wandb/settings
|
| 5 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
|
| 6 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': 'online', '_disable_service': None}
|
| 7 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train.py', 'program_abspath': '/tmp2/chyang/workspace/LLM-BC/train.py', 'program': '/tmp2/chyang/workspace/LLM-BC/./train.py'}
|
| 8 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_setup.py:_flush():79] Applying login settings: {}
|
| 9 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:_log_setup():533] Logging user logs to /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug.log
|
| 10 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:_log_setup():534] Logging internal logs to /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/logs/debug-internal.log
|
| 11 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:init():619] calling init triggers
|
| 12 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
|
| 13 |
+
config: {'name': 'train_diffusion_unet_lowdim', '_target_': 'llmbc.workspace.train_diffusion_unet_lowdim_workspace.TrainDiffusionUnetLowdimWorkspace', 'obs_dim': 59, 'action_dim': 9, 'task_name': 'FrankaKitchen-v1', 'exp_name': 'default', 'horizon': 16, 'n_obs_steps': 2, 'n_action_steps': 8, 'n_latency_steps': 0, 'past_action_visible': False, 'keypoint_visible_rate': 1.0, 'obs_as_local_cond': False, 'obs_as_global_cond': True, 'pred_action_steps_only': False, 'policy': {'_target_': 'llmbc.policy.diffusion_unet_lowdim_policy.DiffusionUnetLowdimPolicy', 'model': {'_target_': 'llmbc.model.diffusion.conditional_unet1d.ConditionalUnet1D', 'input_dim': 9, 'local_cond_dim': None, 'global_cond_dim': 118, 'diffusion_step_embed_dim': 256, 'down_dims': [256, 512, 1024], 'kernel_size': 5, 'upsample_kernel_size': 4, 'n_groups': 8, 'cond_predict_scale': True}, 'noise_scheduler': {'_target_': 'diffusers.schedulers.scheduling_ddpm.DDPMScheduler', 'num_train_timesteps': 100, 'beta_start': 0.0001, 'beta_end': 0.02, 'beta_schedule': 'squaredcos_cap_v2', 'variance_type': 'fixed_small', 'clip_sample': True, 'prediction_type': 'epsilon'}, 'horizon': 16, 'obs_dim': 59, 'action_dim': 9, 'n_action_steps': 8, 'n_obs_steps': 2, 'num_inference_steps': 10, 'obs_as_local_cond': False, 'obs_as_global_cond': True, 'pred_action_steps_only': False, 'oa_step_convention': True}, 'ema': {'_target_': 'llmbc.model.diffusion.ema_model.EMAModel', 'update_after_step': 0, 'inv_gamma': 1.0, 'power': 0.75, 'min_value': 0.0, 'max_value': 0.9999}, 'dataloader': {'batch_size': 256, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'val_dataloader': {'batch_size': 256, 'num_workers': 0, 'shuffle': False, 'pin_memory': False, 'persistent_workers': False}, 'optimizer': {'_target_': 'torch.optim.AdamW', 'lr': 0.0001, 'betas': [0.95, 0.999], 'eps': 1e-08, 'weight_decay': 1e-06}, 'training': {'device': 'cuda:0', 'seed': 45, 'debug': False, 'resume': True, 'lr_scheduler': 'cosine', 'lr_warmup_steps': 500, 'num_epochs': 5001, 'gradient_accumulate_every': 1, 'use_ema': True, 'rollout_every': 50, 'checkpoint_every': 50, 'val_every': 1, 'sample_every': 50, 'max_train_steps': None, 'max_val_steps': None, 'tqdm_interval_sec': 1.0}, 'logging': {'project': 'FrankaKitchen-v1-training', 'resume': True, 'mode': 'online', 'name': '2026.10.05-13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1', 'tags': ['train_diffusion_unet_lowdim', 'FrankaKitchen-v1', 'default'], 'id': None, 'group': None}, 'checkpoint': {'topk': {'monitor_key': 'test_success_rate', 'mode': 'max', 'k': 5, 'format_str': 'epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt'}, 'save_last_ckpt': True, 'save_last_snapshot': False}, 'multi_run': {'run_dir': 'data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1', 'wandb_name_base': '2026.10.05-13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1'}, 'task': {'name': 'FrankaKitchen-v1', 'obs_dim': 59, 'action_dim': 9, 'lang_multistep_merger': {'_target_': 'llfbench.envs.kitchen.multistep_merger.franka_kitchen_merger.KitchenMultistepMerger'}, 'env_runner': {'_target_': 'llmbc.env_runner.kitchen_lowdim_runner.KitchenLowdimRunner', 'env_name': 'llf-kitchen-FrankaKitchen-v1', 'n_train': 10, 'n_test': 50, 'n_envs': 10, 'max_steps': 500, 'n_obs_steps': 2, 'n_action_steps': 8, 'instruction_type': 'b', 'feedback_type': ['hp', 'hn', 'fp'], 'tasks_to_complete': ['microwave', 'kettle', 'light switch', 'slide cabinet'], 'visual': False, 'discount': 0.99, 'inference_expert_action': False, 'lang_multistep_merger': {'_target_': 'llfbench.envs.kitchen.multistep_merger.franka_kitchen_merger.KitchenMultistepMerger'}}, 'dataset': {'_target_': 'llmbc.dataset.kitchen_lowdim_dataset.KitchenLowdimDataset', 'data_path': 'datasets/FrankaKitchen-v1.pt', 'data_path2': 'datasets/FrankaKitchen-v1.pt', 'horizon': 16, 'pad_before': 1, 'pad_after': 7, 'obs_eef_target': True, 'use_manual_normalizer': False, 'val_ratio': 0.05, 'dummy_normalizer': False}, 'instructor': {'_target_': 'llmbc.translator.instructor.kitchen_instructor.FrankaKitchen_v1_instructor.FrankaKitchenV1Instructor'}}}
|
| 14 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:init():669] starting backend
|
| 15 |
+
2026-10-05 13:45:59,161 INFO MainThread:1342604 [wandb_init.py:init():673] sending inform_init request
|
| 16 |
+
2026-10-05 13:45:59,162 INFO MainThread:1342604 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
|
| 17 |
+
2026-10-05 13:45:59,162 INFO MainThread:1342604 [wandb_init.py:init():686] backend started and connected
|
| 18 |
+
2026-10-05 13:45:59,171 INFO MainThread:1342604 [wandb_init.py:init():781] updated telemetry
|
| 19 |
+
2026-10-05 13:45:59,287 INFO MainThread:1342604 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
|
| 20 |
+
2026-10-05 13:46:00,431 INFO MainThread:1342604 [wandb_init.py:init():867] starting run threads in backend
|
| 21 |
+
2026-10-05 13:46:00,735 INFO MainThread:1342604 [wandb_run.py:_console_start():2451] atexit reg
|
| 22 |
+
2026-10-05 13:46:00,735 INFO MainThread:1342604 [wandb_run.py:_redirect():2299] redirect: wrap_raw
|
| 23 |
+
2026-10-05 13:46:00,735 INFO MainThread:1342604 [wandb_run.py:_redirect():2364] Wrapping output streams.
|
| 24 |
+
2026-10-05 13:46:00,735 INFO MainThread:1342604 [wandb_run.py:_redirect():2389] Redirects installed.
|
| 25 |
+
2026-10-05 13:46:00,736 INFO MainThread:1342604 [wandb_init.py:init():911] run started, returning control to user process
|
| 26 |
+
2026-10-05 13:46:00,737 INFO MainThread:1342604 [wandb_run.py:_config_callback():1389] config_cb None None {'output_dir': '/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1'}
|
| 27 |
+
2026-10-06 13:19:59,039 WARNING MsgRouterThr:1342604 [router.py:message_loop():75] message_loop has been closed
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/run-20261005_134559-a0y1jzsf/run-a0y1jzsf.wandb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3daf68b047568a0ed95cf444c0af0e4b7bc7c151638f8f35a2af528cbd34acdb
|
| 3 |
+
size 1220692416
|
2026.10.05/13.45.49_train_diffusion_unet_lowdim_FrankaKitchen-v1/wandb/wandb-resume.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"run_id": "a0y1jzsf"}
|