Instructions to use Prahaladha/nomas-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Prahaladha/nomas-mini with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Prahaladha/nomas-mini", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
sync main: 6 files from /dev/shm/mwm/logs
Browse files- logs/export_tf_nomas4_600.log +5 -0
- logs/fix_q001b.log +6 -0
- logs/fold_events.log +2 -0
- logs/play_tf_nomas4_t3_600.log +0 -0
- logs/prune.log +2 -0
- logs/train_tf_nomas4.until600.log +517 -0
logs/export_tf_nomas4_600.log
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
consolidating DCP shards from /dev/shm/mwm/runs/tf_nomas4/ckpts/checkpoint_600 (key='model') …
|
| 2 |
+
/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/checkpoint/state_dict_loader.py:362: UserWarning: torch.distributed is unavailable or uninitialized, assuming the intent is to load in a single process.
|
| 3 |
+
warnings.warn(
|
| 4 |
+
loaded 885 parameter tensors
|
| 5 |
+
saved .pt → /dev/shm/mwm/exports/tf_nomas4/step_600.pt (5683 MB)
|
logs/fix_q001b.log
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
01:25:59 q001b real copy: 7.9G; dirs: shard_q000 shard_q001 shard_q001b shard_q002 shard_rehearse
|
| 2 |
+
01:25:59 relaunched; waiting for the first step
|
| 3 |
+
[10/31 01:27:15 minwm.engine.checkpoint.checkpointer]: loaded checkpoint /dev/shm/mwm/runs/tf_nomas4/ckpts/checkpoint_600
|
| 4 |
+
[10/31 01:28:58 minwm.engine.monitor]: step 610 time/data(ms): 1.719 time/forward(ms): 2271 time/backward(ms): 6601 grad_norm: 0.1057 loss: 0.1473 steps/s
|
| 5 |
+
01:28:59 checkpoint tester still running
|
| 6 |
+
01:28:59 FIX_Q001B_DONE
|
logs/fold_events.log
CHANGED
|
@@ -1,2 +1,4 @@
|
|
| 1 |
01:12:50 quality dirs: shard_q000 shard_q001 shard_q001b shard_q002 shard_rehearse
|
| 2 |
01:12:50 waiting for the next tf_nomas4 checkpoint
|
|
|
|
|
|
|
|
|
| 1 |
01:12:50 quality dirs: shard_q000 shard_q001 shard_q001b shard_q002 shard_rehearse
|
| 2 |
01:12:50 waiting for the next tf_nomas4 checkpoint
|
| 3 |
+
01:23:50 fold-in at checkpoint_600
|
| 4 |
+
01:23:55 old trainer processes left: 0
|
logs/play_tf_nomas4_t3_600.log
ADDED
|
File without changes
|
logs/prune.log
CHANGED
|
@@ -13,3 +13,5 @@ pruned export (on HF) /dev/shm/mwm/exports/tf_nomas2/step_1000.pt
|
|
| 13 |
22:23:37 pruned tf_nomas3 checkpoint_500 (export kept)
|
| 14 |
pruned export (on HF) /dev/shm/mwm/exports/tf_nomas3/step_250.pt
|
| 15 |
pruned export (on HF) /dev/shm/mwm/exports/tf_nomas3/step_500.pt
|
|
|
|
|
|
|
|
|
| 13 |
22:23:37 pruned tf_nomas3 checkpoint_500 (export kept)
|
| 14 |
pruned export (on HF) /dev/shm/mwm/exports/tf_nomas3/step_250.pt
|
| 15 |
pruned export (on HF) /dev/shm/mwm/exports/tf_nomas3/step_500.pt
|
| 16 |
+
01:23:42 pruned tf_nomas4 checkpoint_200 (export kept)
|
| 17 |
+
pruned export (on HF) /dev/shm/mwm/exports/tf_nomas4/step_200.pt
|
logs/train_tf_nomas4.until600.log
ADDED
|
@@ -0,0 +1,517 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
MWM_TRAIN3 repo /dev/shm/mwm/repo data /dev/shm/mwm/data/quality char_labels none char_k 200 drop 0.1
|
| 2 |
+
MWM_TRAIN config configs/wan21/action2v/train/stage1_ar_tf_aug.py
|
| 3 |
+
MWM_TRAIN start 23:38:58 stage tf name tf_nomas4 gpus 0,1,2,3,4,5 n 6 steps 1200 lr 5e-6 init /dev/shm/mwm/exports/tf_nomas3/step_1000.pt teacher same extra
|
| 4 |
+
[10/30 23:39:03 minwm.distributed.sp.parallel_state]: Initializing distributed environment with world_size=6, device=cuda:0
|
| 5 |
+
[10/30 23:39:03 minwm.distributed.sp.parallel_state]: world_size=6 rank=0 local_rank=0 distributed_init_method=env:// backend=nccl
|
| 6 |
+
[Gloo] Rank [Gloo] Rank [Gloo] Rank 30 is connected to is connected to 545 peer ranks. is connected to peer ranks. Expected number of connected peer ranks is : 5Expected number of connected peer ranks is : 5 peer ranks. 5Expected number of connected peer ranks is :
|
| 7 |
+
|
| 8 |
+
5
|
| 9 |
+
[Gloo] Rank 1 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 10 |
+
[Gloo] Rank 2 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 11 |
+
[Gloo] Rank 5 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 12 |
+
[10/30 23:39:07 minwm.distributed.sp.nccl]: Found nccl from library libnccl.so.2
|
| 13 |
+
[10/30 23:39:07 minwm.distributed.sp.device_communicators.pynccl]: Trainer is using nccl==2.27.5
|
| 14 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 15 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 16 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 17 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 18 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 19 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 20 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 21 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 22 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 23 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 24 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 25 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 26 |
+
[Gloo] Rank 0 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 27 |
+
[Gloo] Rank 2 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 28 |
+
[Gloo] Rank 5 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 29 |
+
[Gloo] Rank 1 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 30 |
+
[Gloo] Rank 4 is connected to 5 peer ranks. [Gloo] Rank Expected number of connected peer ranks is : 53
|
| 31 |
+
is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 32 |
+
[10/30 23:39:08 minwm.distributed.sp.nccl]: Found nccl from library libnccl.so.2
|
| 33 |
+
[10/30 23:39:08 minwm.distributed.sp.device_communicators.pynccl]: Trainer is using nccl==2.27.5
|
| 34 |
+
[10/30 23:39:10 minwm.engine.trainer]: base RNG seed: 1348092628 (+ dp_rank)
|
| 35 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.4.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.weight']
|
| 36 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 37 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.3.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.weight']
|
| 38 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 39 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.8.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias']
|
| 40 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 41 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.5.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.bias']
|
| 42 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 43 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.26.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight']
|
| 44 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 45 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.13.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight']
|
| 46 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 47 |
+
[10/30 23:39:14 minwm.distributed.fsdp]: FSDP2: activation-checkpointed 30 layer module(s)
|
| 48 |
+
[10/30 23:39:14 minwm.distributed.fsdp]: FSDP2: sharded 30 layer module(s) in FSDPCausalWan21Model
|
| 49 |
+
[10/30 23:40:12 minwm.engine.trainer]: loaded pretrained weights from /dev/shm/mwm/exports/tf_nomas3/step_1000.pt
|
| 50 |
+
[10/30 23:41:56 minwm.engine.monitor]: step 10 time/data(ms): 2.218 time/forward(ms): 2128 time/backward(ms): 6758 grad_norm: 2.78 loss: 0.1019 steps/sec: 0.09618 ms/step: 1.04e+04 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 51 |
+
[10/30 23:43:26 minwm.engine.monitor]: step 20 time/data(ms): 2.248 time/forward(ms): 2081 time/backward(ms): 6580 grad_norm: 0.114 loss: 0.05678 steps/sec: 0.1114 ms/step: 8981 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 52 |
+
[10/30 23:44:56 minwm.engine.monitor]: step 30 time/data(ms): 2.305 time/forward(ms): 2099 time/backward(ms): 6584 grad_norm: 0.07225 loss: 0.1151 steps/sec: 0.1107 ms/step: 9032 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 53 |
+
[10/30 23:46:27 minwm.engine.monitor]: step 40 time/data(ms): 2.265 time/forward(ms): 2117 time/backward(ms): 6815 grad_norm: 0.1075 loss: 0.06289 steps/sec: 0.1102 ms/step: 9071 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 54 |
+
[10/30 23:47:57 minwm.engine.monitor]: step 50 time/data(ms): 1.841 time/forward(ms): 2270 time/backward(ms): 6595 grad_norm: 0.05821 loss: 0.02314 steps/sec: 0.111 ms/step: 9008 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 55 |
+
[10/30 23:49:27 minwm.engine.monitor]: step 60 time/data(ms): 2.08 time/forward(ms): 2085 time/backward(ms): 6589 grad_norm: 0.063 loss: 0.09621 steps/sec: 0.1111 ms/step: 9001 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 56 |
+
[10/30 23:50:57 minwm.engine.monitor]: step 70 time/data(ms): 2.021 time/forward(ms): 2263 time/backward(ms): 6599 grad_norm: 0.06582 loss: 0.04823 steps/sec: 0.1108 ms/step: 9023 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 57 |
+
[10/30 23:52:28 minwm.engine.monitor]: step 80 time/data(ms): 2.722 time/forward(ms): 2267 time/backward(ms): 6606 grad_norm: 0.0775 loss: 0.1047 steps/sec: 0.1105 ms/step: 9053 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 58 |
+
[10/30 23:53:58 minwm.engine.monitor]: step 90 time/data(ms): 2.202 time/forward(ms): 2292 time/backward(ms): 6609 grad_norm: 0.08042 loss: 0.07051 steps/sec: 0.1105 ms/step: 9046 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 59 |
+
[10/30 23:55:29 minwm.engine.monitor]: step 100 time/data(ms): 2.19 time/forward(ms): 2294 time/backward(ms): 6621 grad_norm: 0.07171 loss: 0.07699 steps/sec: 0.11 ms/step: 9094 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 60 |
+
[10/30 23:56:59 minwm.engine.monitor]: step 110 time/data(ms): 1.979 time/forward(ms): 2112 time/backward(ms): 6818 grad_norm: 0.06937 loss: 0.08037 steps/sec: 0.1109 ms/step: 9014 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 61 |
+
[10/30 23:58:30 minwm.engine.monitor]: step 120 time/data(ms): 1.512 time/forward(ms): 2110 time/backward(ms): 6796 grad_norm: 0.07279 loss: 0.06516 steps/sec: 0.1104 ms/step: 9060 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 62 |
+
[10/31 00:00:00 minwm.engine.monitor]: step 130 time/data(ms): 2.095 time/forward(ms): 2429 time/backward(ms): 6615 grad_norm: 0.07834 loss: 0.08304 steps/sec: 0.1102 ms/step: 9075 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 63 |
+
[10/31 00:01:31 minwm.engine.monitor]: step 140 time/data(ms): 1.497 time/forward(ms): 2270 time/backward(ms): 6606 grad_norm: 0.07661 loss: 0.0269 steps/sec: 0.1106 ms/step: 9045 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 64 |
+
[10/31 00:03:01 minwm.engine.monitor]: step 150 time/data(ms): 1.517 time/forward(ms): 2273 time/backward(ms): 6614 grad_norm: 0.08383 loss: 0.09444 steps/sec: 0.1114 ms/step: 8979 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 65 |
+
[10/31 00:04:30 minwm.engine.monitor]: step 160 time/data(ms): 1.633 time/forward(ms): 2093 time/backward(ms): 6595 grad_norm: 0.0483 loss: 0.1145 steps/sec: 0.112 ms/step: 8932 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 66 |
+
[10/31 00:06:00 minwm.engine.monitor]: step 170 time/data(ms): 2.199 time/forward(ms): 2091 time/backward(ms): 6594 grad_norm: 0.07617 loss: 0.07862 steps/sec: 0.1107 ms/step: 9034 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 67 |
+
[10/31 00:07:31 minwm.engine.monitor]: step 180 time/data(ms): 2.003 time/forward(ms): 2087 time/backward(ms): 6591 grad_norm: 0.08448 loss: 0.09374 steps/sec: 0.1108 ms/step: 9024 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 68 |
+
[10/31 00:09:01 minwm.engine.monitor]: step 190 time/data(ms): 2.061 time/forward(ms): 2264 time/backward(ms): 6611 grad_norm: 0.05914 loss: 0.1611 steps/sec: 0.1106 ms/step: 9041 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 69 |
+
[10/31 00:10:31 minwm.engine.monitor]: step 200 time/data(ms): 1.953 time/forward(ms): 2114 time/backward(ms): 6789 grad_norm: 0.06499 loss: 0.06016 steps/sec: 0.1105 ms/step: 9046 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 70 |
+
[10/31 00:10:39 minwm.engine.checkpoint.checkpointer]: saved checkpoint /dev/shm/mwm/runs/tf_nomas4/ckpts/checkpoint_200
|
| 71 |
+
[10/31 00:12:09 minwm.engine.monitor]: step 210 time/data(ms): 1.814 time/forward(ms): 2268 time/backward(ms): 6600 grad_norm: 69.79 loss: 0.09043 steps/sec: 0.1024 ms/step: 9767 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 72 |
+
[10/31 00:13:40 minwm.engine.monitor]: step 220 time/data(ms): 1.781 time/forward(ms): 2294 time/backward(ms): 6601 grad_norm: 659.1 loss: 0.07217 steps/sec: 0.1103 ms/step: 9067 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 73 |
+
[10/31 00:15:10 minwm.engine.monitor]: step 230 time/data(ms): 1.706 time/forward(ms): 2111 time/backward(ms): 6813 grad_norm: 2.096 loss: 0.05185 steps/sec: 0.1105 ms/step: 9052 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 74 |
+
[10/31 00:16:41 minwm.engine.monitor]: step 240 time/data(ms): 1.456 time/forward(ms): 2087 time/backward(ms): 6586 grad_norm: 0.0808 loss: 0.1243 steps/sec: 0.1107 ms/step: 9029 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 75 |
+
[10/31 00:18:10 minwm.engine.monitor]: step 250 time/data(ms): 2.028 time/forward(ms): 2263 time/backward(ms): 6603 grad_norm: 0.08702 loss: 0.106 steps/sec: 0.1115 ms/step: 8966 memory/max_reserved(GiB): 30.32 memory/max_reserved(%): 38.29 memory/num_ooms: 0
|
| 76 |
+
W1031 00:19:18.777000 3094248 torch/distributed/elastic/agent/server/api.py:725] Received 15 death signal, shutting down workers
|
| 77 |
+
W1031 00:19:18.779000 3094248 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3094276 closing signal SIGTERM
|
| 78 |
+
W1031 00:19:18.781000 3094248 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3094277 closing signal SIGTERM
|
| 79 |
+
W1031 00:19:18.783000 3094248 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3094278 closing signal SIGTERM
|
| 80 |
+
W1031 00:19:18.787000 3094248 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3094279 closing signal SIGTERM
|
| 81 |
+
W1031 00:19:18.791000 3094248 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3094280 closing signal SIGTERM
|
| 82 |
+
W1031 00:19:18.794000 3094248 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3094281 closing signal SIGTERM
|
| 83 |
+
Traceback (most recent call last):
|
| 84 |
+
File "/dev/shm/mwm/venv/bin/torchrun", line 10, in <module>
|
| 85 |
+
sys.exit(main())
|
| 86 |
+
^^^^^^
|
| 87 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 357, in wrapper
|
| 88 |
+
return f(*args, **kwargs)
|
| 89 |
+
^^^^^^^^^^^^^^^^^^
|
| 90 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/run.py", line 936, in main
|
| 91 |
+
run(args)
|
| 92 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/run.py", line 927, in run
|
| 93 |
+
elastic_launch(
|
| 94 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 156, in __call__
|
| 95 |
+
return launch_agent(self._config, self._entrypoint, list(args))
|
| 96 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 97 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 284, in launch_agent
|
| 98 |
+
result = agent.run()
|
| 99 |
+
^^^^^^^^^^^
|
| 100 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/metrics/api.py", line 138, in wrapper
|
| 101 |
+
result = f(*args, **kwargs)
|
| 102 |
+
^^^^^^^^^^^^^^^^^^
|
| 103 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/agent/server/api.py", line 717, in run
|
| 104 |
+
result = self._invoke_run(role)
|
| 105 |
+
^^^^^^^^^^^^^^^^^^^^^^
|
| 106 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/agent/server/api.py", line 881, in _invoke_run
|
| 107 |
+
time.sleep(monitor_interval)
|
| 108 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 85, in _terminate_process_handler
|
| 109 |
+
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
|
| 110 |
+
torch.distributed.elastic.multiprocessing.api.SignalException: Process 3094248 got signal: 15
|
| 111 |
+
[W1031 00:19:19.659307039 AllocatorConfig.cpp:28] Warning: PYTORCH_CUDA_ALLOC_CONF is deprecated, use PYTORCH_ALLOC_CONF instead (function operator())
|
| 112 |
+
MWM_TRAIN3 repo /dev/shm/mwm/repo data /dev/shm/mwm/data/quality char_labels none char_k 200 drop 0.1
|
| 113 |
+
MWM_TRAIN config configs/wan21/action2v/train/stage1_ar_tf_aug.py
|
| 114 |
+
MWM_TRAIN start 00:19:24 stage tf name tf_nomas4 gpus 0,1,2,3,4,5 n 6 steps 1200 lr 5e-6 init /dev/shm/mwm/exports/tf_nomas3/step_1000.pt teacher same extra checkpoint.resume=True
|
| 115 |
+
[10/31 00:19:28 minwm.distributed.sp.parallel_state]: Initializing distributed environment with world_size=6, device=cuda:0
|
| 116 |
+
[10/31 00:19:28 minwm.distributed.sp.parallel_state]: world_size=6 rank=0 local_rank=0 distributed_init_method=env:// backend=nccl
|
| 117 |
+
[Gloo] Rank 0 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 118 |
+
[Gloo] Rank 1 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 119 |
+
[Gloo] Rank [Gloo] Rank 5 is connected to 54 peer ranks. is connected to Expected number of connected peer ranks is : 55 peer ranks. Expected number of connected peer ranks is :
|
| 120 |
+
5
|
| 121 |
+
[Gloo] Rank [Gloo] Rank 3 is connected to 52 peer ranks. is connected to Expected number of connected peer ranks is : 55 peer ranks. Expected number of connected peer ranks is :
|
| 122 |
+
5
|
| 123 |
+
[10/31 00:19:32 minwm.distributed.sp.nccl]: Found nccl from library libnccl.so.2
|
| 124 |
+
[10/31 00:19:32 minwm.distributed.sp.device_communicators.pynccl]: Trainer is using nccl==2.27.5
|
| 125 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 126 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 127 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 128 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 129 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 130 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 131 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 132 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 133 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 134 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 135 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 136 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 137 |
+
[Gloo] Rank 1 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 138 |
+
[Gloo] Rank 4 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 139 |
+
[Gloo] Rank 0 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 140 |
+
[Gloo] Rank 3 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 141 |
+
[Gloo] Rank 2 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 142 |
+
[Gloo] Rank 5 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 143 |
+
[10/31 00:19:34 minwm.distributed.sp.nccl]: Found nccl from library libnccl.so.2
|
| 144 |
+
[10/31 00:19:34 minwm.distributed.sp.device_communicators.pynccl]: Trainer is using nccl==2.27.5
|
| 145 |
+
[10/31 00:19:35 minwm.engine.trainer]: base RNG seed: 1097413646 (+ dp_rank)
|
| 146 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.16.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.bias']
|
| 147 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 148 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.15.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.bias']
|
| 149 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 150 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.16.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.weight']
|
| 151 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 152 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.25.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight']
|
| 153 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 154 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.27.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.bias']
|
| 155 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 156 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.6.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias']
|
| 157 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 158 |
+
[10/31 00:19:39 minwm.distributed.fsdp]: FSDP2: activation-checkpointed 30 layer module(s)
|
| 159 |
+
[10/31 00:19:39 minwm.distributed.fsdp]: FSDP2: sharded 30 layer module(s) in FSDPCausalWan21Model
|
| 160 |
+
[10/31 00:20:40 minwm.engine.checkpoint.checkpointer]: loaded checkpoint /dev/shm/mwm/runs/tf_nomas4/ckpts/checkpoint_200
|
| 161 |
+
[10/31 00:22:23 minwm.engine.monitor]: step 210 time/data(ms): 1.902 time/forward(ms): 2300 time/backward(ms): 6643 grad_norm: 0.07516 loss: 0.05791 steps/sec: 0.09719 ms/step: 1.029e+04 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 162 |
+
[10/31 00:23:53 minwm.engine.monitor]: step 220 time/data(ms): 1.631 time/forward(ms): 2269 time/backward(ms): 6602 grad_norm: 0.06266 loss: 0.07548 steps/sec: 0.1105 ms/step: 9047 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 163 |
+
[10/31 00:25:24 minwm.engine.monitor]: step 230 time/data(ms): 2.209 time/forward(ms): 2299 time/backward(ms): 6610 grad_norm: 0.06698 loss: 0.08214 steps/sec: 0.1102 ms/step: 9075 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 164 |
+
[10/31 00:26:55 minwm.engine.monitor]: step 240 time/data(ms): 1.785 time/forward(ms): 2112 time/backward(ms): 6783 grad_norm: 0.0766 loss: 0.1359 steps/sec: 0.11 ms/step: 9093 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 165 |
+
[10/31 00:28:25 minwm.engine.monitor]: step 250 time/data(ms): 1.852 time/forward(ms): 2258 time/backward(ms): 6780 grad_norm: 0.06664 loss: 0.05994 steps/sec: 0.1104 ms/step: 9054 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 166 |
+
[10/31 00:29:56 minwm.engine.monitor]: step 260 time/data(ms): 1.803 time/forward(ms): 2259 time/backward(ms): 6589 grad_norm: 0.4421 loss: 0.07811 steps/sec: 0.1103 ms/step: 9065 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 167 |
+
[10/31 00:31:27 minwm.engine.monitor]: step 270 time/data(ms): 1.894 time/forward(ms): 2273 time/backward(ms): 6606 grad_norm: 0.09639 loss: 0.07427 steps/sec: 0.1101 ms/step: 9086 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 168 |
+
[10/31 00:32:58 minwm.engine.monitor]: step 280 time/data(ms): 2.037 time/forward(ms): 2320 time/backward(ms): 6771 grad_norm: 0.07914 loss: 0.1117 steps/sec: 0.1103 ms/step: 9062 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 169 |
+
[10/31 00:34:28 minwm.engine.monitor]: step 290 time/data(ms): 2.011 time/forward(ms): 2369 time/backward(ms): 6618 grad_norm: 0.164 loss: 0.07447 steps/sec: 0.1105 ms/step: 9050 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 170 |
+
[10/31 00:35:58 minwm.engine.monitor]: step 300 time/data(ms): 1.757 time/forward(ms): 2270 time/backward(ms): 6598 grad_norm: 0.0953 loss: 0.0505 steps/sec: 0.111 ms/step: 9009 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 171 |
+
[10/31 00:37:29 minwm.engine.monitor]: step 310 time/data(ms): 2.123 time/forward(ms): 2266 time/backward(ms): 6594 grad_norm: 0.08634 loss: 0.06449 steps/sec: 0.1105 ms/step: 9051 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 172 |
+
[10/31 00:38:59 minwm.engine.monitor]: step 320 time/data(ms): 2.328 time/forward(ms): 2105 time/backward(ms): 6774 grad_norm: 0.07031 loss: 0.03594 steps/sec: 0.1102 ms/step: 9074 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 173 |
+
[10/31 00:40:31 minwm.engine.monitor]: step 330 time/data(ms): 2.232 time/forward(ms): 2110 time/backward(ms): 6778 grad_norm: 27.23 loss: 0.08933 steps/sec: 0.1098 ms/step: 9107 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 174 |
+
[10/31 00:42:01 minwm.engine.monitor]: step 340 time/data(ms): 2.1 time/forward(ms): 2085 time/backward(ms): 6592 grad_norm: 0.07648 loss: 0.06752 steps/sec: 0.1107 ms/step: 9032 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 175 |
+
[10/31 00:43:32 minwm.engine.monitor]: step 350 time/data(ms): 1.864 time/forward(ms): 2267 time/backward(ms): 6607 grad_norm: 0.08208 loss: 0.1899 steps/sec: 0.1103 ms/step: 9069 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 176 |
+
[10/31 00:45:02 minwm.engine.monitor]: step 360 time/data(ms): 2.151 time/forward(ms): 2109 time/backward(ms): 6786 grad_norm: 3.156 loss: 0.07607 steps/sec: 0.1102 ms/step: 9073 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 177 |
+
[10/31 00:46:33 minwm.engine.monitor]: step 370 time/data(ms): 2.449 time/forward(ms): 2128 time/backward(ms): 6771 grad_norm: 0.05692 loss: 0.06076 steps/sec: 0.1107 ms/step: 9034 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 178 |
+
[10/31 00:48:03 minwm.engine.monitor]: step 380 time/data(ms): 2.013 time/forward(ms): 2441 time/backward(ms): 6606 grad_norm: 0.07225 loss: 0.08602 steps/sec: 0.1107 ms/step: 9032 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 179 |
+
[10/31 00:49:33 minwm.engine.monitor]: step 390 time/data(ms): 2.283 time/forward(ms): 2267 time/backward(ms): 6607 grad_norm: 9.927 loss: 0.07774 steps/sec: 0.1106 ms/step: 9044 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 180 |
+
[10/31 00:51:03 minwm.engine.monitor]: step 400 time/data(ms): 2.241 time/forward(ms): 2277 time/backward(ms): 6627 grad_norm: 0.06757 loss: 0.1373 steps/sec: 0.1113 ms/step: 8984 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 181 |
+
[10/31 00:51:09 minwm.engine.checkpoint.checkpointer]: saved checkpoint /dev/shm/mwm/runs/tf_nomas4/ckpts/checkpoint_400
|
| 182 |
+
[10/31 00:52:40 minwm.engine.monitor]: step 410 time/data(ms): 1.911 time/forward(ms): 2277 time/backward(ms): 6606 grad_norm: 0.07318 loss: 0.09068 steps/sec: 0.1034 ms/step: 9669 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 183 |
+
[10/31 00:54:11 minwm.engine.monitor]: step 420 time/data(ms): 1.872 time/forward(ms): 2270 time/backward(ms): 6600 grad_norm: 0.0689 loss: 0.09363 steps/sec: 0.1102 ms/step: 9075 memory/max_reserved(GiB): 30.28 memory/max_reserved(%): 38.24 memory/num_ooms: 0
|
| 184 |
+
[10/31 00:55:42 minwm.engine.monitor]: step 430 time/data(ms): 2.042 time/forward(ms): 2307 time/backward(ms): 6742 grad_norm: 0.05472 loss: 0.04118 steps/sec: 0.11 ms/step: 9090 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 185 |
+
[10/31 00:57:12 minwm.engine.monitor]: step 440 time/data(ms): 1.715 time/forward(ms): 2271 time/backward(ms): 6606 grad_norm: 377.2 loss: 0.06712 steps/sec: 0.1104 ms/step: 9055 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 186 |
+
[10/31 00:58:42 minwm.engine.monitor]: step 450 time/data(ms): 1.999 time/forward(ms): 2118 time/backward(ms): 6801 grad_norm: 0.2745 loss: 0.09503 steps/sec: 0.1106 ms/step: 9038 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 187 |
+
[10/31 01:00:13 minwm.engine.monitor]: step 460 time/data(ms): 1.846 time/forward(ms): 2112 time/backward(ms): 6772 grad_norm: 731.8 loss: 0.1038 steps/sec: 0.1107 ms/step: 9030 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 188 |
+
[10/31 01:01:43 minwm.engine.monitor]: step 470 time/data(ms): 1.855 time/forward(ms): 2083 time/backward(ms): 6581 grad_norm: 0.07778 loss: 0.1285 steps/sec: 0.1105 ms/step: 9049 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 189 |
+
[10/31 01:03:14 minwm.engine.monitor]: step 480 time/data(ms): 1.655 time/forward(ms): 2106 time/backward(ms): 6770 grad_norm: 0.1432 loss: 0.09995 steps/sec: 0.1104 ms/step: 9058 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 190 |
+
[10/31 01:04:45 minwm.engine.monitor]: step 490 time/data(ms): 1.85 time/forward(ms): 2273 time/backward(ms): 6601 grad_norm: 12.71 loss: 0.08873 steps/sec: 0.1099 ms/step: 9102 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 191 |
+
[10/31 01:06:16 minwm.engine.monitor]: step 500 time/data(ms): 2.108 time/forward(ms): 2263 time/backward(ms): 6614 grad_norm: 0.08869 loss: 0.08407 steps/sec: 0.1099 ms/step: 9100 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 192 |
+
[10/31 01:07:47 minwm.engine.monitor]: step 510 time/data(ms): 1.998 time/forward(ms): 2133 time/backward(ms): 6785 grad_norm: 0.07441 loss: 0.1426 steps/sec: 0.1102 ms/step: 9075 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 193 |
+
[10/31 01:09:17 minwm.engine.monitor]: step 520 time/data(ms): 1.793 time/forward(ms): 2266 time/backward(ms): 6594 grad_norm: 0.6371 loss: 0.1089 steps/sec: 0.1105 ms/step: 9049 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 194 |
+
[10/31 01:10:48 minwm.engine.monitor]: step 530 time/data(ms): 1.577 time/forward(ms): 2271 time/backward(ms): 6612 grad_norm: 0.07826 loss: 0.03975 steps/sec: 0.1105 ms/step: 9048 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 195 |
+
[10/31 01:12:18 minwm.engine.monitor]: step 540 time/data(ms): 2.19 time/forward(ms): 2257 time/backward(ms): 6728 grad_norm: 0.07122 loss: 0.075 steps/sec: 0.1108 ms/step: 9025 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 196 |
+
[10/31 01:13:48 minwm.engine.monitor]: step 550 time/data(ms): 1.617 time/forward(ms): 2267 time/backward(ms): 6602 grad_norm: 0.1086 loss: 0.09965 steps/sec: 0.1103 ms/step: 9067 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 197 |
+
[10/31 01:15:19 minwm.engine.monitor]: step 560 time/data(ms): 2.204 time/forward(ms): 2110 time/backward(ms): 6776 grad_norm: 0.08409 loss: 0.09653 steps/sec: 0.1103 ms/step: 9070 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 198 |
+
[10/31 01:16:50 minwm.engine.monitor]: step 570 time/data(ms): 2.623 time/forward(ms): 2268 time/backward(ms): 6602 grad_norm: 0.3704 loss: 0.07062 steps/sec: 0.1103 ms/step: 9063 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 199 |
+
[10/31 01:18:21 minwm.engine.monitor]: step 580 time/data(ms): 2.214 time/forward(ms): 2297 time/backward(ms): 6617 grad_norm: 27.64 loss: 0.07063 steps/sec: 0.1101 ms/step: 9086 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 200 |
+
[10/31 01:19:52 minwm.engine.monitor]: step 590 time/data(ms): 1.577 time/forward(ms): 2265 time/backward(ms): 6606 grad_norm: 0.07944 loss: 0.1037 steps/sec: 0.11 ms/step: 9094 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 201 |
+
[10/31 01:21:22 minwm.engine.monitor]: step 600 time/data(ms): 2.043 time/forward(ms): 2272 time/backward(ms): 6607 grad_norm: 0.05966 loss: 0.1165 steps/sec: 0.1103 ms/step: 9066 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 202 |
+
[10/31 01:21:27 minwm.engine.checkpoint.checkpointer]: saved checkpoint /dev/shm/mwm/runs/tf_nomas4/ckpts/checkpoint_600
|
| 203 |
+
[10/31 01:22:57 minwm.engine.monitor]: step 610 time/data(ms): 2.148 time/forward(ms): 2089 time/backward(ms): 6586 grad_norm: 0.1183 loss: 0.1152 steps/sec: 0.1052 ms/step: 9510 memory/max_reserved(GiB): 30.34 memory/max_reserved(%): 38.32 memory/num_ooms: 0
|
| 204 |
+
W1031 01:23:50.877000 3209799 torch/distributed/elastic/agent/server/api.py:725] Received 15 death signal, shutting down workers
|
| 205 |
+
W1031 01:23:50.878000 3209799 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3209809 closing signal SIGTERM
|
| 206 |
+
W1031 01:23:50.881000 3209799 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3209810 closing signal SIGTERM
|
| 207 |
+
W1031 01:23:50.884000 3209799 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3209811 closing signal SIGTERM
|
| 208 |
+
W1031 01:23:50.888000 3209799 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3209812 closing signal SIGTERM
|
| 209 |
+
W1031 01:23:50.891000 3209799 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3209813 closing signal SIGTERM
|
| 210 |
+
W1031 01:23:50.895000 3209799 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3209814 closing signal SIGTERM
|
| 211 |
+
Traceback (most recent call last):
|
| 212 |
+
File "/dev/shm/mwm/venv/bin/torchrun", line 10, in <module>
|
| 213 |
+
sys.exit(main())
|
| 214 |
+
^^^^^^
|
| 215 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 357, in wrapper
|
| 216 |
+
return f(*args, **kwargs)
|
| 217 |
+
^^^^^^^^^^^^^^^^^^
|
| 218 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/run.py", line 936, in main
|
| 219 |
+
run(args)
|
| 220 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/run.py", line 927, in run
|
| 221 |
+
elastic_launch(
|
| 222 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 156, in __call__
|
| 223 |
+
return launch_agent(self._config, self._entrypoint, list(args))
|
| 224 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 225 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 284, in launch_agent
|
| 226 |
+
result = agent.run()
|
| 227 |
+
^^^^^^^^^^^
|
| 228 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/metrics/api.py", line 138, in wrapper
|
| 229 |
+
result = f(*args, **kwargs)
|
| 230 |
+
^^^^^^^^^^^^^^^^^^
|
| 231 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/agent/server/api.py", line 717, in run
|
| 232 |
+
result = self._invoke_run(role)
|
| 233 |
+
^^^^^^^^^^^^^^^^^^^^^^
|
| 234 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/agent/server/api.py", line 881, in _invoke_run
|
| 235 |
+
time.sleep(monitor_interval)
|
| 236 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/multiprocessing/api.py", line 85, in _terminate_process_handler
|
| 237 |
+
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
|
| 238 |
+
torch.distributed.elastic.multiprocessing.api.SignalException: Process 3209799 got signal: 15
|
| 239 |
+
[W1031 01:23:51.450972437 AllocatorConfig.cpp:28] Warning: PYTORCH_CUDA_ALLOC_CONF is deprecated, use PYTORCH_ALLOC_CONF instead (function operator())
|
| 240 |
+
MWM_TRAIN3 repo /dev/shm/mwm/repo data /dev/shm/mwm/data/quality char_labels none char_k 200 drop 0.1
|
| 241 |
+
MWM_TRAIN config configs/wan21/action2v/train/stage1_ar_tf_aug.py
|
| 242 |
+
MWM_TRAIN start 01:23:56 stage tf name tf_nomas4 gpus 0,1,2,3,4,5 n 6 steps 1200 lr 5e-6 init /dev/shm/mwm/exports/tf_nomas3/step_1000.pt teacher same extra checkpoint.resume=True
|
| 243 |
+
[10/31 01:24:00 minwm.distributed.sp.parallel_state]: Initializing distributed environment with world_size=6, device=cuda:0
|
| 244 |
+
[10/31 01:24:00 minwm.distributed.sp.parallel_state]: world_size=6 rank=0 local_rank=0 distributed_init_method=env:// backend=nccl
|
| 245 |
+
[Gloo] Rank 2 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 246 |
+
[Gloo] Rank 0 is connected to [Gloo] Rank 5 peer ranks. 1Expected number of connected peer ranks is : is connected to 55 peer ranks. Expected number of connected peer ranks is :
|
| 247 |
+
5
|
| 248 |
+
[Gloo] Rank 5 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 249 |
+
[Gloo] Rank [Gloo] Rank 34 is connected to is connected to 55 peer ranks. peer ranks. Expected number of connected peer ranks is : Expected number of connected peer ranks is : 55
|
| 250 |
+
|
| 251 |
+
[10/31 01:24:05 minwm.distributed.sp.nccl]: Found nccl from library libnccl.so.2
|
| 252 |
+
[10/31 01:24:05 minwm.distributed.sp.device_communicators.pynccl]: Trainer is using nccl==2.27.5
|
| 253 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 254 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 255 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 256 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 257 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 258 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 259 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 260 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 261 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 262 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 263 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 264 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 265 |
+
[Gloo] Rank 0 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 266 |
+
[Gloo] Rank 5 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 267 |
+
[Gloo] Rank 1 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 268 |
+
[Gloo] Rank 2 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 269 |
+
[Gloo] Rank 3 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 270 |
+
[Gloo] Rank 4 is connected to 5 peer ranks. Expected number of connected peer ranks is : 5
|
| 271 |
+
[10/31 01:24:06 minwm.distributed.sp.nccl]: Found nccl from library libnccl.so.2
|
| 272 |
+
[10/31 01:24:06 minwm.distributed.sp.device_communicators.pynccl]: Trainer is using nccl==2.27.5
|
| 273 |
+
[10/31 01:24:08 minwm.engine.trainer]: base RNG seed: 2050329764 (+ dp_rank)
|
| 274 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.12.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.weight']
|
| 275 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 276 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.14.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.bias', 'blocks.2.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias']
|
| 277 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 278 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.20.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.weight', 'blocks.22.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias']
|
| 279 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 280 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.0.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.29.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.15.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.weight', 'blocks.25.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.weight']
|
| 281 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 282 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.0.self_attn.prope_o.bias', 'blocks.3.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.11.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.weight', 'blocks.24.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.bias', 'blocks.20.self_attn.prope_o.weight', 'blocks.7.self_attn.prope_o.weight', 'blocks.0.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.weight', 'blocks.21.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.bias', 'blocks.9.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.bias', 'blocks.18.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.weight', 'blocks.6.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.bias', 'blocks.8.self_attn.prope_o.weight']
|
| 283 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 284 |
+
Some weights of CausalWan21Model were not initialized from the model checkpoint at ./ckpts/Wan2.1-T2V-1.3B and are newly initialized: ['blocks.0.self_attn.prope_o.bias', 'blocks.5.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.bias', 'blocks.10.self_attn.prope_o.bias', 'blocks.24.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.weight', 'blocks.1.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.weight', 'blocks.12.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.bias', 'blocks.26.self_attn.prope_o.weight', 'blocks.20.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.weight', 'blocks.23.self_attn.prope_o.weight', 'blocks.26.self_attn.prope_o.bias', 'blocks.12.self_attn.prope_o.bias', 'blocks.0.self_attn.prope_o.weight', 'blocks.19.self_attn.prope_o.bias', 'blocks.27.self_attn.prope_o.bias', 'blocks.23.self_attn.prope_o.bias', 'blocks.16.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.bias', 'blocks.13.self_attn.prope_o.bias', 'blocks.1.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.weight', 'blocks.8.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.weight', 'blocks.4.self_attn.prope_o.weight', 'blocks.27.self_attn.prope_o.weight', 'blocks.16.self_attn.prope_o.weight', 'blocks.17.self_attn.prope_o.weight', 'blocks.2.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.weight', 'blocks.10.self_attn.prope_o.weight', 'blocks.29.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.bias', 'blocks.17.self_attn.prope_o.bias', 'blocks.4.self_attn.prope_o.bias', 'blocks.22.self_attn.prope_o.bias', 'blocks.6.self_attn.prope_o.bias', 'blocks.21.self_attn.prope_o.bias', 'blocks.15.self_attn.prope_o.weight', 'blocks.28.self_attn.prope_o.bias', 'blocks.28.self_attn.prope_o.weight', 'blocks.13.self_attn.prope_o.weight', 'blocks.9.self_attn.prope_o.weight', 'blocks.14.self_attn.prope_o.weight', 'blocks.11.self_attn.prope_o.bias', 'blocks.19.self_attn.prope_o.weight', 'blocks.18.self_attn.prope_o.weight', 'blocks.5.self_attn.prope_o.weight', 'blocks.3.self_attn.prope_o.bias', 'blocks.7.self_attn.prope_o.bias', 'blocks.25.self_attn.prope_o.bias', 'blocks.14.self_attn.prope_o.bias']
|
| 285 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 286 |
+
[10/31 01:24:11 minwm.distributed.fsdp]: FSDP2: activation-checkpointed 30 layer module(s)
|
| 287 |
+
[10/31 01:24:12 minwm.distributed.fsdp]: FSDP2: sharded 30 layer module(s) in FSDPCausalWan21Model
|
| 288 |
+
[rank5]: Traceback (most recent call last):
|
| 289 |
+
[rank5]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 74, in <module>
|
| 290 |
+
[rank5]: main()
|
| 291 |
+
[rank5]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 69, in main
|
| 292 |
+
[rank5]: trainer = build_trainer(cfg)
|
| 293 |
+
[rank5]: ^^^^^^^^^^^^^^^^^^
|
| 294 |
+
[rank5]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 50, in build_trainer
|
| 295 |
+
[rank5]: return trainer_cls(MWMConfig.from_dict(cfg))
|
| 296 |
+
[rank5]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 297 |
+
[rank5]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 167, in __init__
|
| 298 |
+
[rank5]: self.dataloader = self.build_dataloader(self.cfg.data)
|
| 299 |
+
[rank5]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 300 |
+
[rank5]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 386, in build_dataloader
|
| 301 |
+
[rank5]: return _build_dataloader_cfg(data)
|
| 302 |
+
[rank5]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 303 |
+
[rank5]: File "/dev/shm/mwm/repo/minwm/data/build.py", line 68, in build_dataloader
|
| 304 |
+
[rank5]: dataset = build(data.dataset)
|
| 305 |
+
[rank5]: ^^^^^^^^^^^^^^^^^^^
|
| 306 |
+
[rank5]: File "/dev/shm/mwm/repo/minwm/config/lazy.py", line 126, in build
|
| 307 |
+
[rank5]: return cls(**kwargs)
|
| 308 |
+
[rank5]: ^^^^^^^^^^^^^
|
| 309 |
+
[rank5]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 204, in __init__
|
| 310 |
+
[rank5]: self._sds = _open_shards(data_path)
|
| 311 |
+
[rank5]: ^^^^^^^^^^^^^^^^^^^^^^^
|
| 312 |
+
[rank5]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 63, in _open_shards
|
| 313 |
+
[rank5]: envs.append(_open(sub))
|
| 314 |
+
[rank5]: ^^^^^^^^^^
|
| 315 |
+
[rank5]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 27, in _open
|
| 316 |
+
[rank5]: return lmdb.open(path, readonly=True, lock=False, readahead=False, meminit=False)
|
| 317 |
+
[rank5]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 318 |
+
[rank5]: lmdb.Error: The environment '/dev/shm/mwm/data/quality/shard_q001b' is already open in this process.
|
| 319 |
+
[rank4]: Traceback (most recent call last):
|
| 320 |
+
[rank4]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 74, in <module>
|
| 321 |
+
[rank4]: main()
|
| 322 |
+
[rank4]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 69, in main
|
| 323 |
+
[rank4]: trainer = build_trainer(cfg)
|
| 324 |
+
[rank4]: ^^^^^^^^^^^^^^^^^^
|
| 325 |
+
[rank4]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 50, in build_trainer
|
| 326 |
+
[rank4]: return trainer_cls(MWMConfig.from_dict(cfg))
|
| 327 |
+
[rank4]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 328 |
+
[rank4]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 167, in __init__
|
| 329 |
+
[rank4]: self.dataloader = self.build_dataloader(self.cfg.data)
|
| 330 |
+
[rank4]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 331 |
+
[rank4]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 386, in build_dataloader
|
| 332 |
+
[rank4]: return _build_dataloader_cfg(data)
|
| 333 |
+
[rank4]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 334 |
+
[rank4]: File "/dev/shm/mwm/repo/minwm/data/build.py", line 68, in build_dataloader
|
| 335 |
+
[rank4]: dataset = build(data.dataset)
|
| 336 |
+
[rank4]: ^^^^^^^^^^^^^^^^^^^
|
| 337 |
+
[rank4]: File "/dev/shm/mwm/repo/minwm/config/lazy.py", line 126, in build
|
| 338 |
+
[rank4]: return cls(**kwargs)
|
| 339 |
+
[rank4]: ^^^^^^^^^^^^^
|
| 340 |
+
[rank4]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 204, in __init__
|
| 341 |
+
[rank4]: self._sds = _open_shards(data_path)
|
| 342 |
+
[rank4]: ^^^^^^^^^^^^^^^^^^^^^^^
|
| 343 |
+
[rank4]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 63, in _open_shards
|
| 344 |
+
[rank4]: envs.append(_open(sub))
|
| 345 |
+
[rank4]: ^^^^^^^^^^
|
| 346 |
+
[rank4]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 27, in _open
|
| 347 |
+
[rank4]: return lmdb.open(path, readonly=True, lock=False, readahead=False, meminit=False)
|
| 348 |
+
[rank4]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 349 |
+
[rank4]: lmdb.Error: The environment '/dev/shm/mwm/data/quality/shard_q001b' is already open in this process.
|
| 350 |
+
[rank4]:[W1031 01:25:04.127750030 ProcessGroupNCCL.cpp:1524] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
|
| 351 |
+
[rank5]:[W1031 01:25:04.130113754 ProcessGroupNCCL.cpp:1524] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
|
| 352 |
+
[rank2]: Traceback (most recent call last):
|
| 353 |
+
[rank2]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 74, in <module>
|
| 354 |
+
[rank2]: main()
|
| 355 |
+
[rank2]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 69, in main
|
| 356 |
+
[rank2]: trainer = build_trainer(cfg)
|
| 357 |
+
[rank2]: ^^^^^^^^^^^^^^^^^^
|
| 358 |
+
[rank2]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 50, in build_trainer
|
| 359 |
+
[rank2]: return trainer_cls(MWMConfig.from_dict(cfg))
|
| 360 |
+
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 361 |
+
[rank2]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 167, in __init__
|
| 362 |
+
[rank2]: self.dataloader = self.build_dataloader(self.cfg.data)
|
| 363 |
+
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 364 |
+
[rank2]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 386, in build_dataloader
|
| 365 |
+
[rank2]: return _build_dataloader_cfg(data)
|
| 366 |
+
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 367 |
+
[rank2]: File "/dev/shm/mwm/repo/minwm/data/build.py", line 68, in build_dataloader
|
| 368 |
+
[rank2]: dataset = build(data.dataset)
|
| 369 |
+
[rank2]: ^^^^^^^^^^^^^^^^^^^
|
| 370 |
+
[rank2]: File "/dev/shm/mwm/repo/minwm/config/lazy.py", line 126, in build
|
| 371 |
+
[rank2]: return cls(**kwargs)
|
| 372 |
+
[rank2]: ^^^^^^^^^^^^^
|
| 373 |
+
[rank2]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 204, in __init__
|
| 374 |
+
[rank2]: self._sds = _open_shards(data_path)
|
| 375 |
+
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^
|
| 376 |
+
[rank2]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 63, in _open_shards
|
| 377 |
+
[rank2]: envs.append(_open(sub))
|
| 378 |
+
[rank2]: ^^^^^^^^^^
|
| 379 |
+
[rank2]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 27, in _open
|
| 380 |
+
[rank2]: return lmdb.open(path, readonly=True, lock=False, readahead=False, meminit=False)
|
| 381 |
+
[rank2]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 382 |
+
[rank2]: lmdb.Error: The environment '/dev/shm/mwm/data/quality/shard_q001b' is already open in this process.
|
| 383 |
+
[rank3]: Traceback (most recent call last):
|
| 384 |
+
[rank3]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 74, in <module>
|
| 385 |
+
[rank3]: main()
|
| 386 |
+
[rank3]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 69, in main
|
| 387 |
+
[rank3]: trainer = build_trainer(cfg)
|
| 388 |
+
[rank3]: ^^^^^^^^^^^^^^^^^^
|
| 389 |
+
[rank3]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 50, in build_trainer
|
| 390 |
+
[rank3]: return trainer_cls(MWMConfig.from_dict(cfg))
|
| 391 |
+
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 392 |
+
[rank3]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 167, in __init__
|
| 393 |
+
[rank3]: self.dataloader = self.build_dataloader(self.cfg.data)
|
| 394 |
+
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 395 |
+
[rank3]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 386, in build_dataloader
|
| 396 |
+
[rank3]: return _build_dataloader_cfg(data)
|
| 397 |
+
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 398 |
+
[rank3]: File "/dev/shm/mwm/repo/minwm/data/build.py", line 68, in build_dataloader
|
| 399 |
+
[rank3]: dataset = build(data.dataset)
|
| 400 |
+
[rank3]: ^^^^^^^^^^^^^^^^^^^
|
| 401 |
+
[rank3]: File "/dev/shm/mwm/repo/minwm/config/lazy.py", line 126, in build
|
| 402 |
+
[rank3]: return cls(**kwargs)
|
| 403 |
+
[rank3]: ^^^^^^^^^^^^^
|
| 404 |
+
[rank3]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 204, in __init__
|
| 405 |
+
[rank3]: self._sds = _open_shards(data_path)
|
| 406 |
+
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^
|
| 407 |
+
[rank3]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 63, in _open_shards
|
| 408 |
+
[rank3]: envs.append(_open(sub))
|
| 409 |
+
[rank3]: ^^^^^^^^^^
|
| 410 |
+
[rank3]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 27, in _open
|
| 411 |
+
[rank3]: return lmdb.open(path, readonly=True, lock=False, readahead=False, meminit=False)
|
| 412 |
+
[rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 413 |
+
[rank3]: lmdb.Error: The environment '/dev/shm/mwm/data/quality/shard_q001b' is already open in this process.
|
| 414 |
+
[rank5]:[W1031 01:25:05.054446080 AllocatorConfig.cpp:28] Warning: PYTORCH_CUDA_ALLOC_CONF is deprecated, use PYTORCH_ALLOC_CONF instead (function operator())
|
| 415 |
+
[rank4]:[W1031 01:25:05.073169814 AllocatorConfig.cpp:28] Warning: PYTORCH_CUDA_ALLOC_CONF is deprecated, use PYTORCH_ALLOC_CONF instead (function operator())
|
| 416 |
+
[rank0]: Traceback (most recent call last):
|
| 417 |
+
[rank0]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 74, in <module>
|
| 418 |
+
[rank0]: main()
|
| 419 |
+
[rank0]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 69, in main
|
| 420 |
+
[rank0]: trainer = build_trainer(cfg)
|
| 421 |
+
[rank0]: ^^^^^^^^^^^^^^^^^^
|
| 422 |
+
[rank0]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 50, in build_trainer
|
| 423 |
+
[rank0]: return trainer_cls(MWMConfig.from_dict(cfg))
|
| 424 |
+
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 425 |
+
[rank0]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 167, in __init__
|
| 426 |
+
[rank0]: self.dataloader = self.build_dataloader(self.cfg.data)
|
| 427 |
+
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 428 |
+
[rank0]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 386, in build_dataloader
|
| 429 |
+
[rank0]: return _build_dataloader_cfg(data)
|
| 430 |
+
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 431 |
+
[rank0]: File "/dev/shm/mwm/repo/minwm/data/build.py", line 68, in build_dataloader
|
| 432 |
+
[rank0]: dataset = build(data.dataset)
|
| 433 |
+
[rank0]: ^^^^^^^^^^^^^^^^^^^
|
| 434 |
+
[rank0]: File "/dev/shm/mwm/repo/minwm/config/lazy.py", line 126, in build
|
| 435 |
+
[rank0]: return cls(**kwargs)
|
| 436 |
+
[rank0]: ^^^^^^^^^^^^^
|
| 437 |
+
[rank0]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 204, in __init__
|
| 438 |
+
[rank0]: self._sds = _open_shards(data_path)
|
| 439 |
+
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^
|
| 440 |
+
[rank0]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 63, in _open_shards
|
| 441 |
+
[rank0]: envs.append(_open(sub))
|
| 442 |
+
[rank0]: ^^^^^^^^^^
|
| 443 |
+
[rank0]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 27, in _open
|
| 444 |
+
[rank0]: return lmdb.open(path, readonly=True, lock=False, readahead=False, meminit=False)
|
| 445 |
+
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 446 |
+
[rank0]: lmdb.Error: The environment '/dev/shm/mwm/data/quality/shard_q001b' is already open in this process.
|
| 447 |
+
[rank1]: Traceback (most recent call last):
|
| 448 |
+
[rank1]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 74, in <module>
|
| 449 |
+
[rank1]: main()
|
| 450 |
+
[rank1]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 69, in main
|
| 451 |
+
[rank1]: trainer = build_trainer(cfg)
|
| 452 |
+
[rank1]: ^^^^^^^^^^^^^^^^^^
|
| 453 |
+
[rank1]: File "/dev/shm/mwm/minWM-main/tools/train_mwm.py", line 50, in build_trainer
|
| 454 |
+
[rank1]: return trainer_cls(MWMConfig.from_dict(cfg))
|
| 455 |
+
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 456 |
+
[rank1]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 167, in __init__
|
| 457 |
+
[rank1]: self.dataloader = self.build_dataloader(self.cfg.data)
|
| 458 |
+
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 459 |
+
[rank1]: File "/dev/shm/mwm/repo/minwm/engine/trainer.py", line 386, in build_dataloader
|
| 460 |
+
[rank1]: return _build_dataloader_cfg(data)
|
| 461 |
+
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 462 |
+
[rank1]: File "/dev/shm/mwm/repo/minwm/data/build.py", line 68, in build_dataloader
|
| 463 |
+
[rank1]: dataset = build(data.dataset)
|
| 464 |
+
[rank1]: ^^^^^^^^^^^^^^^^^^^
|
| 465 |
+
[rank1]: File "/dev/shm/mwm/repo/minwm/config/lazy.py", line 126, in build
|
| 466 |
+
[rank1]: return cls(**kwargs)
|
| 467 |
+
[rank1]: ^^^^^^^^^^^^^
|
| 468 |
+
[rank1]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 204, in __init__
|
| 469 |
+
[rank1]: self._sds = _open_shards(data_path)
|
| 470 |
+
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^
|
| 471 |
+
[rank1]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 63, in _open_shards
|
| 472 |
+
[rank1]: envs.append(_open(sub))
|
| 473 |
+
[rank1]: ^^^^^^^^^^
|
| 474 |
+
[rank1]: File "/dev/shm/mwm/repo/minwm/data/datasets/lmdb.py", line 27, in _open
|
| 475 |
+
[rank1]: return lmdb.open(path, readonly=True, lock=False, readahead=False, meminit=False)
|
| 476 |
+
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 477 |
+
[rank1]: lmdb.Error: The environment '/dev/shm/mwm/data/quality/shard_q001b' is already open in this process.
|
| 478 |
+
W1031 01:25:05.906000 3353220 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3353230 closing signal SIGTERM
|
| 479 |
+
W1031 01:25:05.907000 3353220 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3353231 closing signal SIGTERM
|
| 480 |
+
W1031 01:25:05.908000 3353220 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3353232 closing signal SIGTERM
|
| 481 |
+
W1031 01:25:05.909000 3353220 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3353233 closing signal SIGTERM
|
| 482 |
+
W1031 01:25:05.910000 3353220 torch/distributed/elastic/multiprocessing/api.py:908] Sending process 3353234 closing signal SIGTERM
|
| 483 |
+
E1031 01:25:07.140000 3353220 torch/distributed/elastic/multiprocessing/api.py:882] failed (exitcode: 1) local_rank: 5 (pid: 3353235) of binary: /dev/shm/mwm/venv/bin/python
|
| 484 |
+
Traceback (most recent call last):
|
| 485 |
+
File "/dev/shm/mwm/venv/bin/torchrun", line 10, in <module>
|
| 486 |
+
sys.exit(main())
|
| 487 |
+
^^^^^^
|
| 488 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 357, in wrapper
|
| 489 |
+
return f(*args, **kwargs)
|
| 490 |
+
^^^^^^^^^^^^^^^^^^
|
| 491 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/run.py", line 936, in main
|
| 492 |
+
run(args)
|
| 493 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/run.py", line 927, in run
|
| 494 |
+
elastic_launch(
|
| 495 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 156, in __call__
|
| 496 |
+
return launch_agent(self._config, self._entrypoint, list(args))
|
| 497 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 498 |
+
File "/dev/shm/mwm/venv/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 293, in launch_agent
|
| 499 |
+
raise ChildFailedError(
|
| 500 |
+
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
|
| 501 |
+
============================================================
|
| 502 |
+
tools/train_mwm.py FAILED
|
| 503 |
+
------------------------------------------------------------
|
| 504 |
+
Failures:
|
| 505 |
+
<NO_OTHER_FAILURES>
|
| 506 |
+
------------------------------------------------------------
|
| 507 |
+
Root Cause (first observed failure):
|
| 508 |
+
[0]:
|
| 509 |
+
time : 2026-10-31_01:25:05
|
| 510 |
+
host : fsxznwc8ls-simpli-server-864dcff478-4tj44
|
| 511 |
+
rank : 5 (local_rank: 5)
|
| 512 |
+
exitcode : 1 (pid: 3353235)
|
| 513 |
+
error_file: <N/A>
|
| 514 |
+
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
|
| 515 |
+
============================================================
|
| 516 |
+
[W1031 01:25:07.004007112 AllocatorConfig.cpp:28] Warning: PYTORCH_CUDA_ALLOC_CONF is deprecated, use PYTORCH_ALLOC_CONF instead (function operator())
|
| 517 |
+
rc=1 MWM_TRAIN_END 01:25:07 tf_nomas4
|