granularity results granularity_next_b200/tiera_topk_trace @ 2026-09-17T03:04:56Z from hp-aiinfra-interactive-aghosh-8-xzthl-8xb200-moe-cg-0
Browse files- .gitattributes +1 -0
- granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K10__echo__matched__seq4096__gbs16__cap1p1/nsys/run.env +102 -0
- granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K10__echo__matched__seq4096__gbs16__cap1p1/nsys/train.log +0 -0
- granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/G4_K8__echo__matched__seq4096__gbs16__cap1p109375.nsys-rep +3 -0
- granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/train.log +983 -0
- granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/verify_trace_ranks.log +6 -0
- granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/trace_results.tsv +1 -0
- granularity_next_b200/tiera_topk_trace/hf_watcher.log +3 -0
- granularity_next_b200/tiera_topk_trace/study.log +7 -0
.gitattributes
CHANGED
|
@@ -88,3 +88,4 @@ granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G3_K8__e
|
|
| 88 |
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K2__echo__matched__seq4096__gbs16__cap1p265625/nsys/G4_K2__echo__matched__seq4096__gbs16__cap1p265625.nsys-rep filter=lfs diff=lfs merge=lfs -text
|
| 89 |
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K4__echo__matched__seq4096__gbs16__cap1p171875/nsys/G4_K4__echo__matched__seq4096__gbs16__cap1p171875.nsys-rep filter=lfs diff=lfs merge=lfs -text
|
| 90 |
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667/nsys/G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667.nsys-rep filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 88 |
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K2__echo__matched__seq4096__gbs16__cap1p265625/nsys/G4_K2__echo__matched__seq4096__gbs16__cap1p265625.nsys-rep filter=lfs diff=lfs merge=lfs -text
|
| 89 |
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K4__echo__matched__seq4096__gbs16__cap1p171875/nsys/G4_K4__echo__matched__seq4096__gbs16__cap1p171875.nsys-rep filter=lfs diff=lfs merge=lfs -text
|
| 90 |
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667/nsys/G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667.nsys-rep filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/G4_K8__echo__matched__seq4096__gbs16__cap1p109375.nsys-rep filter=lfs diff=lfs merge=lfs -text
|
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K10__echo__matched__seq4096__gbs16__cap1p1/nsys/run.env
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
backend=echo
|
| 2 |
+
config=G4_K10
|
| 3 |
+
family=tierA
|
| 4 |
+
source_model=
|
| 5 |
+
standard_num_layers=
|
| 6 |
+
base_rung=G4
|
| 7 |
+
repo=/workspace/Megatron-MoE-Echo
|
| 8 |
+
branch=bracing-regions-through-kernels
|
| 9 |
+
commit=9a236793
|
| 10 |
+
num_layers=16
|
| 11 |
+
hidden=4096
|
| 12 |
+
ffn_hidden=14336
|
| 13 |
+
moe_ffn_hidden=896
|
| 14 |
+
num_experts=128
|
| 15 |
+
topk=10
|
| 16 |
+
experts_per_rank=16
|
| 17 |
+
expert_params=11010048
|
| 18 |
+
heads=32
|
| 19 |
+
kv_groups=8
|
| 20 |
+
kv_channels=
|
| 21 |
+
qk_layernorm=0
|
| 22 |
+
shared_ffn=0
|
| 23 |
+
shared_expert_overlap=0
|
| 24 |
+
moe_token_dispatcher=flex
|
| 25 |
+
mla=0
|
| 26 |
+
q_lora_rank=
|
| 27 |
+
kv_lora_rank=512
|
| 28 |
+
qk_head_dim=128
|
| 29 |
+
qk_pos_emb_head_dim=64
|
| 30 |
+
v_head_dim=128
|
| 31 |
+
dense_first_layers=0
|
| 32 |
+
moe_layers=16
|
| 33 |
+
rotary_base=1000000
|
| 34 |
+
rotary_percent=1.0
|
| 35 |
+
rotary_scaling=
|
| 36 |
+
mscale=
|
| 37 |
+
mscale_all_dim=
|
| 38 |
+
qkv_bias=0
|
| 39 |
+
router_balancing=aux_loss
|
| 40 |
+
aux_loss_coeff=1e-2
|
| 41 |
+
router_pre_softmax=0
|
| 42 |
+
router_fusion=0
|
| 43 |
+
router_dtype=fp32
|
| 44 |
+
router_groups=
|
| 45 |
+
router_group_topk=
|
| 46 |
+
router_score_function=softmax
|
| 47 |
+
router_expert_bias=0
|
| 48 |
+
router_bias_update_rate=
|
| 49 |
+
router_topk_scaling_factor=
|
| 50 |
+
shared_expert_gate=0
|
| 51 |
+
apply_layernorm_1p=0
|
| 52 |
+
attention_output_gate=0
|
| 53 |
+
linear_attention_type=
|
| 54 |
+
linear_attention_freq=
|
| 55 |
+
linear_conv_kernel_dim=
|
| 56 |
+
linear_key_head_dim=
|
| 57 |
+
linear_value_head_dim=
|
| 58 |
+
linear_num_key_heads=
|
| 59 |
+
linear_num_value_heads=
|
| 60 |
+
mtp_num_layers=0
|
| 61 |
+
mtp_loss_scaling_factor=0.1
|
| 62 |
+
no_weight_decay_cond_type=
|
| 63 |
+
max_position_embeddings=32768
|
| 64 |
+
init_method_std=0.01
|
| 65 |
+
device_initiated_grouped_gemm=1
|
| 66 |
+
norm_epsilon=1e-5
|
| 67 |
+
seq_length=4096
|
| 68 |
+
micro_batch_size=1
|
| 69 |
+
global_batch_size=16
|
| 70 |
+
num_microbatches=2
|
| 71 |
+
assignments_per_rank=40960
|
| 72 |
+
mean_tokens_per_expert=2560
|
| 73 |
+
slot_policy=matched
|
| 74 |
+
slots_per_rank=16
|
| 75 |
+
capacity_mode=static
|
| 76 |
+
capacity=1.1
|
| 77 |
+
cuda_graph=1
|
| 78 |
+
probe_mode=0
|
| 79 |
+
async_grad_reduce=0
|
| 80 |
+
branch_role=timing
|
| 81 |
+
memory_dump_mode=none
|
| 82 |
+
memory_snapshot_path=
|
| 83 |
+
cuda_graph_warmup_steps=3
|
| 84 |
+
recompute=none
|
| 85 |
+
force_balance=0
|
| 86 |
+
train_iters=10
|
| 87 |
+
ep_size=8
|
| 88 |
+
echo_dispatch_overlap=1
|
| 89 |
+
echo_dispatch_recompute=0
|
| 90 |
+
ultraep_quota_min_tokens=
|
| 91 |
+
ultraep_weight_sync_join=
|
| 92 |
+
profile_enable=1
|
| 93 |
+
kernel_trace=1
|
| 94 |
+
fp8_mode=mxfp8
|
| 95 |
+
fp8_recipe=mxfp8
|
| 96 |
+
training_seed=1234
|
| 97 |
+
learning_rate=1e-4
|
| 98 |
+
min_learning_rate=1.0e-5
|
| 99 |
+
lr_warmup_iters=5
|
| 100 |
+
state_dump_enable=0
|
| 101 |
+
state_dump_dir=
|
| 102 |
+
moonep_assert_no_pending_reduce=0
|
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K10__echo__matched__seq4096__gbs16__cap1p1/nsys/train.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/G4_K8__echo__matched__seq4096__gbs16__cap1p109375.nsys-rep
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29cbcc6522af47be42598f13f2a180ba3814ec548870bbccc6be9e1a5dc54bc6
|
| 3 |
+
size 19955945
|
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/train.log
CHANGED
|
@@ -560,3 +560,986 @@ WARNING:megatron.core.rerun_state_machine:RerunStateMachine initialized in mode
|
|
| 560 |
> initializing torch distributed ...
|
| 561 |
/workspace/Megatron-MoE-Echo/megatron/training/arguments.py:831: UserWarning: Disabling sequence parallelism because tensor model parallelism is disabled
|
| 562 |
warnings.warn("Disabling sequence parallelism because tensor model parallelism is disabled")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 560 |
> initializing torch distributed ...
|
| 561 |
/workspace/Megatron-MoE-Echo/megatron/training/arguments.py:831: UserWarning: Disabling sequence parallelism because tensor model parallelism is disabled
|
| 562 |
warnings.warn("Disabling sequence parallelism because tensor model parallelism is disabled")
|
| 563 |
+
/workspace/Megatron-MoE-Echo/megatron/training/arguments.py:831: UserWarning: Disabling sequence parallelism because tensor model parallelism is disabled
|
| 564 |
+
warnings.warn("Disabling sequence parallelism because tensor model parallelism is disabled")
|
| 565 |
+
/workspace/Megatron-MoE-Echo/megatron/training/arguments.py:831: UserWarning: Disabling sequence parallelism because tensor model parallelism is disabled
|
| 566 |
+
warnings.warn("Disabling sequence parallelism because tensor model parallelism is disabled")
|
| 567 |
+
/workspace/Megatron-MoE-Echo/megatron/training/arguments.py:831: UserWarning: Disabling sequence parallelism because tensor model parallelism is disabled
|
| 568 |
+
warnings.warn("Disabling sequence parallelism because tensor model parallelism is disabled")
|
| 569 |
+
/workspace/Megatron-MoE-Echo/megatron/training/arguments.py:831: UserWarning: Disabling sequence parallelism because tensor model parallelism is disabled
|
| 570 |
+
warnings.warn("Disabling sequence parallelism because tensor model parallelism is disabled")
|
| 571 |
+
/workspace/Megatron-MoE-Echo/megatron/training/arguments.py:831: UserWarning: Disabling sequence parallelism because tensor model parallelism is disabled
|
| 572 |
+
warnings.warn("Disabling sequence parallelism because tensor model parallelism is disabled")
|
| 573 |
+
/workspace/Megatron-MoE-Echo/megatron/training/arguments.py:831: UserWarning: Disabling sequence parallelism because tensor model parallelism is disabled
|
| 574 |
+
warnings.warn("Disabling sequence parallelism because tensor model parallelism is disabled")
|
| 575 |
+
WARNING: one_logger package is required to enable e2e metrics tracking. please go to https://confluence.nvidia.com/display/MLWFO/Package+Repositories for details to install it
|
| 576 |
+
[Gloo] Rank 1 is connected to 7 peer ranks. Expected number of connected peer ranks is : 7
|
| 577 |
+
[Gloo] Rank 0 is connected to 7 peer ranks. Expected number of connected peer ranks is : 7
|
| 578 |
+
[Gloo] Rank 2 is connected to 7 peer ranks. Expected number of connected peer ranks is : 7
|
| 579 |
+
[Gloo] Rank 3 is connected to 7 peer ranks. [Gloo] Rank Expected number of connected peer ranks is : 7
|
| 580 |
+
5 is connected to 7 peer ranks. Expected number of connected peer ranks is : 7
|
| 581 |
+
[Gloo] Rank 4 is connected to 7 peer ranks. Expected number of connected peer ranks is : 7
|
| 582 |
+
[Gloo] Rank [Gloo] Rank 7 is connected to 76 peer ranks. is connected to Expected number of connected peer ranks is : 77 peer ranks. Expected number of connected peer ranks is : 7
|
| 583 |
+
|
| 584 |
+
[Gloo] Rank [Gloo] Rank 7 is connected to 70 peer ranks. is connected to Expected number of connected peer ranks is : 77 peer ranks. Expected number of connected peer ranks is : 7
|
| 585 |
+
|
| 586 |
+
[Gloo] Rank 1 is connected to 7 peer ranks. Expected number of connected peer ranks is : 7
|
| 587 |
+
[Gloo] Rank 2 is connected to 7 peer ranks. Expected number of connected peer ranks is : 7
|
| 588 |
+
[Gloo] Rank 4 is connected to 7 peer ranks. Expected number of connected peer ranks is : 7
|
| 589 |
+
[Gloo] Rank 3 is connected to [Gloo] Rank 57 is connected to peer ranks. 7Expected number of connected peer ranks is : peer ranks. 7Expected number of connected peer ranks is :
|
| 590 |
+
7
|
| 591 |
+
[Gloo] Rank 6 is connected to 7 peer ranks. Expected number of connected peer ranks is : 7
|
| 592 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 593 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 594 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 595 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 596 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 597 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 598 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 599 |
+
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
|
| 600 |
+
> initialized tensor model parallel with size 1
|
| 601 |
+
> initialized pipeline model parallel with size 1
|
| 602 |
+
> setting random seeds to 1234 ...
|
| 603 |
+
[rank1]:[W917 02:54:57.228066964 ProcessGroupNCCL.cpp:4789] [PG ID 0 PG GUID 0 Rank 1] using GPU 1 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can specify device_id in init_process_group() to force use of a particular device.
|
| 604 |
+
[rank7]:[W917 02:54:57.228203329 ProcessGroupNCCL.cpp:4789] [PG ID 0 PG GUID 0 Rank 7] using GPU 7 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can specify device_id in init_process_group() to force use of a particular device.
|
| 605 |
+
[rank3]:[W917 02:54:57.228215283 ProcessGroupNCCL.cpp:4789] [PG ID 0 PG GUID 0 Rank 3] using GPU 3 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can specify device_id in init_process_group() to force use of a particular device.
|
| 606 |
+
[rank2]:[W917 02:54:57.228230940 ProcessGroupNCCL.cpp:4789] [PG ID 0 PG GUID 0 Rank 2] using GPU 2 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can specify device_id in init_process_group() to force use of a particular device.
|
| 607 |
+
[rank4]:[W917 02:54:57.228248236 ProcessGroupNCCL.cpp:4789] [PG ID 0 PG GUID 0 Rank 4] using GPU 4 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can specify device_id in init_process_group() to force use of a particular device.
|
| 608 |
+
[rank6]:[W917 02:54:57.228282259 ProcessGroupNCCL.cpp:4789] [PG ID 0 PG GUID 0 Rank 6] using GPU 6 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can specify device_id in init_process_group() to force use of a particular device.
|
| 609 |
+
[rank5]:[W917 02:54:57.228608053 ProcessGroupNCCL.cpp:4789] [PG ID 0 PG GUID 0 Rank 5] using GPU 5 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can specify device_id in init_process_group() to force use of a particular device.
|
| 610 |
+
> compiling dataset index builder ...
|
| 611 |
+
make: Entering directory '/workspace/Megatron-MoE-Echo/megatron/core/datasets'
|
| 612 |
+
make: Nothing to be done for 'default'.
|
| 613 |
+
make: Leaving directory '/workspace/Megatron-MoE-Echo/megatron/core/datasets'
|
| 614 |
+
>>> done with dataset index builder. Compilation time: 0.429 seconds
|
| 615 |
+
WARNING: constraints for invoking optimized fused softmax kernel are not met. We default back to unfused kernel invocations.
|
| 616 |
+
> compiling and loading fused kernels ...
|
| 617 |
+
[rank0]:[W917 02:54:57.830667453 ProcessGroupNCCL.cpp:4789] [PG ID 0 PG GUID 0 Rank 0] using GPU 0 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can specify device_id in init_process_group() to force use of a particular device.
|
| 618 |
+
>>> done with compiling and loading fused kernels. Compilation time: 3.957 seconds
|
| 619 |
+
time to initialize megatron (seconds): 9.916
|
| 620 |
+
[after megatron is initialized] datetime: 2026-09-17 02:55:03
|
| 621 |
+
building GPT model ...
|
| 622 |
+
/usr/local/lib/python3.12/dist-packages/transformer_engine/pytorch/cpu_offload.py:708: DeprecationWarning: Offloading weights is deprecated. Using offload_weights=True does not have any effect.
|
| 623 |
+
warnings.warn(
|
| 624 |
+
/usr/local/lib/python3.12/dist-packages/transformer_engine/pytorch/cpu_offload.py:708: DeprecationWarning: Offloading weights is deprecated. Using offload_weights=True does not have any effect.
|
| 625 |
+
warnings.warn(
|
| 626 |
+
/usr/local/lib/python3.12/dist-packages/transformer_engine/pytorch/cpu_offload.py:708: DeprecationWarning: Offloading weights is deprecated. Using offload_weights=True does not have any effect.
|
| 627 |
+
warnings.warn(
|
| 628 |
+
/usr/local/lib/python3.12/dist-packages/transformer_engine/pytorch/cpu_offload.py:708: DeprecationWarning: Offloading weights is deprecated. Using offload_weights=True does not have any effect.
|
| 629 |
+
warnings.warn(
|
| 630 |
+
/usr/local/lib/python3.12/dist-packages/transformer_engine/pytorch/cpu_offload.py:708: DeprecationWarning: Offloading weights is deprecated. Using offload_weights=True does not have any effect.
|
| 631 |
+
warnings.warn(
|
| 632 |
+
/usr/local/lib/python3.12/dist-packages/transformer_engine/pytorch/cpu_offload.py:708: DeprecationWarning: Offloading weights is deprecated. Using offload_weights=True does not have any effect.
|
| 633 |
+
warnings.warn(
|
| 634 |
+
/usr/local/lib/python3.12/dist-packages/transformer_engine/pytorch/cpu_offload.py:708: DeprecationWarning: Offloading weights is deprecated. Using offload_weights=True does not have any effect.
|
| 635 |
+
warnings.warn(
|
| 636 |
+
/usr/local/lib/python3.12/dist-packages/transformer_engine/pytorch/cpu_offload.py:708: DeprecationWarning: Offloading weights is deprecated. Using offload_weights=True does not have any effect.
|
| 637 |
+
warnings.warn(
|
| 638 |
+
> number of parameters on (tensor, pipeline) model parallel rank (0, 0): 3910275072
|
| 639 |
+
INFO:megatron.core.distributed.distributed_data_parallel:Setting up DistributedDataParallel with config DistributedDataParallelConfig(grad_reduce_in_fp32=True, overlap_grad_reduce=True, overlap_param_gather=True, align_param_gather=False, use_distributed_optimizer=True, num_distributed_optimizer_instances=1, check_for_nan_in_grad=False, check_for_large_grads=False, bucket_size=40000000, pad_buckets_for_high_nccl_busbw=False, average_in_collective=False, fp8_param_gather=False, reuse_grad_buf_for_mxfp8_param_ag=False, use_custom_fsdp=False, data_parallel_sharding_strategy='no_shard', gradient_reduce_div_fusion=True, suggested_communication_unit_size=None, preserve_fp32_weights=True, keep_fp8_transpose_cache_when_using_custom_fsdp=False, nccl_ub=False, fsdp_double_buffer=False)
|
| 640 |
+
INFO:megatron.core.distributed.param_and_grad_buffer:Number of buckets for gradient all-reduce / reduce-scatter: 18
|
| 641 |
+
Params for bucket 1 (206045184 elements, 206045184 padded size):
|
| 642 |
+
module.output_layer.weight
|
| 643 |
+
Params for bucket 2 (42479616 elements, 42479616 padded size):
|
| 644 |
+
module.decoder.final_layernorm.weight
|
| 645 |
+
module.decoder.layers.15.mlp.router.weight
|
| 646 |
+
module.decoder.layers.15.self_attention.linear_qkv.layer_norm_weight
|
| 647 |
+
module.decoder.layers.15.pre_mlp_layernorm.weight
|
| 648 |
+
module.decoder.layers.15.self_attention.linear_qkv.weight
|
| 649 |
+
module.decoder.layers.15.self_attention.linear_proj.weight
|
| 650 |
+
Params for bucket 3 (42475520 elements, 42475520 padded size):
|
| 651 |
+
module.decoder.layers.14.self_attention.linear_qkv.weight
|
| 652 |
+
module.decoder.layers.14.pre_mlp_layernorm.weight
|
| 653 |
+
module.decoder.layers.14.mlp.router.weight
|
| 654 |
+
module.decoder.layers.14.self_attention.linear_proj.weight
|
| 655 |
+
module.decoder.layers.14.self_attention.linear_qkv.layer_norm_weight
|
| 656 |
+
Params for bucket 4 (42475520 elements, 42475520 padded size):
|
| 657 |
+
module.decoder.layers.13.mlp.router.weight
|
| 658 |
+
module.decoder.layers.13.self_attention.linear_qkv.layer_norm_weight
|
| 659 |
+
module.decoder.layers.13.self_attention.linear_proj.weight
|
| 660 |
+
module.decoder.layers.13.pre_mlp_layernorm.weight
|
| 661 |
+
module.decoder.layers.13.self_attention.linear_qkv.weight
|
| 662 |
+
Params for bucket 5 (42475520 elements, 42475520 padded size):
|
| 663 |
+
module.decoder.layers.12.pre_mlp_layernorm.weight
|
| 664 |
+
module.decoder.layers.12.mlp.router.weight
|
| 665 |
+
module.decoder.layers.12.self_attention.linear_qkv.weight
|
| 666 |
+
module.decoder.layers.12.self_attention.linear_qkv.layer_norm_weight
|
| 667 |
+
module.decoder.layers.12.self_attention.linear_proj.weight
|
| 668 |
+
Params for bucket 6 (42475520 elements, 42475520 padded size):
|
| 669 |
+
module.decoder.layers.11.mlp.router.weight
|
| 670 |
+
module.decoder.layers.11.self_attention.linear_qkv.weight
|
| 671 |
+
module.decoder.layers.11.pre_mlp_layernorm.weight
|
| 672 |
+
module.decoder.layers.11.self_attention.linear_qkv.layer_norm_weight
|
| 673 |
+
module.decoder.layers.11.self_attention.linear_proj.weight
|
| 674 |
+
Params for bucket 7 (42475520 elements, 42475520 padded size):
|
| 675 |
+
module.decoder.layers.10.self_attention.linear_qkv.weight
|
| 676 |
+
module.decoder.layers.10.pre_mlp_layernorm.weight
|
| 677 |
+
module.decoder.layers.10.self_attention.linear_proj.weight
|
| 678 |
+
module.decoder.layers.10.mlp.router.weight
|
| 679 |
+
module.decoder.layers.10.self_attention.linear_qkv.layer_norm_weight
|
| 680 |
+
Params for bucket 8 (42475520 elements, 42475520 padded size):
|
| 681 |
+
module.decoder.layers.9.mlp.router.weight
|
| 682 |
+
module.decoder.layers.9.self_attention.linear_proj.weight
|
| 683 |
+
module.decoder.layers.9.self_attention.linear_qkv.weight
|
| 684 |
+
module.decoder.layers.9.self_attention.linear_qkv.layer_norm_weight
|
| 685 |
+
module.decoder.layers.9.pre_mlp_layernorm.weight
|
| 686 |
+
Params for bucket 9 (42475520 elements, 42475520 padded size):
|
| 687 |
+
module.decoder.layers.8.mlp.router.weight
|
| 688 |
+
module.decoder.layers.8.self_attention.linear_qkv.weight
|
| 689 |
+
module.decoder.layers.8.pre_mlp_layernorm.weight
|
| 690 |
+
module.decoder.layers.8.self_attention.linear_proj.weight
|
| 691 |
+
module.decoder.layers.8.self_attention.linear_qkv.layer_norm_weight
|
| 692 |
+
Params for bucket 10 (42475520 elements, 42475520 padded size):
|
| 693 |
+
module.decoder.layers.7.self_attention.linear_qkv.weight
|
| 694 |
+
module.decoder.layers.7.pre_mlp_layernorm.weight
|
| 695 |
+
module.decoder.layers.7.self_attention.linear_proj.weight
|
| 696 |
+
module.decoder.layers.7.mlp.router.weight
|
| 697 |
+
module.decoder.layers.7.self_attention.linear_qkv.layer_norm_weight
|
| 698 |
+
Params for bucket 11 (42475520 elements, 42475520 padded size):
|
| 699 |
+
module.decoder.layers.6.mlp.router.weight
|
| 700 |
+
module.decoder.layers.6.pre_mlp_layernorm.weight
|
| 701 |
+
module.decoder.layers.6.self_attention.linear_qkv.weight
|
| 702 |
+
module.decoder.layers.6.self_attention.linear_qkv.layer_norm_weight
|
| 703 |
+
module.decoder.layers.6.self_attention.linear_proj.weight
|
| 704 |
+
Params for bucket 12 (42475520 elements, 42475520 padded size):
|
| 705 |
+
module.decoder.layers.5.self_attention.linear_qkv.weight
|
| 706 |
+
module.decoder.layers.5.pre_mlp_layernorm.weight
|
| 707 |
+
module.decoder.layers.5.mlp.router.weight
|
| 708 |
+
module.decoder.layers.5.self_attention.linear_proj.weight
|
| 709 |
+
module.decoder.layers.5.self_attention.linear_qkv.layer_norm_weight
|
| 710 |
+
Params for bucket 13 (42475520 elements, 42475520 padded size):
|
| 711 |
+
module.decoder.layers.4.pre_mlp_layernorm.weight
|
| 712 |
+
module.decoder.layers.4.self_attention.linear_qkv.weight
|
| 713 |
+
module.decoder.layers.4.mlp.router.weight
|
| 714 |
+
module.decoder.layers.4.self_attention.linear_proj.weight
|
| 715 |
+
module.decoder.layers.4.self_attention.linear_qkv.layer_norm_weight
|
| 716 |
+
Params for bucket 14 (42475520 elements, 42475520 padded size):
|
| 717 |
+
module.decoder.layers.3.self_attention.linear_qkv.weight
|
| 718 |
+
module.decoder.layers.3.self_attention.linear_proj.weight
|
| 719 |
+
module.decoder.layers.3.pre_mlp_layernorm.weight
|
| 720 |
+
module.decoder.layers.3.mlp.router.weight
|
| 721 |
+
module.decoder.layers.3.self_attention.linear_qkv.layer_norm_weight
|
| 722 |
+
Params for bucket 15 (42475520 elements, 42475520 padded size):
|
| 723 |
+
module.decoder.layers.2.pre_mlp_layernorm.weight
|
| 724 |
+
module.decoder.layers.2.self_attention.linear_proj.weight
|
| 725 |
+
module.decoder.layers.2.self_attention.linear_qkv.weight
|
| 726 |
+
module.decoder.layers.2.mlp.router.weight
|
| 727 |
+
module.decoder.layers.2.self_attention.linear_qkv.layer_norm_weight
|
| 728 |
+
Params for bucket 16 (42475520 elements, 42475520 padded size):
|
| 729 |
+
module.decoder.layers.1.mlp.router.weight
|
| 730 |
+
module.decoder.layers.1.self_attention.linear_proj.weight
|
| 731 |
+
module.decoder.layers.1.self_attention.linear_qkv.layer_norm_weight
|
| 732 |
+
module.decoder.layers.1.pre_mlp_layernorm.weight
|
| 733 |
+
module.decoder.layers.1.self_attention.linear_qkv.weight
|
| 734 |
+
Params for bucket 17 (42475520 elements, 42475520 padded size):
|
| 735 |
+
module.decoder.layers.0.mlp.router.weight
|
| 736 |
+
module.decoder.layers.0.self_attention.linear_qkv.weight
|
| 737 |
+
module.decoder.layers.0.self_attention.linear_proj.weight
|
| 738 |
+
module.decoder.layers.0.pre_mlp_layernorm.weight
|
| 739 |
+
module.decoder.layers.0.self_attention.linear_qkv.layer_norm_weight
|
| 740 |
+
Params for bucket 18 (206045184 elements, 206045184 padded size):
|
| 741 |
+
module.embedding.word_embeddings.weight
|
| 742 |
+
INFO:megatron.core.distributed.param_and_grad_buffer:Number of buckets for gradient all-reduce / reduce-scatter: 67
|
| 743 |
+
Params for bucket 1 (40370176 elements, 40370176 padded size):
|
| 744 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight12
|
| 745 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight14
|
| 746 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight10
|
| 747 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight8
|
| 748 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight6
|
| 749 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight15
|
| 750 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight11
|
| 751 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight13
|
| 752 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight9
|
| 753 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight7
|
| 754 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight5
|
| 755 |
+
Params for bucket 2 (40370176 elements, 40370176 padded size):
|
| 756 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight4
|
| 757 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight2
|
| 758 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight0
|
| 759 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight15
|
| 760 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight13
|
| 761 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight3
|
| 762 |
+
module.decoder.layers.15.mlp.experts.linear_fc2.weight1
|
| 763 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight14
|
| 764 |
+
Params for bucket 3 (44040192 elements, 44040192 padded size):
|
| 765 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight9
|
| 766 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight11
|
| 767 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight7
|
| 768 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight12
|
| 769 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight8
|
| 770 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight10
|
| 771 |
+
Params for bucket 4 (44040192 elements, 44040192 padded size):
|
| 772 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight3
|
| 773 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight5
|
| 774 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight1
|
| 775 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight6
|
| 776 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight2
|
| 777 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight4
|
| 778 |
+
Params for bucket 5 (40370176 elements, 40370176 padded size):
|
| 779 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight14
|
| 780 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight12
|
| 781 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight10
|
| 782 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight8
|
| 783 |
+
module.decoder.layers.15.mlp.experts.linear_fc1.weight0
|
| 784 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight13
|
| 785 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight15
|
| 786 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight11
|
| 787 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight9
|
| 788 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight7
|
| 789 |
+
Params for bucket 6 (40370176 elements, 40370176 padded size):
|
| 790 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight6
|
| 791 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight4
|
| 792 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight1
|
| 793 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight0
|
| 794 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight14
|
| 795 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight3
|
| 796 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight2
|
| 797 |
+
module.decoder.layers.14.mlp.experts.linear_fc2.weight5
|
| 798 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight15
|
| 799 |
+
Params for bucket 7 (44040192 elements, 44040192 padded size):
|
| 800 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight10
|
| 801 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight12
|
| 802 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight8
|
| 803 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight13
|
| 804 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight9
|
| 805 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight11
|
| 806 |
+
Params for bucket 8 (44040192 elements, 44040192 padded size):
|
| 807 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight6
|
| 808 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight4
|
| 809 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight2
|
| 810 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight7
|
| 811 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight3
|
| 812 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight5
|
| 813 |
+
Params for bucket 9 (40370176 elements, 40370176 padded size):
|
| 814 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight0
|
| 815 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight15
|
| 816 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight13
|
| 817 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight11
|
| 818 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight9
|
| 819 |
+
module.decoder.layers.14.mlp.experts.linear_fc1.weight1
|
| 820 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight14
|
| 821 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight12
|
| 822 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight10
|
| 823 |
+
Params for bucket 10 (40370176 elements, 40370176 padded size):
|
| 824 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight7
|
| 825 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight5
|
| 826 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight3
|
| 827 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight1
|
| 828 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight8
|
| 829 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight4
|
| 830 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight6
|
| 831 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight2
|
| 832 |
+
module.decoder.layers.13.mlp.experts.linear_fc2.weight0
|
| 833 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight15
|
| 834 |
+
Params for bucket 11 (44040192 elements, 44040192 padded size):
|
| 835 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight14
|
| 836 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight10
|
| 837 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight12
|
| 838 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight13
|
| 839 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight11
|
| 840 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight9
|
| 841 |
+
Params for bucket 12 (44040192 elements, 44040192 padded size):
|
| 842 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight8
|
| 843 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight4
|
| 844 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight6
|
| 845 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight7
|
| 846 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight5
|
| 847 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight3
|
| 848 |
+
Params for bucket 13 (40370176 elements, 40370176 padded size):
|
| 849 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight2
|
| 850 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight0
|
| 851 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight14
|
| 852 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight12
|
| 853 |
+
module.decoder.layers.13.mlp.experts.linear_fc1.weight1
|
| 854 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight15
|
| 855 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight13
|
| 856 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight11
|
| 857 |
+
Params for bucket 14 (40370176 elements, 40370176 padded size):
|
| 858 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight10
|
| 859 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight6
|
| 860 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight8
|
| 861 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight4
|
| 862 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight2
|
| 863 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight0
|
| 864 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight7
|
| 865 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight9
|
| 866 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight5
|
| 867 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight3
|
| 868 |
+
module.decoder.layers.12.mlp.experts.linear_fc2.weight1
|
| 869 |
+
Params for bucket 15 (44040192 elements, 44040192 padded size):
|
| 870 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight15
|
| 871 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight13
|
| 872 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight11
|
| 873 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight14
|
| 874 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight12
|
| 875 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight10
|
| 876 |
+
Params for bucket 16 (44040192 elements, 44040192 padded size):
|
| 877 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight9
|
| 878 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight7
|
| 879 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight5
|
| 880 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight8
|
| 881 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight6
|
| 882 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight4
|
| 883 |
+
Params for bucket 17 (40370176 elements, 40370176 padded size):
|
| 884 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight3
|
| 885 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight1
|
| 886 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight14
|
| 887 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight0
|
| 888 |
+
module.decoder.layers.12.mlp.experts.linear_fc1.weight2
|
| 889 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight15
|
| 890 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight13
|
| 891 |
+
Params for bucket 18 (40370176 elements, 40370176 padded size):
|
| 892 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight12
|
| 893 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight8
|
| 894 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight10
|
| 895 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight6
|
| 896 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight4
|
| 897 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight2
|
| 898 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight11
|
| 899 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight9
|
| 900 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight7
|
| 901 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight5
|
| 902 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight3
|
| 903 |
+
Params for bucket 19 (44040192 elements, 44040192 padded size):
|
| 904 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight15
|
| 905 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight13
|
| 906 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight0
|
| 907 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight11
|
| 908 |
+
module.decoder.layers.11.mlp.experts.linear_fc2.weight1
|
| 909 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight14
|
| 910 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight12
|
| 911 |
+
Params for bucket 20 (44040192 elements, 44040192 padded size):
|
| 912 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight9
|
| 913 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight7
|
| 914 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight5
|
| 915 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight10
|
| 916 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight8
|
| 917 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight6
|
| 918 |
+
Params for bucket 21 (40370176 elements, 40370176 padded size):
|
| 919 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight1
|
| 920 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight3
|
| 921 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight4
|
| 922 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight2
|
| 923 |
+
module.decoder.layers.11.mlp.experts.linear_fc1.weight0
|
| 924 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight15
|
| 925 |
+
Params for bucket 22 (40370176 elements, 40370176 padded size):
|
| 926 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight14
|
| 927 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight12
|
| 928 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight10
|
| 929 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight8
|
| 930 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight6
|
| 931 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight4
|
| 932 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight13
|
| 933 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight11
|
| 934 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight9
|
| 935 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight7
|
| 936 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight5
|
| 937 |
+
Params for bucket 23 (44040192 elements, 44040192 padded size):
|
| 938 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight15
|
| 939 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight0
|
| 940 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight2
|
| 941 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight13
|
| 942 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight3
|
| 943 |
+
module.decoder.layers.10.mlp.experts.linear_fc2.weight1
|
| 944 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight14
|
| 945 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight12
|
| 946 |
+
Params for bucket 24 (44040192 elements, 44040192 padded size):
|
| 947 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight11
|
| 948 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight9
|
| 949 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight7
|
| 950 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight10
|
| 951 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight8
|
| 952 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight6
|
| 953 |
+
Params for bucket 25 (44040192 elements, 44040192 padded size):
|
| 954 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight5
|
| 955 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight3
|
| 956 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight1
|
| 957 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight2
|
| 958 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight4
|
| 959 |
+
module.decoder.layers.10.mlp.experts.linear_fc1.weight0
|
| 960 |
+
Params for bucket 26 (40370176 elements, 40370176 padded size):
|
| 961 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight15
|
| 962 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight11
|
| 963 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight13
|
| 964 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight9
|
| 965 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight7
|
| 966 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight5
|
| 967 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight12
|
| 968 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight14
|
| 969 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight10
|
| 970 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight8
|
| 971 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight6
|
| 972 |
+
Params for bucket 27 (40370176 elements, 40370176 padded size):
|
| 973 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight3
|
| 974 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight1
|
| 975 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight14
|
| 976 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight4
|
| 977 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight2
|
| 978 |
+
module.decoder.layers.9.mlp.experts.linear_fc2.weight0
|
| 979 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight15
|
| 980 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight13
|
| 981 |
+
Params for bucket 28 (44040192 elements, 44040192 padded size):
|
| 982 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight12
|
| 983 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight8
|
| 984 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight10
|
| 985 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight11
|
| 986 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight9
|
| 987 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight7
|
| 988 |
+
Params for bucket 29 (44040192 elements, 44040192 padded size):
|
| 989 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight6
|
| 990 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight2
|
| 991 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight4
|
| 992 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight5
|
| 993 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight3
|
| 994 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight1
|
| 995 |
+
Params for bucket 30 (40370176 elements, 40370176 padded size):
|
| 996 |
+
module.decoder.layers.9.mlp.experts.linear_fc1.weight0
|
| 997 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight14
|
| 998 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight12
|
| 999 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight10
|
| 1000 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight8
|
| 1001 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight15
|
| 1002 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight13
|
| 1003 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight11
|
| 1004 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight9
|
| 1005 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight7
|
| 1006 |
+
Params for bucket 31 (40370176 elements, 40370176 padded size):
|
| 1007 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight6
|
| 1008 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight4
|
| 1009 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight2
|
| 1010 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight0
|
| 1011 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight15
|
| 1012 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight5
|
| 1013 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight3
|
| 1014 |
+
module.decoder.layers.8.mlp.experts.linear_fc2.weight1
|
| 1015 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight14
|
| 1016 |
+
Params for bucket 32 (44040192 elements, 44040192 padded size):
|
| 1017 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight13
|
| 1018 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight11
|
| 1019 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight9
|
| 1020 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight12
|
| 1021 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight10
|
| 1022 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight8
|
| 1023 |
+
Params for bucket 33 (44040192 elements, 44040192 padded size):
|
| 1024 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight7
|
| 1025 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight5
|
| 1026 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight3
|
| 1027 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight6
|
| 1028 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight4
|
| 1029 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight2
|
| 1030 |
+
Params for bucket 34 (40370176 elements, 40370176 padded size):
|
| 1031 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight1
|
| 1032 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight14
|
| 1033 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight12
|
| 1034 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight10
|
| 1035 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight15
|
| 1036 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight13
|
| 1037 |
+
module.decoder.layers.8.mlp.experts.linear_fc1.weight0
|
| 1038 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight11
|
| 1039 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight9
|
| 1040 |
+
Params for bucket 35 (40370176 elements, 40370176 padded size):
|
| 1041 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight8
|
| 1042 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight6
|
| 1043 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight4
|
| 1044 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight2
|
| 1045 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight0
|
| 1046 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight15
|
| 1047 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight7
|
| 1048 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight5
|
| 1049 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight3
|
| 1050 |
+
module.decoder.layers.7.mlp.experts.linear_fc2.weight1
|
| 1051 |
+
Params for bucket 36 (44040192 elements, 44040192 padded size):
|
| 1052 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight11
|
| 1053 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight13
|
| 1054 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight9
|
| 1055 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight14
|
| 1056 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight12
|
| 1057 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight10
|
| 1058 |
+
Params for bucket 37 (44040192 elements, 44040192 padded size):
|
| 1059 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight5
|
| 1060 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight7
|
| 1061 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight3
|
| 1062 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight8
|
| 1063 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight6
|
| 1064 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight4
|
| 1065 |
+
Params for bucket 38 (40370176 elements, 40370176 padded size):
|
| 1066 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight15
|
| 1067 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight1
|
| 1068 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight13
|
| 1069 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight11
|
| 1070 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight2
|
| 1071 |
+
module.decoder.layers.7.mlp.experts.linear_fc1.weight0
|
| 1072 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight14
|
| 1073 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight12
|
| 1074 |
+
Params for bucket 39 (40370176 elements, 40370176 padded size):
|
| 1075 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight9
|
| 1076 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight7
|
| 1077 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight5
|
| 1078 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight3
|
| 1079 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight1
|
| 1080 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight10
|
| 1081 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight8
|
| 1082 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight6
|
| 1083 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight4
|
| 1084 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight2
|
| 1085 |
+
module.decoder.layers.6.mlp.experts.linear_fc2.weight0
|
| 1086 |
+
Params for bucket 40 (44040192 elements, 44040192 padded size):
|
| 1087 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight14
|
| 1088 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight12
|
| 1089 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight10
|
| 1090 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight15
|
| 1091 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight13
|
| 1092 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight11
|
| 1093 |
+
Params for bucket 41 (44040192 elements, 44040192 padded size):
|
| 1094 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight8
|
| 1095 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight6
|
| 1096 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight4
|
| 1097 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight9
|
| 1098 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight5
|
| 1099 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight7
|
| 1100 |
+
Params for bucket 42 (40370176 elements, 40370176 padded size):
|
| 1101 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight2
|
| 1102 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight0
|
| 1103 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight14
|
| 1104 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight3
|
| 1105 |
+
module.decoder.layers.6.mlp.experts.linear_fc1.weight1
|
| 1106 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight15
|
| 1107 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight13
|
| 1108 |
+
Params for bucket 43 (40370176 elements, 40370176 padded size):
|
| 1109 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight12
|
| 1110 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight8
|
| 1111 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight10
|
| 1112 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight6
|
| 1113 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight4
|
| 1114 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight2
|
| 1115 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight11
|
| 1116 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight9
|
| 1117 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight7
|
| 1118 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight5
|
| 1119 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight3
|
| 1120 |
+
Params for bucket 44 (44040192 elements, 44040192 padded size):
|
| 1121 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight15
|
| 1122 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight13
|
| 1123 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight0
|
| 1124 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight11
|
| 1125 |
+
module.decoder.layers.5.mlp.experts.linear_fc2.weight1
|
| 1126 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight14
|
| 1127 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight12
|
| 1128 |
+
Params for bucket 45 (44040192 elements, 44040192 padded size):
|
| 1129 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight9
|
| 1130 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight7
|
| 1131 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight5
|
| 1132 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight10
|
| 1133 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight6
|
| 1134 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight8
|
| 1135 |
+
Params for bucket 46 (40370176 elements, 40370176 padded size):
|
| 1136 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight3
|
| 1137 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight1
|
| 1138 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight15
|
| 1139 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight4
|
| 1140 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight2
|
| 1141 |
+
module.decoder.layers.5.mlp.experts.linear_fc1.weight0
|
| 1142 |
+
Params for bucket 47 (40370176 elements, 40370176 padded size):
|
| 1143 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight13
|
| 1144 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight11
|
| 1145 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight9
|
| 1146 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight7
|
| 1147 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight5
|
| 1148 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight14
|
| 1149 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight12
|
| 1150 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight10
|
| 1151 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight8
|
| 1152 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight6
|
| 1153 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight4
|
| 1154 |
+
Params for bucket 48 (44040192 elements, 44040192 padded size):
|
| 1155 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight3
|
| 1156 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight1
|
| 1157 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight14
|
| 1158 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight12
|
| 1159 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight0
|
| 1160 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight15
|
| 1161 |
+
module.decoder.layers.4.mlp.experts.linear_fc2.weight2
|
| 1162 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight13
|
| 1163 |
+
Params for bucket 49 (44040192 elements, 44040192 padded size):
|
| 1164 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight10
|
| 1165 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight8
|
| 1166 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight6
|
| 1167 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight11
|
| 1168 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight9
|
| 1169 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight7
|
| 1170 |
+
Params for bucket 50 (44040192 elements, 44040192 padded size):
|
| 1171 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight2
|
| 1172 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight4
|
| 1173 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight0
|
| 1174 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight5
|
| 1175 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight3
|
| 1176 |
+
module.decoder.layers.4.mlp.experts.linear_fc1.weight1
|
| 1177 |
+
Params for bucket 51 (40370176 elements, 40370176 padded size):
|
| 1178 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight14
|
| 1179 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight12
|
| 1180 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight10
|
| 1181 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight8
|
| 1182 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight6
|
| 1183 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight15
|
| 1184 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight13
|
| 1185 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight11
|
| 1186 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight9
|
| 1187 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight7
|
| 1188 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight5
|
| 1189 |
+
Params for bucket 52 (40370176 elements, 40370176 padded size):
|
| 1190 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight4
|
| 1191 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight0
|
| 1192 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight2
|
| 1193 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight14
|
| 1194 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight1
|
| 1195 |
+
module.decoder.layers.3.mlp.experts.linear_fc2.weight3
|
| 1196 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight15
|
| 1197 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight13
|
| 1198 |
+
Params for bucket 53 (44040192 elements, 44040192 padded size):
|
| 1199 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight12
|
| 1200 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight8
|
| 1201 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight10
|
| 1202 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight9
|
| 1203 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight11
|
| 1204 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight7
|
| 1205 |
+
Params for bucket 54 (44040192 elements, 44040192 padded size):
|
| 1206 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight6
|
| 1207 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight4
|
| 1208 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight2
|
| 1209 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight5
|
| 1210 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight3
|
| 1211 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight1
|
| 1212 |
+
Params for bucket 55 (40370176 elements, 40370176 padded size):
|
| 1213 |
+
module.decoder.layers.3.mlp.experts.linear_fc1.weight0
|
| 1214 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight12
|
| 1215 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight14
|
| 1216 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight10
|
| 1217 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight8
|
| 1218 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight15
|
| 1219 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight13
|
| 1220 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight11
|
| 1221 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight9
|
| 1222 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight7
|
| 1223 |
+
Params for bucket 56 (40370176 elements, 40370176 padded size):
|
| 1224 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight6
|
| 1225 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight2
|
| 1226 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight4
|
| 1227 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight0
|
| 1228 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight14
|
| 1229 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight3
|
| 1230 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight5
|
| 1231 |
+
module.decoder.layers.2.mlp.experts.linear_fc2.weight1
|
| 1232 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight15
|
| 1233 |
+
Params for bucket 57 (44040192 elements, 44040192 padded size):
|
| 1234 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight12
|
| 1235 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight10
|
| 1236 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight8
|
| 1237 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight13
|
| 1238 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight11
|
| 1239 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight9
|
| 1240 |
+
Params for bucket 58 (44040192 elements, 44040192 padded size):
|
| 1241 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight6
|
| 1242 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight4
|
| 1243 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight2
|
| 1244 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight7
|
| 1245 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight5
|
| 1246 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight3
|
| 1247 |
+
Params for bucket 59 (40370176 elements, 40370176 padded size):
|
| 1248 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight13
|
| 1249 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight15
|
| 1250 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight0
|
| 1251 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight11
|
| 1252 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight9
|
| 1253 |
+
module.decoder.layers.2.mlp.experts.linear_fc1.weight1
|
| 1254 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight14
|
| 1255 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight12
|
| 1256 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight10
|
| 1257 |
+
Params for bucket 60 (40370176 elements, 40370176 padded size):
|
| 1258 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight7
|
| 1259 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight5
|
| 1260 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight3
|
| 1261 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight1
|
| 1262 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight8
|
| 1263 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight6
|
| 1264 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight4
|
| 1265 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight2
|
| 1266 |
+
module.decoder.layers.1.mlp.experts.linear_fc2.weight0
|
| 1267 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight15
|
| 1268 |
+
Params for bucket 61 (44040192 elements, 44040192 padded size):
|
| 1269 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight14
|
| 1270 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight12
|
| 1271 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight10
|
| 1272 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight13
|
| 1273 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight11
|
| 1274 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight9
|
| 1275 |
+
Params for bucket 62 (44040192 elements, 44040192 padded size):
|
| 1276 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight8
|
| 1277 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight6
|
| 1278 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight4
|
| 1279 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight7
|
| 1280 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight5
|
| 1281 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight3
|
| 1282 |
+
Params for bucket 63 (40370176 elements, 40370176 padded size):
|
| 1283 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight2
|
| 1284 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight0
|
| 1285 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight14
|
| 1286 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight12
|
| 1287 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight15
|
| 1288 |
+
module.decoder.layers.1.mlp.experts.linear_fc1.weight1
|
| 1289 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight13
|
| 1290 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight11
|
| 1291 |
+
Params for bucket 64 (40370176 elements, 40370176 padded size):
|
| 1292 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight10
|
| 1293 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight8
|
| 1294 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight6
|
| 1295 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight4
|
| 1296 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight2
|
| 1297 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight0
|
| 1298 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight9
|
| 1299 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight7
|
| 1300 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight5
|
| 1301 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight3
|
| 1302 |
+
module.decoder.layers.0.mlp.experts.linear_fc2.weight1
|
| 1303 |
+
Params for bucket 65 (44040192 elements, 44040192 padded size):
|
| 1304 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight15
|
| 1305 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight11
|
| 1306 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight13
|
| 1307 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight10
|
| 1308 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight14
|
| 1309 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight12
|
| 1310 |
+
Params for bucket 66 (44040192 elements, 44040192 padded size):
|
| 1311 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight7
|
| 1312 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight8
|
| 1313 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight4
|
| 1314 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight9
|
| 1315 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight5
|
| 1316 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight6
|
| 1317 |
+
Params for bucket 67 (29360128 elements, 29360128 padded size):
|
| 1318 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight3
|
| 1319 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight0
|
| 1320 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight2
|
| 1321 |
+
module.decoder.layers.0.mlp.experts.linear_fc1.weight1
|
| 1322 |
+
INFO:megatron.core.optimizer:Setting up optimizer with config OptimizerConfig(optimizer='adam', lr=0.0001, min_lr=1e-05, decoupled_lr=None, decoupled_min_lr=None, weight_decay=0.1, fp8_recipe='mxfp8', fp16=False, bf16=True, reuse_grad_buf_for_mxfp8_param_ag=False, params_dtype=torch.bfloat16, use_precision_aware_optimizer=False, store_param_remainders=True, main_grads_dtype=torch.float32, main_params_dtype=torch.float32, exp_avg_dtype=torch.float32, exp_avg_sq_dtype=torch.float32, loss_scale=None, initial_loss_scale=4294967296, min_loss_scale=1.0, loss_scale_window=1000, hysteresis=2, adam_beta1=0.9, adam_beta2=0.999, adam_eps=1e-08, sgd_momentum=0.9, use_distributed_optimizer=True, overlap_param_gather_with_optimizer_step=False, optimizer_cpu_offload=False, optimizer_offload_fraction=1.0, use_torch_optimizer_for_cpu_offload=False, overlap_cpu_optimizer_d2h_h2d=False, pin_cpu_grads=True, pin_cpu_params=True, clip_grad=1.0, log_num_zeros_in_grad=False, barrier_with_L1_time=True, timers=<megatron.core.timers.Timers object at 0x78d63de35b50>, config_logger_dir='')
|
| 1323 |
+
INFO:megatron.core.optimizer_param_scheduler:> learning rate decay style: cosine
|
| 1324 |
+
[after model, optimizer, and learning rate scheduler are built] datetime: 2026-09-17 02:55:04
|
| 1325 |
+
> building train, validation, and test datasets ...
|
| 1326 |
+
> datasets target sizes (minimum size):
|
| 1327 |
+
train: 160
|
| 1328 |
+
validation: 0
|
| 1329 |
+
test: 0
|
| 1330 |
+
INFO:megatron.core.datasets.blended_megatron_dataset_config:Let split_matrix = [(0, 1.0), None, None]
|
| 1331 |
+
> building train, validation, and test datasets for GPT ...
|
| 1332 |
+
INFO:megatron.core.datasets.blended_megatron_dataset_builder:Building GPTDataset splits with sizes=(160, 0, 0) and config=GPTDatasetConfig(random_seed=1234, sequence_length=4096, blend=(['/workspace/data/wikitext/wikitext103_gpt2_text_document'], None), blend_per_split=None, split='100,0,0', split_matrix=[(0, 1.0), None, None], num_dataset_builder_threads=1, path_to_cache=None, mmap_bin_files=True, mock=False, tokenizer=<megatron.training.tokenizer.tokenizer._GPT2BPETokenizer object at 0x78d63eb9afc0>, mid_level_dataset_surplus=0.005, reset_position_ids=False, reset_attention_mask=False, eod_mask_loss=False, create_attention_mask=True, drop_last_partial_validation_sequence=True, add_extra_token_to_sequence=True, object_storage_cache_path=None)
|
| 1333 |
+
INFO:megatron.core.datasets.indexed_dataset:Load the _IndexReader from /workspace/data/wikitext/wikitext103_gpt2_text_document.idx
|
| 1334 |
+
INFO:megatron.core.datasets.indexed_dataset: Extract the sequence lengths
|
| 1335 |
+
INFO:megatron.core.datasets.indexed_dataset: Extract the sequence pointers
|
| 1336 |
+
INFO:megatron.core.datasets.indexed_dataset: Extract the document indices
|
| 1337 |
+
INFO:megatron.core.datasets.indexed_dataset:> total number of sequences: 1165029
|
| 1338 |
+
INFO:megatron.core.datasets.indexed_dataset:> total number of documents: 1801350
|
| 1339 |
+
INFO:megatron.core.datasets.gpt_dataset:Load the GPTDataset train indices
|
| 1340 |
+
INFO:megatron.core.datasets.gpt_dataset: Load the document index from 68684a515e118253a8572c4517cf2ffe-GPTDataset-train-document_index.npy
|
| 1341 |
+
INFO:megatron.core.datasets.gpt_dataset: Load the sample index from 68684a515e118253a8572c4517cf2ffe-GPTDataset-train-sample_index.npy
|
| 1342 |
+
INFO:megatron.core.datasets.gpt_dataset: Load the shuffle index from 68684a515e118253a8572c4517cf2ffe-GPTDataset-train-shuffle_index.npy
|
| 1343 |
+
INFO:megatron.core.datasets.gpt_dataset:> total number of samples: 29073
|
| 1344 |
+
> finished creating GPT datasets ...
|
| 1345 |
+
[after dataloaders are built] datetime: 2026-09-17 02:55:04
|
| 1346 |
+
done with setup ...
|
| 1347 |
+
(min, max) time across ranks (ms):
|
| 1348 |
+
model-and-optimizer-setup ......................: (828.03, 861.50)
|
| 1349 |
+
train/valid/test-data-iterators-setup ..........: (96.75, 107.45)
|
| 1350 |
+
training ...
|
| 1351 |
+
Overwriting rerun_state_machine.current_iteration from -1 to 0...
|
| 1352 |
+
[before the start of training step] datetime: 2026-09-17 02:55:04
|
| 1353 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1354 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1355 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1356 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1357 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1358 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1359 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1360 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1361 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1362 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1363 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1364 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1365 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1366 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1367 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1368 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1369 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1370 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1371 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1372 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1373 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1374 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1375 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1376 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1377 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1378 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1379 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1380 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1381 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1382 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1383 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1384 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1385 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1386 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1387 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1388 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1389 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1390 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1391 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1392 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1393 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1394 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1395 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1396 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1397 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1398 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1399 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1400 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1401 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1402 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1403 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1404 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1405 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1406 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1407 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1408 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1409 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1410 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1411 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1412 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1413 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1414 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1415 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1416 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1417 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1418 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1419 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1420 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1421 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1422 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1423 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1424 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1425 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1426 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1427 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1428 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1429 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1430 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1431 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1432 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1433 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1434 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1435 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1436 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1437 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1438 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1439 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1440 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1441 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1442 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1443 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1444 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1445 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1446 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1447 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:482: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1448 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1449 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1450 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1451 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1452 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1453 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1454 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1455 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1456 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1457 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1458 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1459 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1460 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1461 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1462 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1463 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:334: UserWarning: The num_dispatched_tokens is deprecated, it will be removed in the future.
|
| 1464 |
+
warnings.warn("The num_dispatched_tokens is deprecated, it will be removed in the future.")
|
| 1465 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1466 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1467 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1468 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1469 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1470 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1471 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1472 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1473 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1474 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1475 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1476 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1477 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1478 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1479 |
+
/workspace/DeepEP/deep_ep/hybrid_ep_buffer.py:336: UserWarning: The use_host_meta is deprecated, it will be removed in the future.
|
| 1480 |
+
warnings.warn("The use_host_meta is deprecated, it will be removed in the future.")
|
| 1481 |
+
[2026-09-17 02:55:48] iteration 1/ 10 | consumed samples: 16 | elapsed time per iteration (ms): 43511.8 | throughput per GPU (TFLOP/s/GPU): 2.9 | learning rate: 2.000000E-05 | global batch size: 16 | lm loss: 1.102484E+01 | loss scale: 1.0 | grad norm: 44.692 | number of skipped iterations: 0 | number of nan iterations: 0 |
|
| 1482 |
+
Number of parameters in transformer block in billions: 23.22
|
| 1483 |
+
Number of parameters in embedding layers in billions: 0.41
|
| 1484 |
+
Total number of parameters in billions: 23.63
|
| 1485 |
+
Number of parameters in most loaded shard in billions: 23.6320
|
| 1486 |
+
Theoretical memory footprints: weight and optimizer=169029.43 MB
|
| 1487 |
+
[Rank 0] (after 1 iterations) memory (MB) | allocated: 64034.8828125 | max allocated: 79445.076171875 | reserved: 82888.0 | max reserved: 82888.0
|
| 1488 |
+
[2026-09-17 02:55:49] iteration 2/ 10 | consumed samples: 32 | elapsed time per iteration (ms): 946.1 | throughput per GPU (TFLOP/s/GPU): 132.7 | learning rate: 4.000000E-05 | global batch size: 16 | lm loss: 1.101710E+01 | loss scale: 1.0 | grad norm: 46.419 | number of skipped iterations: 0 | number of nan iterations: 0 |
|
| 1489 |
+
[2026-09-17 02:55:49] iteration 3/ 10 | consumed samples: 48 | elapsed time per iteration (ms): 592.0 | throughput per GPU (TFLOP/s/GPU): 212.1 | learning rate: 6.000000E-05 | global batch size: 16 | lm loss: 1.055648E+01 | loss scale: 1.0 | grad norm: 213.531 | number of skipped iterations: 0 | number of nan iterations: 0 |
|
| 1490 |
+
Capture CUDA graph for training!!!
|
| 1491 |
+
CUDA graph capture done!!!
|
| 1492 |
+
[2026-09-17 02:55:53] iteration 4/ 10 | consumed samples: 64 | elapsed time per iteration (ms): 3377.2 | throughput per GPU (TFLOP/s/GPU): 37.2 | learning rate: 8.000000E-05 | global batch size: 16 | lm loss: 1.297811E+01 | loss scale: 1.0 | grad norm: 49.016 | number of skipped iterations: 0 | number of nan iterations: 0 |
|
| 1493 |
+
[2026-09-17 02:55:53] iteration 5/ 10 | consumed samples: 80 | elapsed time per iteration (ms): 341.6 | throughput per GPU (TFLOP/s/GPU): 367.7 | learning rate: 1.000000E-04 | global batch size: 16 | lm loss: 1.032672E+01 | loss scale: 1.0 | grad norm: 17.807 | number of skipped iterations: 0 | number of nan iterations: 0 |
|
| 1494 |
+
[2026-09-17 02:55:54] iteration 6/ 10 | consumed samples: 96 | elapsed time per iteration (ms): 341.5 | throughput per GPU (TFLOP/s/GPU): 367.7 | learning rate: 7.750000E-05 | global batch size: 16 | lm loss: 1.009215E+01 | loss scale: 1.0 | grad norm: 13.671 | number of skipped iterations: 0 | number of nan iterations: 0 |
|
| 1495 |
+
[2026-09-17 02:55:57] iteration 7/ 10 | consumed samples: 112 | elapsed time per iteration (ms): 3269.7 | throughput per GPU (TFLOP/s/GPU): 38.4 | learning rate: 3.250000E-05 | global batch size: 16 | lm loss: 9.764772E+00 | loss scale: 1.0 | grad norm: 6.485 | number of skipped iterations: 0 | number of nan iterations: 0 |
|
| 1496 |
+
[2026-09-17 02:55:57] iteration 8/ 10 | consumed samples: 128 | elapsed time per iteration (ms): 355.8 | throughput per GPU (TFLOP/s/GPU): 352.9 | learning rate: 1.000000E-05 | global batch size: 16 | lm loss: 9.185248E+00 | loss scale: 1.0 | grad norm: 5.739 | number of skipped iterations: 0 | number of nan iterations: 0 |
|
| 1497 |
+
Capture range started in the application.
|
| 1498 |
+
Capture range ended in the application.
|
| 1499 |
+
Generating '/tmp/nsys-report-418c.qdstrm'
|
| 1500 |
+
|
| 1501 |
+
|
| 1502 |
+
Collection stop is not allowed in this state.
|
| 1503 |
+
W0917 03:03:37.518000 880794 torch/distributed/elastic/agent/server/api.py:719] Received 15 death signal, shutting down workers
|
| 1504 |
+
W0917 03:03:37.519000 880794 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 880908 closing signal SIGTERM
|
| 1505 |
+
Generated:
|
| 1506 |
+
/workspace/granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/G4_K8__echo__matched__seq4096__gbs16__cap1p109375.nsys-rep
|
| 1507 |
+
W0917 03:03:37.524000 880794 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 880909 closing signal SIGTERM
|
| 1508 |
+
W0917 03:03:37.527000 880794 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 880910 closing signal SIGTERM
|
| 1509 |
+
W0917 03:03:37.532000 880794 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 880911 closing signal SIGTERM
|
| 1510 |
+
W0917 03:03:37.536000 880794 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 880912 closing signal SIGTERM
|
| 1511 |
+
W0917 03:03:37.538000 880794 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 880913 closing signal SIGTERM
|
| 1512 |
+
W0917 03:03:37.551000 880794 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 880914 closing signal SIGTERM
|
| 1513 |
+
W0917 03:03:37.558000 880794 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 880915 closing signal SIGTERM
|
| 1514 |
+
Traceback (most recent call last):
|
| 1515 |
+
File "/usr/local/bin/torchrun", line 8, in <module>
|
| 1516 |
+
sys.exit(main())
|
| 1517 |
+
^^^^^^
|
| 1518 |
+
File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
|
| 1519 |
+
return f(*args, **kwargs)
|
| 1520 |
+
^^^^^^^^^^^^^^^^^^
|
| 1521 |
+
File "/usr/local/lib/python3.12/dist-packages/torch/distributed/run.py", line 892, in main
|
| 1522 |
+
run(args)
|
| 1523 |
+
File "/usr/local/lib/python3.12/dist-packages/torch/distributed/run.py", line 883, in run
|
| 1524 |
+
elastic_launch(
|
| 1525 |
+
File "/usr/local/lib/python3.12/dist-packages/torch/distributed/launcher/api.py", line 139, in __call__
|
| 1526 |
+
return launch_agent(self._config, self._entrypoint, list(args))
|
| 1527 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 1528 |
+
File "/usr/local/lib/python3.12/dist-packages/torch/distributed/launcher/api.py", line 261, in launch_agent
|
| 1529 |
+
result = agent.run()
|
| 1530 |
+
^^^^^^^^^^^
|
| 1531 |
+
File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/metrics/api.py", line 138, in wrapper
|
| 1532 |
+
result = f(*args, **kwargs)
|
| 1533 |
+
^^^^^^^^^^^^^^^^^^
|
| 1534 |
+
File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/agent/server/api.py", line 711, in run
|
| 1535 |
+
result = self._invoke_run(role)
|
| 1536 |
+
^^^^^^^^^^^^^^^^^^^^^^
|
| 1537 |
+
File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/agent/server/api.py", line 870, in _invoke_run
|
| 1538 |
+
time.sleep(monitor_interval)
|
| 1539 |
+
File "/usr/local/lib/python3.12/dist-packages/torch/distributed/elastic/multiprocessing/api.py", line 84, in _terminate_process_handler
|
| 1540 |
+
raise SignalException(f"Process {os.getpid()} got signal: {sigval}", sigval=sigval)
|
| 1541 |
+
torch.distributed.elastic.multiprocessing.api.SignalException: Process 880794 got signal: 15
|
| 1542 |
+
The target application terminated. One or more process it created re-parented.
|
| 1543 |
+
Waiting for termination of re-parented processes.
|
| 1544 |
+
Use the `--wait` option to modify this behavior.
|
| 1545 |
+
There are no active sessions.
|
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/verify_trace_ranks.log
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
report : /workspace/granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/G4_K8__echo__matched__seq4096__gbs16__cap1p109375.nsys-rep
|
| 2 |
+
kernels : 281286
|
| 3 |
+
devices : 8 of 8 -> [0, 1, 2, 3, 4, 5, 6, 7]
|
| 4 |
+
processes: 1
|
| 5 |
+
markers : 23552 echo_trace__ kernels on devices [0, 1, 2, 3, 4, 5, 6, 7]
|
| 6 |
+
PASS: all ranks present and backend markers emitted
|
granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/trace_results.tsv
CHANGED
|
@@ -5,3 +5,4 @@ G3_K8 echo 1.09375 OK /workspace/granularity_next_b200/tiera_topk_trace/echo/tie
|
|
| 5 |
G4_K2 echo 1.265625 OK /workspace/granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K2__echo__matched__seq4096__gbs16__cap1p265625/nsys/G4_K2__echo__matched__seq4096__gbs16__cap1p265625.nsys-rep
|
| 6 |
G4_K4 echo 1.171875 OK /workspace/granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K4__echo__matched__seq4096__gbs16__cap1p171875/nsys/G4_K4__echo__matched__seq4096__gbs16__cap1p171875.nsys-rep
|
| 7 |
G4_K6 echo 1.1354166666666667 OK /workspace/granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667/nsys/G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667.nsys-rep
|
|
|
|
|
|
| 5 |
G4_K2 echo 1.265625 OK /workspace/granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K2__echo__matched__seq4096__gbs16__cap1p265625/nsys/G4_K2__echo__matched__seq4096__gbs16__cap1p265625.nsys-rep
|
| 6 |
G4_K4 echo 1.171875 OK /workspace/granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K4__echo__matched__seq4096__gbs16__cap1p171875/nsys/G4_K4__echo__matched__seq4096__gbs16__cap1p171875.nsys-rep
|
| 7 |
G4_K6 echo 1.1354166666666667 OK /workspace/granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667/nsys/G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667.nsys-rep
|
| 8 |
+
G4_K8 echo 1.109375 OK /workspace/granularity_next_b200/tiera_topk_trace/echo/tierbtrace/tierbtrace_gbs16/G4_K8__echo__matched__seq4096__gbs16__cap1p109375/nsys/G4_K8__echo__matched__seq4096__gbs16__cap1p109375.nsys-rep
|
granularity_next_b200/tiera_topk_trace/hf_watcher.log
CHANGED
|
@@ -19,3 +19,6 @@ https://huggingface.co/MoE-CUDA-Graph-Analysis/tierb-b200-gbs8/tree/main
|
|
| 19 |
uploaded: /workspace/granularity_next_b200/tiera_topk_trace -> MoE-CUDA-Graph-Analysis/tierb-b200-gbs8/granularity_next_b200/tiera_topk_trace
|
| 20 |
https://huggingface.co/MoE-CUDA-Graph-Analysis/tierb-b200-gbs8/tree/main
|
| 21 |
[2026-09-17T02:54:52+00:00] backup pass
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
uploaded: /workspace/granularity_next_b200/tiera_topk_trace -> MoE-CUDA-Graph-Analysis/tierb-b200-gbs8/granularity_next_b200/tiera_topk_trace
|
| 20 |
https://huggingface.co/MoE-CUDA-Graph-Analysis/tierb-b200-gbs8/tree/main
|
| 21 |
[2026-09-17T02:54:52+00:00] backup pass
|
| 22 |
+
uploaded: /workspace/granularity_next_b200/tiera_topk_trace -> MoE-CUDA-Graph-Analysis/tierb-b200-gbs8/granularity_next_b200/tiera_topk_trace
|
| 23 |
+
https://huggingface.co/MoE-CUDA-Graph-Analysis/tierb-b200-gbs8/tree/main
|
| 24 |
+
[2026-09-17T03:04:55+00:00] backup pass
|
granularity_next_b200/tiera_topk_trace/study.log
CHANGED
|
@@ -60,3 +60,10 @@ driver_repo: /workspace/blackwell_run_scripts @ 10756d4
|
|
| 60 |
[guard] tearing down process group (outcome=STALLED)
|
| 61 |
[02:54:36] trace verified -> G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667.nsys-rep (19M, all 8 GPUs + echo markers)
|
| 62 |
[02:54:36] TRACE-ONLY G4_K8__echo__matched__seq4096__gbs16__cap1p109375 (ranks: 0 1 2 3 4 5 6 7)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
[guard] tearing down process group (outcome=STALLED)
|
| 61 |
[02:54:36] trace verified -> G4_K6__echo__matched__seq4096__gbs16__cap1p1354166666666667.nsys-rep (19M, all 8 GPUs + echo markers)
|
| 62 |
[02:54:36] TRACE-ONLY G4_K8__echo__matched__seq4096__gbs16__cap1p109375 (ranks: 0 1 2 3 4 5 6 7)
|
| 63 |
+
[guard] iter 6/10 (80s)
|
| 64 |
+
[guard] iter 8/10 (90s)
|
| 65 |
+
[guard] no progress for 420s at iter 8/10; treating as done
|
| 66 |
+
[guard] nsys stop (flushing report)
|
| 67 |
+
[guard] tearing down process group (outcome=STALLED)
|
| 68 |
+
[03:03:55] trace verified -> G4_K8__echo__matched__seq4096__gbs16__cap1p109375.nsys-rep (20M, all 8 GPUs + echo markers)
|
| 69 |
+
[03:03:55] TRACE-ONLY G4_K10__echo__matched__seq4096__gbs16__cap1p1 (ranks: 0 1 2 3 4 5 6 7)
|