File size: 4,289 Bytes
cbacfbc | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 | === Llama Context Parallel Training Script (bluscriptCP) ===
[CP attn fusion] split (Stage-2 rope-once + Stage-3 Hopper causal-attn kernels)
[watchdog] collective no-progress deadline 600 s, poll 2 s (BLU_NCCL_WATCHDOG=0 to disable)
[watchdog] collective no-progress deadline 600 s, poll 2 s (BLU_NCCL_WATCHDOG=0 to disable)
================ Configuration (bluscriptCP) ================
d_model/layers : 1536 / 36
q/kv heads : 12 / 4 (G=3, hd=128)
ffn_hidden : 4096 (SwiGLU)
context_length : 32768
vocab_size : 50304 tying=0
B x T : 1 x 32768
world_size : 2 (dp=1 x cp=2)
CP_ATTN_MODE : ring (load_balance=HeadTail)
global_batch : 65536 (grad_accum=2)
precision : bf16 Linears + fp32 norms/residual/logits (fp32 master weights in AdamW) [mask=15 QKV WO MLP HEAD]
max_lr/min_lr : 0.0006 / 6e-05
warmup/steps : 100 / 3 (cosine, no stable phase)
checkpointing : false (ckpt_freq=50, dir=checkpoints_bluscriptcp)
=============================================================
Initializing model on CUDA device 0...
[YaRN] build_rope_cache: seq_len=32768 hd=128 scale=2.000 low=21 high=39 m=1.0693
[InitFrom] weights loaded from /root/Adhi/BluTrain/dist/Context_Parallelism/checkpoints_bluscriptcp/rank_0/lenbucket_l2_blumodelcp_run2_step_400.ckpt (base step 400, loss 2.79415) -- optimizer state and RNG intentionally NOT restored; pair with CP_REWARMUP
Parameters: 1060624896
Parameters per GPU: 1060624896
max_steps: 3
warmup_steps: 100
[ZeRO-1 v2] build=v2.4 supports: rs+ag | can-symmetric-window | can-fp32-reduce | can-bf16-reduce | can-reshard-v1-ckpt
[ZeRO-1 v2] ACTIVE: reduce_dtype=bfloat16 (= param dtype) symmetric=off overlap=-/-
[ZeRO-1 v2] zero1-v2 reduce-scatter/all-gather (standard memory)
[ZeRO-1 v2] params=983236608 padded=983236608 W=2 shard=491618304 | 38 buckets of 50 MB (13107200 elems/rank/bucket) | optimizer state/GPU: 5626.12 MB (vs 11252.2 MB unsharded)
[ZeRO-1 v2] NOTE: symmetric memory is NOT active — collectives will run NCCL's ring/tree path, not NVLS. Create the process group with MemoryMode::Symmetric (and NCCL >= 2.27) to enable it.
[ZeRO-1 v2] build=v2.4 supports: rs+ag | can-symmetric-window | can-fp32-reduce | can-bf16-reduce | can-reshard-v1-ckpt
[ZeRO-1 v2] ACTIVE: reduce_dtype=float32 (= param dtype) symmetric=off overlap=-/-
[ZeRO-1 v2] zero1-v2 reduce-scatter/all-gather (standard memory)
[ZeRO-1 v2] params=77388288 padded=77388288 W=2 shard=38694144 | 6 buckets of 50 MB (6553600 elems/rank/bucket) | optimizer state/GPU: 442.819 MB (vs 885.639 MB unsharded)
[ZeRO-1 v2] NOTE: symmetric memory is NOT active — collectives will run NCCL's ring/tree path, not NVLS. Create the process group with MemoryMode::Symmetric (and NCCL >= 2.27) to enable it.
[ZeRO-1] variant=v2 reduce-scatter/all-gather groups=2 [bfloat16/983236608] [float32/77388288]
[ZeRO-1] DataParallel is DISABLED (both would double-reduce)
[precision] bf16 params=217, all with fp32 master weights
found 6 shards for split train
found 1 shards for split val
Saving logs to: CP_BluScreipt_Training_logs/CP_Training_log1.csv (run 1)
[rope_theta] 500000 compiled default (no sidecar -- legacy run, assuming it was trained at this base)
Checkpointing: OFF
[re-warmup] anchored at step 0 for 100 steps -> peak 0.00018 (0.3 x max_lr), then cosine-decay to 6e-05 | resuming at step 0 (mid-ramp)
Starting training...
[CP ring P2P] OVERLAP: dedicated non-blocking stream
validation loss: 3.2605
[CP bwd] overlap=ON
step 0 | loss: 3.265621 | lr 1.8000e-06 | norm: 0.6861 | dt: 10194.68ms | tok/sec: 6428.5 | mem: 107275MB | Time Left: 00 hrs : 00 mins
[TIMING] data: 0.7ms | fwd: 1107.2ms | loss: 1.7ms | bwd: 1579.8ms | clip: 0.0ms | optim: 24.2ms
step 1 | loss: 3.303823 | lr 3.6000e-06 | norm: 0.6243 | dt: 2304.09ms | tok/sec: 28443.3 | mem: 108811MB | Time Left: 00 hrs : 00 mins
[TIMING] data: 1.8ms | fwd: 914.6ms | loss: 1.7ms | bwd: 1358.8ms | clip: 0.0ms | optim: 23.7ms
validation loss: 3.2597
step 2 | loss: 3.228388 | lr 5.4000e-06 | norm: 0.6796 | dt: 6985.50ms | tok/sec: 9381.7 | mem: 108619MB | Time Left: 00 hrs : 00 mins
[TIMING] data: 0.4ms | fwd: 776.6ms | loss: 1.7ms | bwd: 1558.1ms | clip: 0.0ms | optim: 23.7ms
=== Training complete ===
|