mirror of https://github.com/maderix/ANE.git
57 lines
5.5 KiB
Plaintext
57 lines
5.5 KiB
Plaintext
=== ANE Training: Stories110M (12 layers) ===
|
|
dim=768 hidden=2048 heads=12 seq=256 vocab=32000 layers=12
|
|
Cannot open stories110M.bin
|
|
Pretrained load failed, using random init
|
|
Params: 109.53M (transformer 84.95M + embed 24.58M)
|
|
Kernels: 72 (60 weight-bearing + 12 static sdpaBwd2)
|
|
Accum 10 steps per recompile | Adam LR=1.0e-04 b1=0.9 b2=0.999
|
|
FLOPs/step: fwd=43487M bwd_dx=43487M bwd_dW=43487M sdpa_bwd=6040M total=174248M
|
|
ANE FLOPs/step: 93013M (fwd+bwd_dx+sdpa_bwd) | CPU: dW+cls (cblas)
|
|
|
|
Token data: 20658981 tokens (41.3 MB)
|
|
Compiling layer 1/12... (12 compiles)
|
|
Compiling layer 2/12... (17 compiles)
|
|
Compiling layer 3/12... (22 compiles)
|
|
Compiling layer 4/12... (27 compiles)
|
|
Compiling layer 5/12... (32 compiles)
|
|
Compiling layer 6/12... (37 compiles)
|
|
Compiling layer 7/12... (42 compiles)
|
|
Compiling layer 8/12... (47 compiles)
|
|
Compiling layer 9/12... (52 compiles)
|
|
Compiling layer 10/12... (57 compiles)
|
|
Compiling layer 11/12... (62 compiles)
|
|
Compiling layer 12/12... (67 compiles)
|
|
Compiled 60 kernels in 3554ms
|
|
step 0 loss=10.3907
|
|
{"type":"step","step":0,"loss":10.390698,"t_ane":12.288,"t_io":14.233,"t_cls":30.426,"t_elem":21.143,"t_rms":0.094,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":1,"loss":10.434500,"t_ane":10.653,"t_io":13.757,"t_cls":20.472,"t_elem":18.814,"t_rms":0.070,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":2,"loss":10.484736,"t_ane":10.050,"t_io":10.094,"t_cls":16.495,"t_elem":17.783,"t_rms":0.061,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":3,"loss":10.417551,"t_ane":9.755,"t_io":8.214,"t_cls":14.512,"t_elem":16.853,"t_rms":0.068,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":4,"loss":10.392599,"t_ane":9.537,"t_io":7.032,"t_cls":13.297,"t_elem":16.319,"t_rms":0.063,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":5,"loss":10.392069,"t_ane":9.404,"t_io":6.251,"t_cls":12.475,"t_elem":15.887,"t_rms":0.060,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":6,"loss":10.382063,"t_ane":9.313,"t_io":5.697,"t_cls":11.874,"t_elem":15.678,"t_rms":0.058,"t_cblas_wait":0.001,"compiles":72}
|
|
{"type":"step","step":7,"loss":10.377501,"t_ane":9.238,"t_io":5.293,"t_cls":11.437,"t_elem":15.556,"t_rms":0.056,"t_cblas_wait":0.001,"compiles":72}
|
|
{"type":"step","step":8,"loss":10.409813,"t_ane":9.174,"t_io":4.967,"t_cls":11.101,"t_elem":15.372,"t_rms":0.055,"t_cblas_wait":0.001,"compiles":72}
|
|
{"type":"step","step":9,"loss":10.395181,"t_ane":9.138,"t_io":4.720,"t_cls":10.819,"t_elem":15.289,"t_rms":0.054,"t_cblas_wait":0.001,"compiles":72}
|
|
[batch 10: compile=3554ms train=1253.8ms (125.4ms/step) compiles=72]
|
|
ane=9.1 io=4.7 cls=10.8 elem=15.3 rms=0.1 cblas_wait=0.0 ms/step
|
|
{"type":"batch","batch":10,"compile_ms":3554.3,"train_ms":1253.8,"ms_per_step":125.4}
|
|
{"type":"perf","ane_tflops":0.742,"ane_util_pct":4.70}
|
|
[exec() restart step 10, 72 compiles, loss=10.3952]
|
|
[RESUMED step 10, loss=10.3952]
|
|
Token data: 20658981 tokens (41.3 MB)
|
|
Compiling layer 1/12... (12 compiles)
|
|
Compiling layer 2/12... (17 compiles)
|
|
Compiling layer 3/12... (22 compiles)
|
|
Compiling layer 4/12... (27 compiles)
|
|
Compiling layer 5/12... (32 compiles)
|
|
Compiling layer 6/12... (37 compiles)
|
|
Compiling layer 7/12... (42 compiles)
|
|
Compiling layer 8/12... (47 compiles)
|
|
Compiling layer 9/12... (52 compiles)
|
|
Compiling layer 10/12... (57 compiles)
|
|
Compiling layer 11/12... (62 compiles)
|
|
Compiling layer 12/12... (67 compiles)
|
|
Compiled 60 kernels in 3633ms
|
|
step 10 loss=10.2671
|
|
{"type":"step","step":10,"loss":10.267123,"t_ane":13.398,"t_io":14.979,"t_cls":29.723,"t_elem":22.190,"t_rms":0.109,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":11,"loss":10.389436,"t_ane":11.150,"t_io":13.816,"t_cls":19.297,"t_elem":17.862,"t_rms":0.078,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":12,"loss":10.246490,"t_ane":10.356,"t_io":10.036,"t_cls":15.691,"t_elem":16.749,"t_rms":0.067,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":13,"loss":10.322395,"t_ane":9.971,"t_io":8.113,"t_cls":13.880,"t_elem":16.200,"t_rms":0.061,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":14,"loss":10.280519,"t_ane":9.708,"t_io":7.002,"t_cls":12.817,"t_elem":15.972,"t_rms":0.061,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":15,"loss":10.202168,"t_ane":9.575,"t_io":6.212,"t_cls":12.096,"t_elem":15.716,"t_rms":0.059,"t_cblas_wait":0.003,"compiles":72}
|
|
{"type":"step","step":16,"loss":10.306752,"t_ane":9.450,"t_io":5.685,"t_cls":11.577,"t_elem":15.530,"t_rms":0.057,"t_cblas_wait":0.003,"compiles":72}
|
|
{"type":"step","step":17,"loss":10.293774,"t_ane":9.361,"t_io":5.280,"t_cls":11.209,"t_elem":15.392,"t_rms":0.055,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":18,"loss":10.263789,"t_ane":9.278,"t_io":4.976,"t_cls":10.908,"t_elem":15.263,"t_rms":0.054,"t_cblas_wait":0.002,"compiles":72}
|
|
{"type":"step","step":19,"loss":10.307909,"t_ane":9.237,"t_io":4.751,"t_cls":10.657,"t_elem":15.160,"t_rms":0.053,"t_cblas_wait":0.002,"compiles":72}
|
|
[batch 10: compile=3633ms train=1287.8ms (128.8ms/step) compiles=72]
|
|
ane=9.2 io=4.8 cls=10.7 elem=15.2 rms=0.1 cblas_wait=0.0 ms/step
|
|
{"type":"batch","batch":10,"compile_ms":3632.9,"train_ms":1287.8,"ms_per_step":128.8}
|
|
{"type":"perf","ane_tflops":0.722,"ane_util_pct":4.57}
|
|
|
|
=== Efficiency Report ===
|
|
Total steps: 20
|
|
Wall time: 10423 ms (10.4 s)
|
|
Compile time: 7187 ms (69.0%)
|
|
Train time: 2542 ms (24.4%)
|
|
Avg train: 127.1 ms/step
|
|
ANE TFLOPS: 0.73 sustained
|
|
Total TFLOPS: 1.37 (ANE+CPU)
|
|
ANE utilization: 4.6% of 15.8 TFLOPS
|