AGILLM-4 / local_sweep_after_mfold_sublinear.json
OpenTransformer's picture
Harvest exact M-fold attention from n1
421314d verified
Raw
History Blame Contribute Delete
489 Bytes
[
{
"alloc_gb": 0.027,
"amp": false,
"attn_backend": "sublinear",
"batch_size": 1,
"block": 64,
"elapsed_s": 0.635,
"error": null,
"grad_checkpoint": true,
"loss": 18.7676,
"ok": true,
"peak_alloc_gb": 0.031,
"peak_reserved_gb": 0.057,
"reserved_gb": 0.057,
"sublinear_chunk": 16,
"sublinear_max_anchors": 16,
"sublinear_stride": 8,
"sublinear_window": 16,
"tokens_per_s_synthetic": 100.8
}
]