| { | |
| "variant": "ref2va", | |
| "source": "F:\\AI\\hf_originals\\MiniMax__MiniMax-H3\\HF\\transformer_ref", | |
| "groupsize": 256, | |
| "rows": 64, | |
| "search_min": 0.8, | |
| "clip_margin": 0.05, | |
| "elapsed_seconds": 66.3423388004303, | |
| "layers": [ | |
| { | |
| "layer": "blocks.0.attn.qkv_proj", | |
| "block": 0, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009149877354502678, | |
| "searched_error": 0.009098502807319164, | |
| "improvement": 5.137454718351364e-05, | |
| "clipped_row_fraction": 0.109375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.0.attn.out_proj", | |
| "block": 0, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.011861145496368408, | |
| "searched_error": 0.01176026277244091, | |
| "improvement": 0.00010088272392749786, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.0.mlp.fc1", | |
| "block": 0, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008755319751799107, | |
| "searched_error": 0.00868719257414341, | |
| "improvement": 6.812717765569687e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.0.mlp.fc2", | |
| "block": 0, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009267843328416348, | |
| "searched_error": 0.00897966418415308, | |
| "improvement": 0.0002881791442632675, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.1.attn.qkv_proj", | |
| "block": 1, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008966601453721523, | |
| "searched_error": 0.008890115655958652, | |
| "improvement": 7.648579776287079e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.1.attn.out_proj", | |
| "block": 1, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.012773617170751095, | |
| "searched_error": 0.012632046826183796, | |
| "improvement": 0.0001415703445672989, | |
| "clipped_row_fraction": 0.390625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.1.mlp.fc1", | |
| "block": 1, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00876633170992136, | |
| "searched_error": 0.008713556453585625, | |
| "improvement": 5.277525633573532e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.1.mlp.fc2", | |
| "block": 1, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009261968545615673, | |
| "searched_error": 0.008988389745354652, | |
| "improvement": 0.00027357880026102066, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.2.attn.qkv_proj", | |
| "block": 2, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008780846372246742, | |
| "searched_error": 0.00874966662377119, | |
| "improvement": 3.1179748475551605e-05, | |
| "clipped_row_fraction": 0.109375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.2.attn.out_proj", | |
| "block": 2, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.012882267124950886, | |
| "searched_error": 0.01274180319160223, | |
| "improvement": 0.0001404639333486557, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.2.mlp.fc1", | |
| "block": 2, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008909977041184902, | |
| "searched_error": 0.008883747272193432, | |
| "improvement": 2.6229768991470337e-05, | |
| "clipped_row_fraction": 0.109375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.2.mlp.fc2", | |
| "block": 2, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009286819025874138, | |
| "searched_error": 0.009042869322001934, | |
| "improvement": 0.00024394970387220383, | |
| "clipped_row_fraction": 0.765625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.3.attn.qkv_proj", | |
| "block": 3, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008728427812457085, | |
| "searched_error": 0.008676868863403797, | |
| "improvement": 5.1558949053287506e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.3.attn.out_proj", | |
| "block": 3, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.011711601167917252, | |
| "searched_error": 0.011610935442149639, | |
| "improvement": 0.00010066572576761246, | |
| "clipped_row_fraction": 0.359375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.3.mlp.fc1", | |
| "block": 3, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008689207956194878, | |
| "searched_error": 0.008630858734250069, | |
| "improvement": 5.834922194480896e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.3.mlp.fc2", | |
| "block": 3, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009451334364712238, | |
| "searched_error": 0.00917091965675354, | |
| "improvement": 0.00028041470795869827, | |
| "clipped_row_fraction": 0.796875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.4.attn.qkv_proj", | |
| "block": 4, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008999093435704708, | |
| "searched_error": 0.008943070657551289, | |
| "improvement": 5.6022778153419495e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.4.attn.out_proj", | |
| "block": 4, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010633870959281921, | |
| "searched_error": 0.01052608247846365, | |
| "improvement": 0.00010778848081827164, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.4.mlp.fc1", | |
| "block": 4, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008890100754797459, | |
| "searched_error": 0.00882396474480629, | |
| "improvement": 6.613600999116898e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.4.mlp.fc2", | |
| "block": 4, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009374679997563362, | |
| "searched_error": 0.00907217524945736, | |
| "improvement": 0.0003025047481060028, | |
| "clipped_row_fraction": 0.875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.5.attn.qkv_proj", | |
| "block": 5, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008881070651113987, | |
| "searched_error": 0.00881462637335062, | |
| "improvement": 6.64442777633667e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.5.attn.out_proj", | |
| "block": 5, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.011126119643449783, | |
| "searched_error": 0.011061684228479862, | |
| "improvement": 6.443541496992111e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.5.mlp.fc1", | |
| "block": 5, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008905366994440556, | |
| "searched_error": 0.00883188284933567, | |
| "improvement": 7.34841451048851e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.5.mlp.fc2", | |
| "block": 5, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009375902824103832, | |
| "searched_error": 0.009108574129641056, | |
| "improvement": 0.0002673286944627762, | |
| "clipped_row_fraction": 0.75, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.6.attn.qkv_proj", | |
| "block": 6, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008814658969640732, | |
| "searched_error": 0.008784820325672626, | |
| "improvement": 2.9838643968105316e-05, | |
| "clipped_row_fraction": 0.125, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.6.attn.out_proj", | |
| "block": 6, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010695223696529865, | |
| "searched_error": 0.010601626709103584, | |
| "improvement": 9.359698742628098e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.6.mlp.fc1", | |
| "block": 6, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008920718915760517, | |
| "searched_error": 0.008867485448718071, | |
| "improvement": 5.3233467042446136e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.6.mlp.fc2", | |
| "block": 6, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009407012723386288, | |
| "searched_error": 0.00913174543529749, | |
| "improvement": 0.0002752672880887985, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.7.attn.qkv_proj", | |
| "block": 7, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00881594605743885, | |
| "searched_error": 0.008770952932536602, | |
| "improvement": 4.499312490224838e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.7.attn.out_proj", | |
| "block": 7, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.011022337712347507, | |
| "searched_error": 0.010928143747150898, | |
| "improvement": 9.41939651966095e-05, | |
| "clipped_row_fraction": 0.28125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.7.mlp.fc1", | |
| "block": 7, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008879266679286957, | |
| "searched_error": 0.008849864825606346, | |
| "improvement": 2.9401853680610657e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.7.mlp.fc2", | |
| "block": 7, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009405774064362049, | |
| "searched_error": 0.009109561331570148, | |
| "improvement": 0.00029621273279190063, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.8.attn.qkv_proj", | |
| "block": 8, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009008223190903664, | |
| "searched_error": 0.0089647201821208, | |
| "improvement": 4.350300878286362e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.8.attn.out_proj", | |
| "block": 8, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.01042734831571579, | |
| "searched_error": 0.010339769534766674, | |
| "improvement": 8.757878094911575e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.8.mlp.fc1", | |
| "block": 8, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008798491209745407, | |
| "searched_error": 0.008746922016143799, | |
| "improvement": 5.1569193601608276e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.8.mlp.fc2", | |
| "block": 8, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009286905638873577, | |
| "searched_error": 0.009002236649394035, | |
| "improvement": 0.0002846689894795418, | |
| "clipped_row_fraction": 0.84375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.9.attn.qkv_proj", | |
| "block": 9, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008678901940584183, | |
| "searched_error": 0.008630734868347645, | |
| "improvement": 4.816707223653793e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.9.attn.out_proj", | |
| "block": 9, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010669376701116562, | |
| "searched_error": 0.010587197728455067, | |
| "improvement": 8.217897266149521e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.9.mlp.fc1", | |
| "block": 9, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008611093275249004, | |
| "searched_error": 0.008564319461584091, | |
| "improvement": 4.677381366491318e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.9.mlp.fc2", | |
| "block": 9, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009352547116577625, | |
| "searched_error": 0.009089149534702301, | |
| "improvement": 0.00026339758187532425, | |
| "clipped_row_fraction": 0.765625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.10.attn.qkv_proj", | |
| "block": 10, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00882525835186243, | |
| "searched_error": 0.008772222325205803, | |
| "improvement": 5.3036026656627655e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.10.attn.out_proj", | |
| "block": 10, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.01042264699935913, | |
| "searched_error": 0.010306568816304207, | |
| "improvement": 0.00011607818305492401, | |
| "clipped_row_fraction": 0.375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.10.mlp.fc1", | |
| "block": 10, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008798566646873951, | |
| "searched_error": 0.008739395067095757, | |
| "improvement": 5.917157977819443e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.10.mlp.fc2", | |
| "block": 10, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009307919070124626, | |
| "searched_error": 0.00904966052621603, | |
| "improvement": 0.00025825854390859604, | |
| "clipped_row_fraction": 0.765625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.11.attn.qkv_proj", | |
| "block": 11, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.0088732298463583, | |
| "searched_error": 0.008829551748931408, | |
| "improvement": 4.367809742689133e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.11.attn.out_proj", | |
| "block": 11, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010403656400740147, | |
| "searched_error": 0.01028230506926775, | |
| "improvement": 0.00012135133147239685, | |
| "clipped_row_fraction": 0.359375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.11.mlp.fc1", | |
| "block": 11, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008903699927031994, | |
| "searched_error": 0.008855773136019707, | |
| "improvement": 4.792679101228714e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.11.mlp.fc2", | |
| "block": 11, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009393034502863884, | |
| "searched_error": 0.009126064367592335, | |
| "improvement": 0.0002669701352715492, | |
| "clipped_row_fraction": 0.734375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.12.attn.qkv_proj", | |
| "block": 12, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008730018511414528, | |
| "searched_error": 0.008657277561724186, | |
| "improvement": 7.274094969034195e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.12.attn.out_proj", | |
| "block": 12, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010259442962706089, | |
| "searched_error": 0.010190111584961414, | |
| "improvement": 6.933137774467468e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.12.mlp.fc1", | |
| "block": 12, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008771385997533798, | |
| "searched_error": 0.00874131079763174, | |
| "improvement": 3.0075199902057648e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.12.mlp.fc2", | |
| "block": 12, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009368893690407276, | |
| "searched_error": 0.009100206196308136, | |
| "improvement": 0.00026868749409914017, | |
| "clipped_row_fraction": 0.75, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.13.attn.qkv_proj", | |
| "block": 13, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008816634304821491, | |
| "searched_error": 0.008743951097130775, | |
| "improvement": 7.268320769071579e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.13.attn.out_proj", | |
| "block": 13, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010227742604911327, | |
| "searched_error": 0.010140802711248398, | |
| "improvement": 8.693989366292953e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.13.mlp.fc1", | |
| "block": 13, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00874239206314087, | |
| "searched_error": 0.008691736496984959, | |
| "improvement": 5.065556615591049e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.13.mlp.fc2", | |
| "block": 13, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009334002621471882, | |
| "searched_error": 0.009064814075827599, | |
| "improvement": 0.0002691885456442833, | |
| "clipped_row_fraction": 0.796875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.14.attn.qkv_proj", | |
| "block": 14, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008730604313313961, | |
| "searched_error": 0.008698868565261364, | |
| "improvement": 3.1735748052597046e-05, | |
| "clipped_row_fraction": 0.109375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.14.attn.out_proj", | |
| "block": 14, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010583301074802876, | |
| "searched_error": 0.010479689575731754, | |
| "improvement": 0.00010361149907112122, | |
| "clipped_row_fraction": 0.359375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.14.mlp.fc1", | |
| "block": 14, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00874729547649622, | |
| "searched_error": 0.008711329661309719, | |
| "improvement": 3.596581518650055e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.14.mlp.fc2", | |
| "block": 14, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009479190222918987, | |
| "searched_error": 0.009177664294838905, | |
| "improvement": 0.00030152592808008194, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.15.attn.qkv_proj", | |
| "block": 15, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008874666877090931, | |
| "searched_error": 0.008819757029414177, | |
| "improvement": 5.4909847676754e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.15.attn.out_proj", | |
| "block": 15, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.011003787629306316, | |
| "searched_error": 0.010917904786765575, | |
| "improvement": 8.588284254074097e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.15.mlp.fc1", | |
| "block": 15, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008837355300784111, | |
| "searched_error": 0.00877710897475481, | |
| "improvement": 6.024632602930069e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.15.mlp.fc2", | |
| "block": 15, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009284839034080505, | |
| "searched_error": 0.008988245390355587, | |
| "improvement": 0.00029659364372491837, | |
| "clipped_row_fraction": 0.84375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.16.attn.qkv_proj", | |
| "block": 16, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008748017251491547, | |
| "searched_error": 0.008695828728377819, | |
| "improvement": 5.218852311372757e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.16.attn.out_proj", | |
| "block": 16, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00988137535750866, | |
| "searched_error": 0.009816288948059082, | |
| "improvement": 6.508640944957733e-05, | |
| "clipped_row_fraction": 0.28125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.16.mlp.fc1", | |
| "block": 16, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008817206136882305, | |
| "searched_error": 0.008756496012210846, | |
| "improvement": 6.07101246714592e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.16.mlp.fc2", | |
| "block": 16, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009356603026390076, | |
| "searched_error": 0.009065966121852398, | |
| "improvement": 0.00029063690453767776, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.17.attn.qkv_proj", | |
| "block": 17, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008703425526618958, | |
| "searched_error": 0.008664635941386223, | |
| "improvement": 3.878958523273468e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.17.attn.out_proj", | |
| "block": 17, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010421531274914742, | |
| "searched_error": 0.01031559333205223, | |
| "improvement": 0.00010593794286251068, | |
| "clipped_row_fraction": 0.390625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.17.mlp.fc1", | |
| "block": 17, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00872599147260189, | |
| "searched_error": 0.00865576695650816, | |
| "improvement": 7.022451609373093e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.17.mlp.fc2", | |
| "block": 17, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009331951849162579, | |
| "searched_error": 0.009054707363247871, | |
| "improvement": 0.0002772444859147072, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.18.attn.qkv_proj", | |
| "block": 18, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008934194222092628, | |
| "searched_error": 0.008866879157721996, | |
| "improvement": 6.731506437063217e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.18.attn.out_proj", | |
| "block": 18, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009590333327651024, | |
| "searched_error": 0.009500373154878616, | |
| "improvement": 8.996017277240753e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.18.mlp.fc1", | |
| "block": 18, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.0087647195905447, | |
| "searched_error": 0.00870244950056076, | |
| "improvement": 6.227008998394012e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.18.mlp.fc2", | |
| "block": 18, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009473690763115883, | |
| "searched_error": 0.009212583303451538, | |
| "improvement": 0.0002611074596643448, | |
| "clipped_row_fraction": 0.75, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.19.attn.qkv_proj", | |
| "block": 19, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00883630383759737, | |
| "searched_error": 0.008758751675486565, | |
| "improvement": 7.755216211080551e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.19.attn.out_proj", | |
| "block": 19, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010613351128995419, | |
| "searched_error": 0.010535142384469509, | |
| "improvement": 7.820874452590942e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.19.mlp.fc1", | |
| "block": 19, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008808483369648457, | |
| "searched_error": 0.00879175029695034, | |
| "improvement": 1.6733072698116302e-05, | |
| "clipped_row_fraction": 0.09375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.19.mlp.fc2", | |
| "block": 19, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009467557072639465, | |
| "searched_error": 0.009168003685772419, | |
| "improvement": 0.00029955338686704636, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.20.attn.qkv_proj", | |
| "block": 20, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008711456321179867, | |
| "searched_error": 0.00862672459334135, | |
| "improvement": 8.473172783851624e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.20.attn.out_proj", | |
| "block": 20, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010097628459334373, | |
| "searched_error": 0.010016809217631817, | |
| "improvement": 8.081924170255661e-05, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.20.mlp.fc1", | |
| "block": 20, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008967501111328602, | |
| "searched_error": 0.008894388563930988, | |
| "improvement": 7.311254739761353e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.20.mlp.fc2", | |
| "block": 20, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009428652003407478, | |
| "searched_error": 0.00914465170353651, | |
| "improvement": 0.00028400029987096786, | |
| "clipped_row_fraction": 0.796875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.21.attn.qkv_proj", | |
| "block": 21, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.0088729839771986, | |
| "searched_error": 0.00883404165506363, | |
| "improvement": 3.894232213497162e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.21.attn.out_proj", | |
| "block": 21, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009565706364810467, | |
| "searched_error": 0.009480264037847519, | |
| "improvement": 8.544232696294785e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.21.mlp.fc1", | |
| "block": 21, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00895257480442524, | |
| "searched_error": 0.00890747457742691, | |
| "improvement": 4.510022699832916e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.21.mlp.fc2", | |
| "block": 21, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009270595386624336, | |
| "searched_error": 0.008980251848697662, | |
| "improvement": 0.0002903435379266739, | |
| "clipped_row_fraction": 0.84375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.22.attn.qkv_proj", | |
| "block": 22, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00894355308264494, | |
| "searched_error": 0.00891187135130167, | |
| "improvement": 3.168173134326935e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.22.attn.out_proj", | |
| "block": 22, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00975025724619627, | |
| "searched_error": 0.009666379541158676, | |
| "improvement": 8.387770503759384e-05, | |
| "clipped_row_fraction": 0.28125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.22.mlp.fc1", | |
| "block": 22, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00883104931563139, | |
| "searched_error": 0.008784261532127857, | |
| "improvement": 4.678778350353241e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.22.mlp.fc2", | |
| "block": 22, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009395661763846874, | |
| "searched_error": 0.009091234765946865, | |
| "improvement": 0.00030442699790000916, | |
| "clipped_row_fraction": 0.875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.23.attn.qkv_proj", | |
| "block": 23, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00885548535734415, | |
| "searched_error": 0.008821829222142696, | |
| "improvement": 3.365613520145416e-05, | |
| "clipped_row_fraction": 0.125, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.23.attn.out_proj", | |
| "block": 23, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009813772514462471, | |
| "searched_error": 0.009709117002785206, | |
| "improvement": 0.00010465551167726517, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.23.mlp.fc1", | |
| "block": 23, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008615493774414062, | |
| "searched_error": 0.008556989952921867, | |
| "improvement": 5.850382149219513e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.23.mlp.fc2", | |
| "block": 23, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00936894677579403, | |
| "searched_error": 0.009070239961147308, | |
| "improvement": 0.0002987068146467209, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.24.attn.qkv_proj", | |
| "block": 24, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008828956633806229, | |
| "searched_error": 0.008763122372329235, | |
| "improvement": 6.583426147699356e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.24.attn.out_proj", | |
| "block": 24, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00980150606483221, | |
| "searched_error": 0.009715952910482883, | |
| "improvement": 8.555315434932709e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.24.mlp.fc1", | |
| "block": 24, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008843949995934963, | |
| "searched_error": 0.008792220614850521, | |
| "improvement": 5.172938108444214e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.24.mlp.fc2", | |
| "block": 24, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009455005638301373, | |
| "searched_error": 0.009169526398181915, | |
| "improvement": 0.00028547924011945724, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.25.attn.qkv_proj", | |
| "block": 25, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00900735892355442, | |
| "searched_error": 0.008946533314883709, | |
| "improvement": 6.082560867071152e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.25.attn.out_proj", | |
| "block": 25, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009812835603952408, | |
| "searched_error": 0.00972868874669075, | |
| "improvement": 8.414685726165771e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.25.mlp.fc1", | |
| "block": 25, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008857025764882565, | |
| "searched_error": 0.008804724551737309, | |
| "improvement": 5.230121314525604e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.25.mlp.fc2", | |
| "block": 25, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009359694086015224, | |
| "searched_error": 0.009061169810593128, | |
| "improvement": 0.00029852427542209625, | |
| "clipped_row_fraction": 0.875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.26.attn.qkv_proj", | |
| "block": 26, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008898529224097729, | |
| "searched_error": 0.008845372125506401, | |
| "improvement": 5.315709859132767e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.26.attn.out_proj", | |
| "block": 26, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010012996383011341, | |
| "searched_error": 0.009899193421006203, | |
| "improvement": 0.0001138029620051384, | |
| "clipped_row_fraction": 0.359375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.26.mlp.fc1", | |
| "block": 26, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008813909254968166, | |
| "searched_error": 0.008754000067710876, | |
| "improvement": 5.9909187257289886e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.26.mlp.fc2", | |
| "block": 26, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009220638312399387, | |
| "searched_error": 0.008964918553829193, | |
| "improvement": 0.00025571975857019424, | |
| "clipped_row_fraction": 0.765625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.27.attn.qkv_proj", | |
| "block": 27, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008921593427658081, | |
| "searched_error": 0.008879701606929302, | |
| "improvement": 4.189182072877884e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.27.attn.out_proj", | |
| "block": 27, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010251954197883606, | |
| "searched_error": 0.01017802581191063, | |
| "improvement": 7.392838597297668e-05, | |
| "clipped_row_fraction": 0.28125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.27.mlp.fc1", | |
| "block": 27, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008891111239790916, | |
| "searched_error": 0.008837737143039703, | |
| "improvement": 5.3374096751213074e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.27.mlp.fc2", | |
| "block": 27, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009307934902608395, | |
| "searched_error": 0.009034196846187115, | |
| "improvement": 0.0002737380564212799, | |
| "clipped_row_fraction": 0.78125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.28.attn.qkv_proj", | |
| "block": 28, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008664083667099476, | |
| "searched_error": 0.008631406351923943, | |
| "improvement": 3.2677315175533295e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.28.attn.out_proj", | |
| "block": 28, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010012027807533741, | |
| "searched_error": 0.009910239838063717, | |
| "improvement": 0.00010178796947002411, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.28.mlp.fc1", | |
| "block": 28, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00868856068700552, | |
| "searched_error": 0.008628825657069683, | |
| "improvement": 5.973502993583679e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.28.mlp.fc2", | |
| "block": 28, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009298889897763729, | |
| "searched_error": 0.00900914054363966, | |
| "improvement": 0.0002897493541240692, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.29.attn.qkv_proj", | |
| "block": 29, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008712724782526493, | |
| "searched_error": 0.008658976294100285, | |
| "improvement": 5.3748488426208496e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.29.attn.out_proj", | |
| "block": 29, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009863519109785557, | |
| "searched_error": 0.009750662371516228, | |
| "improvement": 0.00011285673826932907, | |
| "clipped_row_fraction": 0.375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.29.mlp.fc1", | |
| "block": 29, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008687011897563934, | |
| "searched_error": 0.00863416213542223, | |
| "improvement": 5.284976214170456e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.29.mlp.fc2", | |
| "block": 29, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00952060241252184, | |
| "searched_error": 0.009227273054420948, | |
| "improvement": 0.0002933293581008911, | |
| "clipped_row_fraction": 0.84375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.30.attn.qkv_proj", | |
| "block": 30, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008769126608967781, | |
| "searched_error": 0.008718494325876236, | |
| "improvement": 5.0632283091545105e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.30.attn.out_proj", | |
| "block": 30, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00980446208268404, | |
| "searched_error": 0.009715707041323185, | |
| "improvement": 8.87550413608551e-05, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.30.mlp.fc1", | |
| "block": 30, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008770755492150784, | |
| "searched_error": 0.008700021542608738, | |
| "improvement": 7.07339495420456e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.30.mlp.fc2", | |
| "block": 30, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00926683098077774, | |
| "searched_error": 0.008997678756713867, | |
| "improvement": 0.0002691522240638733, | |
| "clipped_row_fraction": 0.765625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.31.attn.qkv_proj", | |
| "block": 31, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008715620264410973, | |
| "searched_error": 0.008677283301949501, | |
| "improvement": 3.833696246147156e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.31.attn.out_proj", | |
| "block": 31, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010006719268858433, | |
| "searched_error": 0.009893168695271015, | |
| "improvement": 0.0001135505735874176, | |
| "clipped_row_fraction": 0.375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.31.mlp.fc1", | |
| "block": 31, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008751807734370232, | |
| "searched_error": 0.008717701770365238, | |
| "improvement": 3.410596400499344e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.31.mlp.fc2", | |
| "block": 31, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009457345120608807, | |
| "searched_error": 0.009170906618237495, | |
| "improvement": 0.0002864385023713112, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.32.attn.qkv_proj", | |
| "block": 32, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008660205639898777, | |
| "searched_error": 0.008621814660727978, | |
| "improvement": 3.8390979170799255e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.32.attn.out_proj", | |
| "block": 32, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009854556061327457, | |
| "searched_error": 0.009778095409274101, | |
| "improvement": 7.646065205335617e-05, | |
| "clipped_row_fraction": 0.28125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.32.mlp.fc1", | |
| "block": 32, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008708640933036804, | |
| "searched_error": 0.00866017211228609, | |
| "improvement": 4.846882075071335e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.32.mlp.fc2", | |
| "block": 32, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009446533396840096, | |
| "searched_error": 0.009172597900032997, | |
| "improvement": 0.0002739354968070984, | |
| "clipped_row_fraction": 0.78125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.33.attn.qkv_proj", | |
| "block": 33, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008753178641200066, | |
| "searched_error": 0.00870854314416647, | |
| "improvement": 4.463549703359604e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.33.attn.out_proj", | |
| "block": 33, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009544803760945797, | |
| "searched_error": 0.009460123255848885, | |
| "improvement": 8.468050509691238e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.33.mlp.fc1", | |
| "block": 33, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00878031924366951, | |
| "searched_error": 0.008725587278604507, | |
| "improvement": 5.473196506500244e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.33.mlp.fc2", | |
| "block": 33, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009336614981293678, | |
| "searched_error": 0.009038848802447319, | |
| "improvement": 0.00029776617884635925, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.34.attn.qkv_proj", | |
| "block": 34, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00897362269461155, | |
| "searched_error": 0.008926293812692165, | |
| "improvement": 4.7328881919384e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.34.attn.out_proj", | |
| "block": 34, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009532013908028603, | |
| "searched_error": 0.009444000199437141, | |
| "improvement": 8.801370859146118e-05, | |
| "clipped_row_fraction": 0.34375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.34.mlp.fc1", | |
| "block": 34, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008846458047628403, | |
| "searched_error": 0.00876232236623764, | |
| "improvement": 8.413568139076233e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.34.mlp.fc2", | |
| "block": 34, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009401639923453331, | |
| "searched_error": 0.009106581099331379, | |
| "improvement": 0.00029505882412195206, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.35.attn.qkv_proj", | |
| "block": 35, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00885989610105753, | |
| "searched_error": 0.008797014132142067, | |
| "improvement": 6.28819689154625e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.35.attn.out_proj", | |
| "block": 35, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009578592143952847, | |
| "searched_error": 0.00948287919163704, | |
| "improvement": 9.571295231580734e-05, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.35.mlp.fc1", | |
| "block": 35, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008819864131510258, | |
| "searched_error": 0.008781999349594116, | |
| "improvement": 3.786478191614151e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.35.mlp.fc2", | |
| "block": 35, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009462808258831501, | |
| "searched_error": 0.009170095436275005, | |
| "improvement": 0.00029271282255649567, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.36.attn.qkv_proj", | |
| "block": 36, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008869685232639313, | |
| "searched_error": 0.008822268806397915, | |
| "improvement": 4.741642624139786e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.36.attn.out_proj", | |
| "block": 36, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010005505755543709, | |
| "searched_error": 0.009918516501784325, | |
| "improvement": 8.698925375938416e-05, | |
| "clipped_row_fraction": 0.28125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.36.mlp.fc1", | |
| "block": 36, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008894680067896843, | |
| "searched_error": 0.008845840580761433, | |
| "improvement": 4.883948713541031e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.36.mlp.fc2", | |
| "block": 36, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00928464811295271, | |
| "searched_error": 0.009009410627186298, | |
| "improvement": 0.00027523748576641083, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.37.attn.qkv_proj", | |
| "block": 37, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008858516812324524, | |
| "searched_error": 0.008785505779087543, | |
| "improvement": 7.301103323698044e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.37.attn.out_proj", | |
| "block": 37, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010057258419692516, | |
| "searched_error": 0.009970421902835369, | |
| "improvement": 8.683651685714722e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.37.mlp.fc1", | |
| "block": 37, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008871573954820633, | |
| "searched_error": 0.008826128207147121, | |
| "improvement": 4.5445747673511505e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.37.mlp.fc2", | |
| "block": 37, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009507856331765652, | |
| "searched_error": 0.009210675954818726, | |
| "improvement": 0.0002971803769469261, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.38.attn.qkv_proj", | |
| "block": 38, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008879483677446842, | |
| "searched_error": 0.008825055323541164, | |
| "improvement": 5.4428353905677795e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.38.attn.out_proj", | |
| "block": 38, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010883932933211327, | |
| "searched_error": 0.0107962591573596, | |
| "improvement": 8.767377585172653e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.38.mlp.fc1", | |
| "block": 38, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00895624328404665, | |
| "searched_error": 0.00889838207513094, | |
| "improvement": 5.786120891571045e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.38.mlp.fc2", | |
| "block": 38, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009250178001821041, | |
| "searched_error": 0.008992554619908333, | |
| "improvement": 0.0002576233819127083, | |
| "clipped_row_fraction": 0.78125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.39.attn.qkv_proj", | |
| "block": 39, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008887657895684242, | |
| "searched_error": 0.008838411420583725, | |
| "improvement": 4.924647510051727e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.39.attn.out_proj", | |
| "block": 39, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009882594458758831, | |
| "searched_error": 0.009741849265992641, | |
| "improvement": 0.00014074519276618958, | |
| "clipped_row_fraction": 0.46875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.39.mlp.fc1", | |
| "block": 39, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008798052556812763, | |
| "searched_error": 0.008744299411773682, | |
| "improvement": 5.3753145039081573e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.39.mlp.fc2", | |
| "block": 39, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009530093520879745, | |
| "searched_error": 0.009255670011043549, | |
| "improvement": 0.0002744235098361969, | |
| "clipped_row_fraction": 0.765625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.40.attn.qkv_proj", | |
| "block": 40, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008775589056313038, | |
| "searched_error": 0.008701545186340809, | |
| "improvement": 7.4043869972229e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.40.attn.out_proj", | |
| "block": 40, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009700240567326546, | |
| "searched_error": 0.009606442414224148, | |
| "improvement": 9.379815310239792e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.40.mlp.fc1", | |
| "block": 40, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008850575424730778, | |
| "searched_error": 0.008782174438238144, | |
| "improvement": 6.840098649263382e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.40.mlp.fc2", | |
| "block": 40, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00927836075425148, | |
| "searched_error": 0.009013586677610874, | |
| "improvement": 0.0002647740766406059, | |
| "clipped_row_fraction": 0.78125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.41.attn.qkv_proj", | |
| "block": 41, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008886943571269512, | |
| "searched_error": 0.008859841153025627, | |
| "improvement": 2.710241824388504e-05, | |
| "clipped_row_fraction": 0.125, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.41.attn.out_proj", | |
| "block": 41, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009859757497906685, | |
| "searched_error": 0.009754279628396034, | |
| "improvement": 0.00010547786951065063, | |
| "clipped_row_fraction": 0.359375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.41.mlp.fc1", | |
| "block": 41, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008647102862596512, | |
| "searched_error": 0.008588128723204136, | |
| "improvement": 5.8974139392375946e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.41.mlp.fc2", | |
| "block": 41, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009476621635258198, | |
| "searched_error": 0.009172627702355385, | |
| "improvement": 0.00030399393290281296, | |
| "clipped_row_fraction": 0.890625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.42.attn.qkv_proj", | |
| "block": 42, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008771860040724277, | |
| "searched_error": 0.00870048813521862, | |
| "improvement": 7.13719055056572e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.42.attn.out_proj", | |
| "block": 42, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009836846962571144, | |
| "searched_error": 0.009762815199792385, | |
| "improvement": 7.4031762778759e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.42.mlp.fc1", | |
| "block": 42, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008824005722999573, | |
| "searched_error": 0.008773360401391983, | |
| "improvement": 5.064532160758972e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.42.mlp.fc2", | |
| "block": 42, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009384780190885067, | |
| "searched_error": 0.009103096090257168, | |
| "improvement": 0.00028168410062789917, | |
| "clipped_row_fraction": 0.78125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.43.attn.qkv_proj", | |
| "block": 43, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008804121054708958, | |
| "searched_error": 0.008760816417634487, | |
| "improvement": 4.330463707447052e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.43.attn.out_proj", | |
| "block": 43, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010491183958947659, | |
| "searched_error": 0.010409677401185036, | |
| "improvement": 8.150655776262283e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.43.mlp.fc1", | |
| "block": 43, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008889754302799702, | |
| "searched_error": 0.00882685650140047, | |
| "improvement": 6.289780139923096e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.43.mlp.fc2", | |
| "block": 43, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00917684007436037, | |
| "searched_error": 0.008919608779251575, | |
| "improvement": 0.00025723129510879517, | |
| "clipped_row_fraction": 0.78125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.44.attn.qkv_proj", | |
| "block": 44, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008927070535719395, | |
| "searched_error": 0.008864369243383408, | |
| "improvement": 6.270129233598709e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.44.attn.out_proj", | |
| "block": 44, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.01023987215012312, | |
| "searched_error": 0.010153288953006268, | |
| "improvement": 8.65831971168518e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.44.mlp.fc1", | |
| "block": 44, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008789545856416225, | |
| "searched_error": 0.008748597465455532, | |
| "improvement": 4.094839096069336e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.44.mlp.fc2", | |
| "block": 44, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009537559002637863, | |
| "searched_error": 0.009217891842126846, | |
| "improvement": 0.00031966716051101685, | |
| "clipped_row_fraction": 0.90625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.45.attn.qkv_proj", | |
| "block": 45, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008663962595164776, | |
| "searched_error": 0.008605223149061203, | |
| "improvement": 5.8739446103572845e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.45.attn.out_proj", | |
| "block": 45, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010613594204187393, | |
| "searched_error": 0.010560794733464718, | |
| "improvement": 5.2799470722675323e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.45.mlp.fc1", | |
| "block": 45, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008878356777131557, | |
| "searched_error": 0.008829115889966488, | |
| "improvement": 4.924088716506958e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.45.mlp.fc2", | |
| "block": 45, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009541809558868408, | |
| "searched_error": 0.009230870753526688, | |
| "improvement": 0.0003109388053417206, | |
| "clipped_row_fraction": 0.890625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.46.attn.qkv_proj", | |
| "block": 46, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008875416591763496, | |
| "searched_error": 0.008823243901133537, | |
| "improvement": 5.2172690629959106e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.46.attn.out_proj", | |
| "block": 46, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010151972994208336, | |
| "searched_error": 0.010055840946733952, | |
| "improvement": 9.613204747438431e-05, | |
| "clipped_row_fraction": 0.34375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.46.mlp.fc1", | |
| "block": 46, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008902542293071747, | |
| "searched_error": 0.008869115263223648, | |
| "improvement": 3.3427029848098755e-05, | |
| "clipped_row_fraction": 0.125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.46.mlp.fc2", | |
| "block": 46, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00948946550488472, | |
| "searched_error": 0.009184555150568485, | |
| "improvement": 0.0003049103543162346, | |
| "clipped_row_fraction": 0.875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.47.attn.qkv_proj", | |
| "block": 47, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008789182640612125, | |
| "searched_error": 0.008733595721423626, | |
| "improvement": 5.558691918849945e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.47.attn.out_proj", | |
| "block": 47, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010352781042456627, | |
| "searched_error": 0.01026771031320095, | |
| "improvement": 8.507072925567627e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.47.mlp.fc1", | |
| "block": 47, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008751441724598408, | |
| "searched_error": 0.008704815059900284, | |
| "improvement": 4.662666469812393e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.47.mlp.fc2", | |
| "block": 47, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00933810044080019, | |
| "searched_error": 0.009066533297300339, | |
| "improvement": 0.0002715671434998512, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.48.attn.qkv_proj", | |
| "block": 48, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00888779480010271, | |
| "searched_error": 0.00883910246193409, | |
| "improvement": 4.869233816862106e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.48.attn.out_proj", | |
| "block": 48, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009902337566018105, | |
| "searched_error": 0.009842359460890293, | |
| "improvement": 5.997810512781143e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.48.mlp.fc1", | |
| "block": 48, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008990074507892132, | |
| "searched_error": 0.008957264944911003, | |
| "improvement": 3.280956298112869e-05, | |
| "clipped_row_fraction": 0.125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.48.mlp.fc2", | |
| "block": 48, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00943906232714653, | |
| "searched_error": 0.00914239976555109, | |
| "improvement": 0.0002966625615954399, | |
| "clipped_row_fraction": 0.84375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.49.attn.qkv_proj", | |
| "block": 49, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008817118592560291, | |
| "searched_error": 0.00875457189977169, | |
| "improvement": 6.254669278860092e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.49.attn.out_proj", | |
| "block": 49, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010820906609296799, | |
| "searched_error": 0.010764333419501781, | |
| "improvement": 5.657318979501724e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.49.mlp.fc1", | |
| "block": 49, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008758306503295898, | |
| "searched_error": 0.008717977441847324, | |
| "improvement": 4.0329061448574066e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.49.mlp.fc2", | |
| "block": 49, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009797228500247002, | |
| "searched_error": 0.009535545483231544, | |
| "improvement": 0.00026168301701545715, | |
| "clipped_row_fraction": 0.71875, | |
| "bf16_delta_bytes": 77048760 | |
| } | |
| ] | |
| } |