| { | |
| "variant": "fl2va", | |
| "source": "MiniMaxAI/MiniMax-H3:transformer/", | |
| "groupsize": 256, | |
| "rows": 64, | |
| "search_min": 0.8, | |
| "clip_margin": 0.05, | |
| "elapsed_seconds": 59.14021396636963, | |
| "layers": [ | |
| { | |
| "layer": "blocks.0.attn.qkv_proj", | |
| "block": 0, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009152177721261978, | |
| "searched_error": 0.009113732725381851, | |
| "improvement": 3.844499588012695e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.0.attn.out_proj", | |
| "block": 0, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.011882137507200241, | |
| "searched_error": 0.011777178384363651, | |
| "improvement": 0.00010495912283658981, | |
| "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": 0.00878384243696928, | |
| "searched_error": 0.00870873685926199, | |
| "improvement": 7.510557770729065e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.0.mlp.fc2", | |
| "block": 0, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009269612841308117, | |
| "searched_error": 0.008981985971331596, | |
| "improvement": 0.00028762686997652054, | |
| "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": 0.008961416780948639, | |
| "searched_error": 0.008927497081458569, | |
| "improvement": 3.391969949007034e-05, | |
| "clipped_row_fraction": 0.109375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.1.attn.out_proj", | |
| "block": 1, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.012739170342683792, | |
| "searched_error": 0.012587778270244598, | |
| "improvement": 0.00015139207243919373, | |
| "clipped_row_fraction": 0.375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.1.mlp.fc1", | |
| "block": 1, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008769280277192593, | |
| "searched_error": 0.008701339364051819, | |
| "improvement": 6.794091314077377e-05, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.1.mlp.fc2", | |
| "block": 1, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009266164153814316, | |
| "searched_error": 0.00898699089884758, | |
| "improvement": 0.00027917325496673584, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.2.attn.qkv_proj", | |
| "block": 2, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008809692226350307, | |
| "searched_error": 0.008738144300878048, | |
| "improvement": 7.154792547225952e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.2.attn.out_proj", | |
| "block": 2, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.012884954921901226, | |
| "searched_error": 0.0127450842410326, | |
| "improvement": 0.00013987068086862564, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.2.mlp.fc1", | |
| "block": 2, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00894160382449627, | |
| "searched_error": 0.008885352872312069, | |
| "improvement": 5.625095218420029e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.2.mlp.fc2", | |
| "block": 2, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009285910055041313, | |
| "searched_error": 0.009044776670634747, | |
| "improvement": 0.00024113338440656662, | |
| "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": 0.008725655265152454, | |
| "searched_error": 0.008664319291710854, | |
| "improvement": 6.13359734416008e-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": 0.011724220588803291, | |
| "searched_error": 0.011615997180342674, | |
| "improvement": 0.00010822340846061707, | |
| "clipped_row_fraction": 0.34375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.3.mlp.fc1", | |
| "block": 3, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008707783184945583, | |
| "searched_error": 0.00865384191274643, | |
| "improvement": 5.39412721991539e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.3.mlp.fc2", | |
| "block": 3, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00944015197455883, | |
| "searched_error": 0.00914775114506483, | |
| "improvement": 0.0002924008294939995, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.4.attn.qkv_proj", | |
| "block": 4, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009004554711282253, | |
| "searched_error": 0.008930174633860588, | |
| "improvement": 7.438007742166519e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.4.attn.out_proj", | |
| "block": 4, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010641911998391151, | |
| "searched_error": 0.010547509416937828, | |
| "improvement": 9.440258145332336e-05, | |
| "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": 0.00890740193426609, | |
| "searched_error": 0.008863168768584728, | |
| "improvement": 4.423316568136215e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.4.mlp.fc2", | |
| "block": 4, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009372618049383163, | |
| "searched_error": 0.009068206883966923, | |
| "improvement": 0.0003044111654162407, | |
| "clipped_row_fraction": 0.90625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.5.attn.qkv_proj", | |
| "block": 5, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008844029158353806, | |
| "searched_error": 0.008820337243378162, | |
| "improvement": 2.3691914975643158e-05, | |
| "clipped_row_fraction": 0.09375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.5.attn.out_proj", | |
| "block": 5, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.01112278364598751, | |
| "searched_error": 0.011005363427102566, | |
| "improvement": 0.00011742021888494492, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.5.mlp.fc1", | |
| "block": 5, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008900557644665241, | |
| "searched_error": 0.008855637162923813, | |
| "improvement": 4.4920481741428375e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.5.mlp.fc2", | |
| "block": 5, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009373556822538376, | |
| "searched_error": 0.009093226864933968, | |
| "improvement": 0.00028032995760440826, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.6.attn.qkv_proj", | |
| "block": 6, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008842005394399166, | |
| "searched_error": 0.00879959762096405, | |
| "improvement": 4.2407773435115814e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.6.attn.out_proj", | |
| "block": 6, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010709479451179504, | |
| "searched_error": 0.010630433447659016, | |
| "improvement": 7.904600352048874e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.6.mlp.fc1", | |
| "block": 6, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008929567411541939, | |
| "searched_error": 0.008865898475050926, | |
| "improvement": 6.366893649101257e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.6.mlp.fc2", | |
| "block": 6, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00941010843962431, | |
| "searched_error": 0.0091486144810915, | |
| "improvement": 0.0002614939585328102, | |
| "clipped_row_fraction": 0.765625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.7.attn.qkv_proj", | |
| "block": 7, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00882177148014307, | |
| "searched_error": 0.008771982975304127, | |
| "improvement": 4.978850483894348e-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": 0.011009636335074902, | |
| "searched_error": 0.010906275361776352, | |
| "improvement": 0.00010336097329854965, | |
| "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": 0.008888943120837212, | |
| "searched_error": 0.00882368441671133, | |
| "improvement": 6.52587041258812e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.7.mlp.fc2", | |
| "block": 7, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00938947219401598, | |
| "searched_error": 0.00911177508533001, | |
| "improvement": 0.0002776971086859703, | |
| "clipped_row_fraction": 0.796875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.8.attn.qkv_proj", | |
| "block": 8, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008989319205284119, | |
| "searched_error": 0.00893863569945097, | |
| "improvement": 5.0683505833148956e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.8.attn.out_proj", | |
| "block": 8, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010419621132314205, | |
| "searched_error": 0.010341066867113113, | |
| "improvement": 7.855426520109177e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.8.mlp.fc1", | |
| "block": 8, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00879050511866808, | |
| "searched_error": 0.008731446228921413, | |
| "improvement": 5.9058889746665955e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.8.mlp.fc2", | |
| "block": 8, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009295894764363766, | |
| "searched_error": 0.009004893712699413, | |
| "improvement": 0.0002910010516643524, | |
| "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": 0.008668643422424793, | |
| "searched_error": 0.008617810904979706, | |
| "improvement": 5.083251744508743e-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": 0.010687579400837421, | |
| "searched_error": 0.010574358515441418, | |
| "improvement": 0.00011322088539600372, | |
| "clipped_row_fraction": 0.375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.9.mlp.fc1", | |
| "block": 9, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008629563264548779, | |
| "searched_error": 0.008573157712817192, | |
| "improvement": 5.6405551731586456e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.9.mlp.fc2", | |
| "block": 9, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009348033927381039, | |
| "searched_error": 0.009073112159967422, | |
| "improvement": 0.0002749217674136162, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.10.attn.qkv_proj", | |
| "block": 10, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008851743303239346, | |
| "searched_error": 0.008800441399216652, | |
| "improvement": 5.1301904022693634e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.10.attn.out_proj", | |
| "block": 10, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.01040264405310154, | |
| "searched_error": 0.010317868553102016, | |
| "improvement": 8.477549999952316e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.10.mlp.fc1", | |
| "block": 10, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00881904549896717, | |
| "searched_error": 0.00878453440964222, | |
| "improvement": 3.451108932495117e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.10.mlp.fc2", | |
| "block": 10, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009316526353359222, | |
| "searched_error": 0.009032001718878746, | |
| "improvement": 0.0002845246344804764, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.11.attn.qkv_proj", | |
| "block": 11, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008875393308699131, | |
| "searched_error": 0.008854538202285767, | |
| "improvement": 2.085510641336441e-05, | |
| "clipped_row_fraction": 0.09375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.11.attn.out_proj", | |
| "block": 11, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010382995009422302, | |
| "searched_error": 0.010304039344191551, | |
| "improvement": 7.895566523075104e-05, | |
| "clipped_row_fraction": 0.28125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.11.mlp.fc1", | |
| "block": 11, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008945159614086151, | |
| "searched_error": 0.008855168707668781, | |
| "improvement": 8.999090641736984e-05, | |
| "clipped_row_fraction": 0.28125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.11.mlp.fc2", | |
| "block": 11, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009415395557880402, | |
| "searched_error": 0.009122848510742188, | |
| "improvement": 0.0002925470471382141, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.12.attn.qkv_proj", | |
| "block": 12, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008705309592187405, | |
| "searched_error": 0.008628779090940952, | |
| "improvement": 7.653050124645233e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.12.attn.out_proj", | |
| "block": 12, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010260747745633125, | |
| "searched_error": 0.01013985276222229, | |
| "improvement": 0.00012089498341083527, | |
| "clipped_row_fraction": 0.40625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.12.mlp.fc1", | |
| "block": 12, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008776841685175896, | |
| "searched_error": 0.008733909577131271, | |
| "improvement": 4.293210804462433e-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": 0.009360354393720627, | |
| "searched_error": 0.009091442450881004, | |
| "improvement": 0.0002689119428396225, | |
| "clipped_row_fraction": 0.796875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.13.attn.qkv_proj", | |
| "block": 13, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008797130547463894, | |
| "searched_error": 0.008764015510678291, | |
| "improvement": 3.311503678560257e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.13.attn.out_proj", | |
| "block": 13, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.01025098841637373, | |
| "searched_error": 0.010134506039321423, | |
| "improvement": 0.00011648237705230713, | |
| "clipped_row_fraction": 0.34375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.13.mlp.fc1", | |
| "block": 13, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008742579258978367, | |
| "searched_error": 0.008683488704264164, | |
| "improvement": 5.909055471420288e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.13.mlp.fc2", | |
| "block": 13, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009341541677713394, | |
| "searched_error": 0.009044078178703785, | |
| "improvement": 0.0002974634990096092, | |
| "clipped_row_fraction": 0.90625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.14.attn.qkv_proj", | |
| "block": 14, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008731739595532417, | |
| "searched_error": 0.00866743829101324, | |
| "improvement": 6.430130451917648e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.14.attn.out_proj", | |
| "block": 14, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010588740929961205, | |
| "searched_error": 0.0104738874360919, | |
| "improvement": 0.00011485349386930466, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.14.mlp.fc1", | |
| "block": 14, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008739639073610306, | |
| "searched_error": 0.008686761371791363, | |
| "improvement": 5.2877701818943024e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.14.mlp.fc2", | |
| "block": 14, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009477745741605759, | |
| "searched_error": 0.009174283593893051, | |
| "improvement": 0.0003034621477127075, | |
| "clipped_row_fraction": 0.875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.15.attn.qkv_proj", | |
| "block": 15, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008885015733540058, | |
| "searched_error": 0.00882111955434084, | |
| "improvement": 6.389617919921875e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.15.attn.out_proj", | |
| "block": 15, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010997327975928783, | |
| "searched_error": 0.010905122384428978, | |
| "improvement": 9.220559149980545e-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": 0.008847352117300034, | |
| "searched_error": 0.008780043572187424, | |
| "improvement": 6.730854511260986e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.15.mlp.fc2", | |
| "block": 15, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009283319115638733, | |
| "searched_error": 0.009016971103847027, | |
| "improvement": 0.0002663480117917061, | |
| "clipped_row_fraction": 0.734375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.16.attn.qkv_proj", | |
| "block": 16, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008748023770749569, | |
| "searched_error": 0.008716645650565624, | |
| "improvement": 3.13781201839447e-05, | |
| "clipped_row_fraction": 0.109375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.16.attn.out_proj", | |
| "block": 16, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009902860969305038, | |
| "searched_error": 0.00981918629258871, | |
| "improvement": 8.367467671632767e-05, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.16.mlp.fc1", | |
| "block": 16, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008831686340272427, | |
| "searched_error": 0.008767331019043922, | |
| "improvement": 6.435532122850418e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.16.mlp.fc2", | |
| "block": 16, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009359601885080338, | |
| "searched_error": 0.009068690240383148, | |
| "improvement": 0.00029091164469718933, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.17.attn.qkv_proj", | |
| "block": 17, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008687121793627739, | |
| "searched_error": 0.00865284912288189, | |
| "improvement": 3.427267074584961e-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": 0.010405216366052628, | |
| "searched_error": 0.010322467423975468, | |
| "improvement": 8.274894207715988e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.17.mlp.fc1", | |
| "block": 17, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008705413900315762, | |
| "searched_error": 0.0086616026237607, | |
| "improvement": 4.381127655506134e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.17.mlp.fc2", | |
| "block": 17, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009333509020507336, | |
| "searched_error": 0.009056181646883488, | |
| "improvement": 0.00027732737362384796, | |
| "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": 0.008936939761042595, | |
| "searched_error": 0.008889943361282349, | |
| "improvement": 4.699639976024628e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.18.attn.out_proj", | |
| "block": 18, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009594418108463287, | |
| "searched_error": 0.009486166760325432, | |
| "improvement": 0.00010825134813785553, | |
| "clipped_row_fraction": 0.375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.18.mlp.fc1", | |
| "block": 18, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008742792531847954, | |
| "searched_error": 0.008695181459188461, | |
| "improvement": 4.761107265949249e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.18.mlp.fc2", | |
| "block": 18, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009461008943617344, | |
| "searched_error": 0.009183678776025772, | |
| "improvement": 0.0002773301675915718, | |
| "clipped_row_fraction": 0.78125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.19.attn.qkv_proj", | |
| "block": 19, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008822006173431873, | |
| "searched_error": 0.008770683780312538, | |
| "improvement": 5.1322393119335175e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.19.attn.out_proj", | |
| "block": 19, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010611477307975292, | |
| "searched_error": 0.010500634089112282, | |
| "improvement": 0.0001108432188630104, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.19.mlp.fc1", | |
| "block": 19, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008817723952233791, | |
| "searched_error": 0.008774425834417343, | |
| "improvement": 4.329811781644821e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.19.mlp.fc2", | |
| "block": 19, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009473009034991264, | |
| "searched_error": 0.009183146059513092, | |
| "improvement": 0.0002898629754781723, | |
| "clipped_row_fraction": 0.84375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.20.attn.qkv_proj", | |
| "block": 20, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008687637746334076, | |
| "searched_error": 0.008649254217743874, | |
| "improvement": 3.838352859020233e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.20.attn.out_proj", | |
| "block": 20, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010098835453391075, | |
| "searched_error": 0.010017567314207554, | |
| "improvement": 8.126813918352127e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.20.mlp.fc1", | |
| "block": 20, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00895522441715002, | |
| "searched_error": 0.008894613943994045, | |
| "improvement": 6.061047315597534e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.20.mlp.fc2", | |
| "block": 20, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009419957175850868, | |
| "searched_error": 0.009130561724305153, | |
| "improvement": 0.00028939545154571533, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.21.attn.qkv_proj", | |
| "block": 21, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00888002384454012, | |
| "searched_error": 0.008830714970827103, | |
| "improvement": 4.930887371301651e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.21.attn.out_proj", | |
| "block": 21, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009559880010783672, | |
| "searched_error": 0.009482322260737419, | |
| "improvement": 7.75577500462532e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.21.mlp.fc1", | |
| "block": 21, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008936901576817036, | |
| "searched_error": 0.00889648962765932, | |
| "improvement": 4.0411949157714844e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.21.mlp.fc2", | |
| "block": 21, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009269020520150661, | |
| "searched_error": 0.00896172784268856, | |
| "improvement": 0.000307292677462101, | |
| "clipped_row_fraction": 0.890625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.22.attn.qkv_proj", | |
| "block": 22, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008947743102908134, | |
| "searched_error": 0.008884221315383911, | |
| "improvement": 6.352178752422333e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.22.attn.out_proj", | |
| "block": 22, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009753851220011711, | |
| "searched_error": 0.009624251164495945, | |
| "improvement": 0.00012960005551576614, | |
| "clipped_row_fraction": 0.453125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.22.mlp.fc1", | |
| "block": 22, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008831880986690521, | |
| "searched_error": 0.008773558773100376, | |
| "improvement": 5.832221359014511e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.22.mlp.fc2", | |
| "block": 22, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009388533420860767, | |
| "searched_error": 0.009097986854612827, | |
| "improvement": 0.00029054656624794006, | |
| "clipped_row_fraction": 0.84375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.23.attn.qkv_proj", | |
| "block": 23, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008868304081261158, | |
| "searched_error": 0.008819671347737312, | |
| "improvement": 4.863273352384567e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.23.attn.out_proj", | |
| "block": 23, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009776268154382706, | |
| "searched_error": 0.009708729572594166, | |
| "improvement": 6.753858178853989e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.23.mlp.fc1", | |
| "block": 23, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008618944324553013, | |
| "searched_error": 0.008562471717596054, | |
| "improvement": 5.647260695695877e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.23.mlp.fc2", | |
| "block": 23, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009360692463815212, | |
| "searched_error": 0.009071816690266132, | |
| "improvement": 0.0002888757735490799, | |
| "clipped_row_fraction": 0.84375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.24.attn.qkv_proj", | |
| "block": 24, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008849837817251682, | |
| "searched_error": 0.008781054988503456, | |
| "improvement": 6.878282874822617e-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": 0.009803637862205505, | |
| "searched_error": 0.009698456153273582, | |
| "improvement": 0.00010518170893192291, | |
| "clipped_row_fraction": 0.375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.24.mlp.fc1", | |
| "block": 24, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008830823004245758, | |
| "searched_error": 0.00879497081041336, | |
| "improvement": 3.585219383239746e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.24.mlp.fc2", | |
| "block": 24, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009445111267268658, | |
| "searched_error": 0.009153909049928188, | |
| "improvement": 0.00029120221734046936, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.25.attn.qkv_proj", | |
| "block": 25, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009023238904774189, | |
| "searched_error": 0.008959091268479824, | |
| "improvement": 6.414763629436493e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.25.attn.out_proj", | |
| "block": 25, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009833511896431446, | |
| "searched_error": 0.009738020598888397, | |
| "improvement": 9.549129754304886e-05, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.25.mlp.fc1", | |
| "block": 25, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008853540755808353, | |
| "searched_error": 0.008794158697128296, | |
| "improvement": 5.9382058680057526e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.25.mlp.fc2", | |
| "block": 25, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009346915408968925, | |
| "searched_error": 0.009076721034944057, | |
| "improvement": 0.000270194374024868, | |
| "clipped_row_fraction": 0.765625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.26.attn.qkv_proj", | |
| "block": 26, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008902003057301044, | |
| "searched_error": 0.008850892074406147, | |
| "improvement": 5.111098289489746e-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": 0.010004710406064987, | |
| "searched_error": 0.009898032993078232, | |
| "improvement": 0.00010667741298675537, | |
| "clipped_row_fraction": 0.390625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.26.mlp.fc1", | |
| "block": 26, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008825123310089111, | |
| "searched_error": 0.008754185400903225, | |
| "improvement": 7.093790918588638e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.26.mlp.fc2", | |
| "block": 26, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.0092239361256361, | |
| "searched_error": 0.008974296040832996, | |
| "improvement": 0.0002496400848031044, | |
| "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": 0.008917473256587982, | |
| "searched_error": 0.008879797533154488, | |
| "improvement": 3.767572343349457e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.27.attn.out_proj", | |
| "block": 27, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010261861607432365, | |
| "searched_error": 0.010153005830943584, | |
| "improvement": 0.00010885577648878098, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.27.mlp.fc1", | |
| "block": 27, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008872292935848236, | |
| "searched_error": 0.008831623010337353, | |
| "improvement": 4.066992551088333e-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": 0.009318964555859566, | |
| "searched_error": 0.0090524572879076, | |
| "improvement": 0.00026650726795196533, | |
| "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": 0.008684765547513962, | |
| "searched_error": 0.008628505282104015, | |
| "improvement": 5.626026540994644e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.28.attn.out_proj", | |
| "block": 28, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010002732276916504, | |
| "searched_error": 0.009931528940796852, | |
| "improvement": 7.12033361196518e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.28.mlp.fc1", | |
| "block": 28, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008683769032359123, | |
| "searched_error": 0.008647016249597073, | |
| "improvement": 3.675278276205063e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.28.mlp.fc2", | |
| "block": 28, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009296281263232231, | |
| "searched_error": 0.00901525653898716, | |
| "improvement": 0.0002810247242450714, | |
| "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": 0.008713721297681332, | |
| "searched_error": 0.008659077808260918, | |
| "improvement": 5.464348942041397e-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": 0.009850416332483292, | |
| "searched_error": 0.009744553826749325, | |
| "improvement": 0.00010586250573396683, | |
| "clipped_row_fraction": 0.34375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.29.mlp.fc1", | |
| "block": 29, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008692266419529915, | |
| "searched_error": 0.008643834851682186, | |
| "improvement": 4.843156784772873e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.29.mlp.fc2", | |
| "block": 29, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009496194310486317, | |
| "searched_error": 0.00922020897269249, | |
| "improvement": 0.00027598533779382706, | |
| "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": 0.008765683509409428, | |
| "searched_error": 0.00874114129692316, | |
| "improvement": 2.454221248626709e-05, | |
| "clipped_row_fraction": 0.109375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.30.attn.out_proj", | |
| "block": 30, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009816651232540607, | |
| "searched_error": 0.00971936620771885, | |
| "improvement": 9.728502482175827e-05, | |
| "clipped_row_fraction": 0.34375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.30.mlp.fc1", | |
| "block": 30, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008752512745559216, | |
| "searched_error": 0.008692821487784386, | |
| "improvement": 5.9691257774829865e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.30.mlp.fc2", | |
| "block": 30, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009255063720047474, | |
| "searched_error": 0.008998647332191467, | |
| "improvement": 0.0002564163878560066, | |
| "clipped_row_fraction": 0.75, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.31.attn.qkv_proj", | |
| "block": 31, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008724010549485683, | |
| "searched_error": 0.008665692992508411, | |
| "improvement": 5.8317556977272034e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.31.attn.out_proj", | |
| "block": 31, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009994729422032833, | |
| "searched_error": 0.009889819659292698, | |
| "improvement": 0.00010490976274013519, | |
| "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": 0.00875474326312542, | |
| "searched_error": 0.008676552213728428, | |
| "improvement": 7.819104939699173e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.31.mlp.fc2", | |
| "block": 31, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009443852119147778, | |
| "searched_error": 0.009161427617073059, | |
| "improvement": 0.0002824245020747185, | |
| "clipped_row_fraction": 0.796875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.32.attn.qkv_proj", | |
| "block": 32, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008674316108226776, | |
| "searched_error": 0.008613810874521732, | |
| "improvement": 6.050523370504379e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.32.attn.out_proj", | |
| "block": 32, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00985008291900158, | |
| "searched_error": 0.009747494012117386, | |
| "improvement": 0.00010258890688419342, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.32.mlp.fc1", | |
| "block": 32, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008692612871527672, | |
| "searched_error": 0.008645152673125267, | |
| "improvement": 4.7460198402404785e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.32.mlp.fc2", | |
| "block": 32, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00947093777358532, | |
| "searched_error": 0.009159333072602749, | |
| "improvement": 0.00031160470098257065, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.33.attn.qkv_proj", | |
| "block": 33, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008766084909439087, | |
| "searched_error": 0.008694433607161045, | |
| "improvement": 7.165130227804184e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.33.attn.out_proj", | |
| "block": 33, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00954029243439436, | |
| "searched_error": 0.009445435367524624, | |
| "improvement": 9.485706686973572e-05, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.33.mlp.fc1", | |
| "block": 33, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008781595155596733, | |
| "searched_error": 0.008732284419238567, | |
| "improvement": 4.931073635816574e-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": 0.009335415437817574, | |
| "searched_error": 0.00904041063040495, | |
| "improvement": 0.00029500480741262436, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.34.attn.qkv_proj", | |
| "block": 34, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008966388180851936, | |
| "searched_error": 0.008931505493819714, | |
| "improvement": 3.488268703222275e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.34.attn.out_proj", | |
| "block": 34, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009540051221847534, | |
| "searched_error": 0.009449652396142483, | |
| "improvement": 9.039882570505142e-05, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.34.mlp.fc1", | |
| "block": 34, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008829145692288876, | |
| "searched_error": 0.008788610808551311, | |
| "improvement": 4.053488373756409e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.34.mlp.fc2", | |
| "block": 34, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009387649595737457, | |
| "searched_error": 0.009096373803913593, | |
| "improvement": 0.000291275791823864, | |
| "clipped_row_fraction": 0.875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.35.attn.qkv_proj", | |
| "block": 35, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008860242553055286, | |
| "searched_error": 0.008821065537631512, | |
| "improvement": 3.917701542377472e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.35.attn.out_proj", | |
| "block": 35, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009603094309568405, | |
| "searched_error": 0.009491439908742905, | |
| "improvement": 0.00011165440082550049, | |
| "clipped_row_fraction": 0.390625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.35.mlp.fc1", | |
| "block": 35, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008813166990876198, | |
| "searched_error": 0.008791708387434483, | |
| "improvement": 2.145860344171524e-05, | |
| "clipped_row_fraction": 0.09375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.35.mlp.fc2", | |
| "block": 35, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009444838389754295, | |
| "searched_error": 0.009172103367745876, | |
| "improvement": 0.00027273502200841904, | |
| "clipped_row_fraction": 0.765625, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.36.attn.qkv_proj", | |
| "block": 36, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008860931731760502, | |
| "searched_error": 0.00881150271743536, | |
| "improvement": 4.942901432514191e-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": 0.009988026693463326, | |
| "searched_error": 0.009919547475874424, | |
| "improvement": 6.847921758890152e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.36.mlp.fc1", | |
| "block": 36, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.0088988421484828, | |
| "searched_error": 0.008851088583469391, | |
| "improvement": 4.775356501340866e-05, | |
| "clipped_row_fraction": 0.1875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.36.mlp.fc2", | |
| "block": 36, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009266898967325687, | |
| "searched_error": 0.008992289192974567, | |
| "improvement": 0.00027460977435112, | |
| "clipped_row_fraction": 0.796875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.37.attn.qkv_proj", | |
| "block": 37, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008839167654514313, | |
| "searched_error": 0.00880094151943922, | |
| "improvement": 3.8226135075092316e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.37.attn.out_proj", | |
| "block": 37, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010024740360677242, | |
| "searched_error": 0.009966987185180187, | |
| "improvement": 5.7753175497055054e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.37.mlp.fc1", | |
| "block": 37, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008853678591549397, | |
| "searched_error": 0.008804235607385635, | |
| "improvement": 4.944298416376114e-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": 0.009491628967225552, | |
| "searched_error": 0.009205091744661331, | |
| "improvement": 0.00028653722256422043, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.38.attn.qkv_proj", | |
| "block": 38, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008884002454578876, | |
| "searched_error": 0.008830550126731396, | |
| "improvement": 5.3452327847480774e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.38.attn.out_proj", | |
| "block": 38, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.01087699644267559, | |
| "searched_error": 0.01077630091458559, | |
| "improvement": 0.00010069552809000015, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.38.mlp.fc1", | |
| "block": 38, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008931271731853485, | |
| "searched_error": 0.008866948075592518, | |
| "improvement": 6.432365626096725e-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": 0.009255966171622276, | |
| "searched_error": 0.008989330381155014, | |
| "improvement": 0.00026663579046726227, | |
| "clipped_row_fraction": 0.796875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.39.attn.qkv_proj", | |
| "block": 39, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008898977190256119, | |
| "searched_error": 0.008829842321574688, | |
| "improvement": 6.913486868143082e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.39.attn.out_proj", | |
| "block": 39, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00986478291451931, | |
| "searched_error": 0.00979786366224289, | |
| "improvement": 6.69192522764206e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.39.mlp.fc1", | |
| "block": 39, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008810189552605152, | |
| "searched_error": 0.008753194473683834, | |
| "improvement": 5.6995078921318054e-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": 0.009537908248603344, | |
| "searched_error": 0.009237056598067284, | |
| "improvement": 0.00030085165053606033, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.40.attn.qkv_proj", | |
| "block": 40, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008767694234848022, | |
| "searched_error": 0.00870572030544281, | |
| "improvement": 6.19739294052124e-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": 0.009701002389192581, | |
| "searched_error": 0.009602167643606663, | |
| "improvement": 9.883474558591843e-05, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.40.mlp.fc1", | |
| "block": 40, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008829804137349129, | |
| "searched_error": 0.008786809630692005, | |
| "improvement": 4.2994506657123566e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.40.mlp.fc2", | |
| "block": 40, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009279806166887283, | |
| "searched_error": 0.009015350602567196, | |
| "improvement": 0.00026445556432008743, | |
| "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": 0.00888835359364748, | |
| "searched_error": 0.008865226991474628, | |
| "improvement": 2.3126602172851562e-05, | |
| "clipped_row_fraction": 0.09375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.41.attn.out_proj", | |
| "block": 41, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009856064803898335, | |
| "searched_error": 0.009737283922731876, | |
| "improvement": 0.00011878088116645813, | |
| "clipped_row_fraction": 0.40625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.41.mlp.fc1", | |
| "block": 41, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008642565459012985, | |
| "searched_error": 0.008587867952883244, | |
| "improvement": 5.469750612974167e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.41.mlp.fc2", | |
| "block": 41, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009489201940596104, | |
| "searched_error": 0.009183059446513653, | |
| "improvement": 0.00030614249408245087, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.42.attn.qkv_proj", | |
| "block": 42, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00878732930868864, | |
| "searched_error": 0.008722234517335892, | |
| "improvement": 6.509479135274887e-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": 0.009849688038229942, | |
| "searched_error": 0.009761529974639416, | |
| "improvement": 8.815806359052658e-05, | |
| "clipped_row_fraction": 0.3125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.42.mlp.fc1", | |
| "block": 42, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00881112739443779, | |
| "searched_error": 0.008781219832599163, | |
| "improvement": 2.990756183862686e-05, | |
| "clipped_row_fraction": 0.140625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.42.mlp.fc2", | |
| "block": 42, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009377618320286274, | |
| "searched_error": 0.009100445546209812, | |
| "improvement": 0.0002771727740764618, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.43.attn.qkv_proj", | |
| "block": 43, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00880368147045374, | |
| "searched_error": 0.00876226183027029, | |
| "improvement": 4.141964018344879e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.43.attn.out_proj", | |
| "block": 43, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010473590344190598, | |
| "searched_error": 0.010342192836105824, | |
| "improvement": 0.00013139750808477402, | |
| "clipped_row_fraction": 0.40625, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.43.mlp.fc1", | |
| "block": 43, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00889844261109829, | |
| "searched_error": 0.008808812126517296, | |
| "improvement": 8.963048458099365e-05, | |
| "clipped_row_fraction": 0.34375, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.43.mlp.fc2", | |
| "block": 43, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009177000261843204, | |
| "searched_error": 0.008896099403500557, | |
| "improvement": 0.00028090085834264755, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.44.attn.qkv_proj", | |
| "block": 44, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008935483172535896, | |
| "searched_error": 0.008860749192535877, | |
| "improvement": 7.473398000001907e-05, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.44.attn.out_proj", | |
| "block": 44, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010236470960080624, | |
| "searched_error": 0.010147100314497948, | |
| "improvement": 8.937064558267593e-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": 0.008784499950706959, | |
| "searched_error": 0.00872789416462183, | |
| "improvement": 5.6605786085128784e-05, | |
| "clipped_row_fraction": 0.21875, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.44.mlp.fc2", | |
| "block": 44, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009541667997837067, | |
| "searched_error": 0.009210311807692051, | |
| "improvement": 0.0003313561901450157, | |
| "clipped_row_fraction": 0.953125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.45.attn.qkv_proj", | |
| "block": 45, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008662065491080284, | |
| "searched_error": 0.008622739464044571, | |
| "improvement": 3.9326027035713196e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.45.attn.out_proj", | |
| "block": 45, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010617692954838276, | |
| "searched_error": 0.010556809604167938, | |
| "improvement": 6.088335067033768e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.45.mlp.fc1", | |
| "block": 45, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00887010246515274, | |
| "searched_error": 0.008804753422737122, | |
| "improvement": 6.53490424156189e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.45.mlp.fc2", | |
| "block": 45, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009545751847326756, | |
| "searched_error": 0.009240850806236267, | |
| "improvement": 0.00030490104109048843, | |
| "clipped_row_fraction": 0.859375, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.46.attn.qkv_proj", | |
| "block": 46, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008876703679561615, | |
| "searched_error": 0.008820494636893272, | |
| "improvement": 5.620904266834259e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.46.attn.out_proj", | |
| "block": 46, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010161706246435642, | |
| "searched_error": 0.010050925426185131, | |
| "improvement": 0.00011078082025051117, | |
| "clipped_row_fraction": 0.359375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.46.mlp.fc1", | |
| "block": 46, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008911539800465107, | |
| "searched_error": 0.008827130310237408, | |
| "improvement": 8.440949022769928e-05, | |
| "clipped_row_fraction": 0.265625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.46.mlp.fc2", | |
| "block": 46, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009484718553721905, | |
| "searched_error": 0.009192200377583504, | |
| "improvement": 0.00029251817613840103, | |
| "clipped_row_fraction": 0.828125, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.47.attn.qkv_proj", | |
| "block": 47, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008795163594186306, | |
| "searched_error": 0.00872830580919981, | |
| "improvement": 6.685778498649597e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.47.attn.out_proj", | |
| "block": 47, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010367481037974358, | |
| "searched_error": 0.010297443717718124, | |
| "improvement": 7.003732025623322e-05, | |
| "clipped_row_fraction": 0.234375, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.47.mlp.fc1", | |
| "block": 47, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008772429078817368, | |
| "searched_error": 0.00872031506150961, | |
| "improvement": 5.211401730775833e-05, | |
| "clipped_row_fraction": 0.203125, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.47.mlp.fc2", | |
| "block": 47, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00934167392551899, | |
| "searched_error": 0.009070958010852337, | |
| "improvement": 0.0002707159146666527, | |
| "clipped_row_fraction": 0.796875, | |
| "bf16_delta_bytes": 77048760 | |
| }, | |
| { | |
| "layer": "blocks.48.attn.qkv_proj", | |
| "block": 48, | |
| "kind": "attn.qkv_proj", | |
| "shape": [ | |
| 21504, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.00887906365096569, | |
| "searched_error": 0.008829780854284763, | |
| "improvement": 4.9282796680927277e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.48.attn.out_proj", | |
| "block": 48, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009912649169564247, | |
| "searched_error": 0.009812348522245884, | |
| "improvement": 0.00010030064731836319, | |
| "clipped_row_fraction": 0.328125, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.48.mlp.fc1", | |
| "block": 48, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008999514393508434, | |
| "searched_error": 0.008927279151976109, | |
| "improvement": 7.223524153232574e-05, | |
| "clipped_row_fraction": 0.25, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.48.mlp.fc2", | |
| "block": 48, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009443627670407295, | |
| "searched_error": 0.009146802127361298, | |
| "improvement": 0.0002968255430459976, | |
| "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": 0.008813359774649143, | |
| "searched_error": 0.008786115795373917, | |
| "improvement": 2.7243979275226593e-05, | |
| "clipped_row_fraction": 0.171875, | |
| "bf16_delta_bytes": 115519416 | |
| }, | |
| { | |
| "layer": "blocks.49.attn.out_proj", | |
| "block": 49, | |
| "kind": "attn.out_proj", | |
| "shape": [ | |
| 5376, | |
| 7168 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.010824794881045818, | |
| "searched_error": 0.010720481164753437, | |
| "improvement": 0.00010431371629238129, | |
| "clipped_row_fraction": 0.296875, | |
| "bf16_delta_bytes": 38513592 | |
| }, | |
| { | |
| "layer": "blocks.49.mlp.fc1", | |
| "block": 49, | |
| "kind": "mlp.fc1", | |
| "shape": [ | |
| 28672, | |
| 5376 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.008785880170762539, | |
| "searched_error": 0.008741860277950764, | |
| "improvement": 4.401989281177521e-05, | |
| "clipped_row_fraction": 0.15625, | |
| "bf16_delta_bytes": 154025912 | |
| }, | |
| { | |
| "layer": "blocks.49.mlp.fc2", | |
| "block": 49, | |
| "kind": "mlp.fc2", | |
| "shape": [ | |
| 5376, | |
| 14336 | |
| ], | |
| "sample_rows": 64, | |
| "absmax_error": 0.009804457426071167, | |
| "searched_error": 0.009507114998996258, | |
| "improvement": 0.0002973424270749092, | |
| "clipped_row_fraction": 0.8125, | |
| "bf16_delta_bytes": 77048760 | |
| } | |
| ] | |
| } | |