Upload checkpoints_all36_d128_block/search_step_800.compare_retrieval.json
Browse files
checkpoints_all36_d128_block/search_step_800.compare_retrieval.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "Qwen/Qwen3-4B-Instruct-2507",
|
| 3 |
+
"ckpt": "/tmp/checkpoints_all36_d128_block/search_step_800.pt",
|
| 4 |
+
"by_K": {
|
| 5 |
+
"128": {
|
| 6 |
+
"raw_qk": {
|
| 7 |
+
"per_layer": {
|
| 8 |
+
"0": 0.9221310317516327,
|
| 9 |
+
"1": 0.9183070361614227,
|
| 10 |
+
"2": 0.9386252164840698,
|
| 11 |
+
"3": 0.9387637376785278,
|
| 12 |
+
"4": 0.9440614581108093,
|
| 13 |
+
"5": 0.96429443359375,
|
| 14 |
+
"6": 0.9560344219207764,
|
| 15 |
+
"7": 0.9818542897701263,
|
| 16 |
+
"8": 0.9707900285720825,
|
| 17 |
+
"9": 0.9587394297122955,
|
| 18 |
+
"10": 0.9742867350578308,
|
| 19 |
+
"11": 0.9763059914112091,
|
| 20 |
+
"12": 0.9611693322658539,
|
| 21 |
+
"13": 0.9707654714584351,
|
| 22 |
+
"14": 0.9733296930789948,
|
| 23 |
+
"15": 0.9675203263759613,
|
| 24 |
+
"16": 0.9556995928287506,
|
| 25 |
+
"17": 0.9593449831008911,
|
| 26 |
+
"18": 0.9652450382709503,
|
| 27 |
+
"19": 0.9612957835197449,
|
| 28 |
+
"20": 0.9591256380081177,
|
| 29 |
+
"21": 0.9657162129878998,
|
| 30 |
+
"22": 0.962736189365387,
|
| 31 |
+
"23": 0.9788879752159119,
|
| 32 |
+
"24": 0.9710511267185211,
|
| 33 |
+
"25": 0.9860879778862,
|
| 34 |
+
"26": 0.9775076508522034,
|
| 35 |
+
"27": 0.977691113948822,
|
| 36 |
+
"28": 0.9794201850891113,
|
| 37 |
+
"29": 0.9821525514125824,
|
| 38 |
+
"30": 0.9875719547271729,
|
| 39 |
+
"31": 0.9842455685138702,
|
| 40 |
+
"32": 0.9791028797626495,
|
| 41 |
+
"33": 0.9772593379020691,
|
| 42 |
+
"34": 0.9759000241756439,
|
| 43 |
+
"35": 0.9796911776065826
|
| 44 |
+
},
|
| 45 |
+
"avg": 0.9661864332026906
|
| 46 |
+
},
|
| 47 |
+
"learned": {
|
| 48 |
+
"per_layer": {
|
| 49 |
+
"0": 0.7756268978118896,
|
| 50 |
+
"1": 0.8533660173416138,
|
| 51 |
+
"2": 0.8985396027565002,
|
| 52 |
+
"3": 0.9248833358287811,
|
| 53 |
+
"4": 0.9358105957508087,
|
| 54 |
+
"5": 0.9497621357440948,
|
| 55 |
+
"6": 0.9386124014854431,
|
| 56 |
+
"7": 0.9828340709209442,
|
| 57 |
+
"8": 0.9707432389259338,
|
| 58 |
+
"9": 0.9764380753040314,
|
| 59 |
+
"10": 0.9706515073776245,
|
| 60 |
+
"11": 0.9758569598197937,
|
| 61 |
+
"12": 0.9699209034442902,
|
| 62 |
+
"13": 0.9717125296592712,
|
| 63 |
+
"14": 0.9731432497501373,
|
| 64 |
+
"15": 0.9723271131515503,
|
| 65 |
+
"16": 0.9620000123977661,
|
| 66 |
+
"17": 0.9667199552059174,
|
| 67 |
+
"18": 0.972541332244873,
|
| 68 |
+
"19": 0.9684668481349945,
|
| 69 |
+
"20": 0.9755434393882751,
|
| 70 |
+
"21": 0.9796880185604095,
|
| 71 |
+
"22": 0.9698434174060822,
|
| 72 |
+
"23": 0.9845690429210663,
|
| 73 |
+
"24": 0.9784398972988129,
|
| 74 |
+
"25": 0.98859041929245,
|
| 75 |
+
"26": 0.9856358468532562,
|
| 76 |
+
"27": 0.9832888841629028,
|
| 77 |
+
"28": 0.9848624765872955,
|
| 78 |
+
"29": 0.9874634146690369,
|
| 79 |
+
"30": 0.9862565696239471,
|
| 80 |
+
"31": 0.9839431643486023,
|
| 81 |
+
"32": 0.9798043966293335,
|
| 82 |
+
"33": 0.9695849716663361,
|
| 83 |
+
"34": 0.9600768983364105,
|
| 84 |
+
"35": 0.9647442996501923
|
| 85 |
+
},
|
| 86 |
+
"avg": 0.9603414427902963
|
| 87 |
+
}
|
| 88 |
+
},
|
| 89 |
+
"256": {
|
| 90 |
+
"raw_qk": {
|
| 91 |
+
"per_layer": {
|
| 92 |
+
"0": 0.9736533463001251,
|
| 93 |
+
"1": 0.9831015169620514,
|
| 94 |
+
"2": 0.985590249300003,
|
| 95 |
+
"3": 0.9856403172016144,
|
| 96 |
+
"4": 0.9863723814487457,
|
| 97 |
+
"5": 0.9927175343036652,
|
| 98 |
+
"6": 0.9899796843528748,
|
| 99 |
+
"7": 0.9961064755916595,
|
| 100 |
+
"8": 0.9944310188293457,
|
| 101 |
+
"9": 0.9924624264240265,
|
| 102 |
+
"10": 0.9945598244667053,
|
| 103 |
+
"11": 0.9956617951393127,
|
| 104 |
+
"12": 0.9914700388908386,
|
| 105 |
+
"13": 0.9947893917560577,
|
| 106 |
+
"14": 0.9956192076206207,
|
| 107 |
+
"15": 0.9947386384010315,
|
| 108 |
+
"16": 0.9918601512908936,
|
| 109 |
+
"17": 0.9932802319526672,
|
| 110 |
+
"18": 0.994801938533783,
|
| 111 |
+
"19": 0.9929636716842651,
|
| 112 |
+
"20": 0.9928486049175262,
|
| 113 |
+
"21": 0.9940518736839294,
|
| 114 |
+
"22": 0.9925838708877563,
|
| 115 |
+
"23": 0.9956205189228058,
|
| 116 |
+
"24": 0.9944405257701874,
|
| 117 |
+
"25": 0.99702388048172,
|
| 118 |
+
"26": 0.9963724911212921,
|
| 119 |
+
"27": 0.9952751994132996,
|
| 120 |
+
"28": 0.9952269494533539,
|
| 121 |
+
"29": 0.9970046579837799,
|
| 122 |
+
"30": 0.9976439476013184,
|
| 123 |
+
"31": 0.9967932999134064,
|
| 124 |
+
"32": 0.9949435591697693,
|
| 125 |
+
"33": 0.9954463541507721,
|
| 126 |
+
"34": 0.9949491024017334,
|
| 127 |
+
"35": 0.9950292408466339
|
| 128 |
+
},
|
| 129 |
+
"avg": 0.9929181643658214
|
| 130 |
+
},
|
| 131 |
+
"learned": {
|
| 132 |
+
"per_layer": {
|
| 133 |
+
"0": 0.9241782128810883,
|
| 134 |
+
"1": 0.9612297713756561,
|
| 135 |
+
"2": 0.9658167064189911,
|
| 136 |
+
"3": 0.9773095548152924,
|
| 137 |
+
"4": 0.9823991358280182,
|
| 138 |
+
"5": 0.9867597222328186,
|
| 139 |
+
"6": 0.9807394444942474,
|
| 140 |
+
"7": 0.9962039291858673,
|
| 141 |
+
"8": 0.9934562742710114,
|
| 142 |
+
"9": 0.9951532781124115,
|
| 143 |
+
"10": 0.9924466609954834,
|
| 144 |
+
"11": 0.9950800836086273,
|
| 145 |
+
"12": 0.992906391620636,
|
| 146 |
+
"13": 0.9934229552745819,
|
| 147 |
+
"14": 0.9937788546085358,
|
| 148 |
+
"15": 0.9944615662097931,
|
| 149 |
+
"16": 0.9920341670513153,
|
| 150 |
+
"17": 0.9936630129814148,
|
| 151 |
+
"18": 0.995515376329422,
|
| 152 |
+
"19": 0.993456095457077,
|
| 153 |
+
"20": 0.9959358274936676,
|
| 154 |
+
"21": 0.9966034889221191,
|
| 155 |
+
"22": 0.9939581751823425,
|
| 156 |
+
"23": 0.9973926544189453,
|
| 157 |
+
"24": 0.9962430894374847,
|
| 158 |
+
"25": 0.9975726306438446,
|
| 159 |
+
"26": 0.9972138106822968,
|
| 160 |
+
"27": 0.9966393709182739,
|
| 161 |
+
"28": 0.9968178272247314,
|
| 162 |
+
"29": 0.9975622594356537,
|
| 163 |
+
"30": 0.9967368543148041,
|
| 164 |
+
"31": 0.9965087473392487,
|
| 165 |
+
"32": 0.9954238533973694,
|
| 166 |
+
"33": 0.9919829368591309,
|
| 167 |
+
"34": 0.9898959100246429,
|
| 168 |
+
"35": 0.9893121719360352
|
| 169 |
+
},
|
| 170 |
+
"avg": 0.9896058556106355
|
| 171 |
+
}
|
| 172 |
+
}
|
| 173 |
+
},
|
| 174 |
+
"learned_over_raw_K128": 0.9939504528199392
|
| 175 |
+
}
|