Upload checkpoints_all36_d128_block/search_step_750.compare_retrieval.json
Browse files
checkpoints_all36_d128_block/search_step_750.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_750.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": 0.7756117284297943,
|
| 50 |
+
"1": 0.8532524108886719,
|
| 51 |
+
"2": 0.898503303527832,
|
| 52 |
+
"3": 0.9247933924198151,
|
| 53 |
+
"4": 0.9357087314128876,
|
| 54 |
+
"5": 0.9496567249298096,
|
| 55 |
+
"6": 0.9385866224765778,
|
| 56 |
+
"7": 0.9828359186649323,
|
| 57 |
+
"8": 0.9707390367984772,
|
| 58 |
+
"9": 0.9764299988746643,
|
| 59 |
+
"10": 0.9706397652626038,
|
| 60 |
+
"11": 0.9758526980876923,
|
| 61 |
+
"12": 0.9699114561080933,
|
| 62 |
+
"13": 0.9716702997684479,
|
| 63 |
+
"14": 0.9731307923793793,
|
| 64 |
+
"15": 0.9723065197467804,
|
| 65 |
+
"16": 0.9619724154472351,
|
| 66 |
+
"17": 0.9667060077190399,
|
| 67 |
+
"18": 0.9725159108638763,
|
| 68 |
+
"19": 0.9684217274188995,
|
| 69 |
+
"20": 0.9755173027515411,
|
| 70 |
+
"21": 0.9796667695045471,
|
| 71 |
+
"22": 0.9698297381401062,
|
| 72 |
+
"23": 0.9845495820045471,
|
| 73 |
+
"24": 0.9784150421619415,
|
| 74 |
+
"25": 0.9885841608047485,
|
| 75 |
+
"26": 0.98563352227211,
|
| 76 |
+
"27": 0.9832673370838165,
|
| 77 |
+
"28": 0.9848426878452301,
|
| 78 |
+
"29": 0.987438291311264,
|
| 79 |
+
"30": 0.9862436354160309,
|
| 80 |
+
"31": 0.9839730858802795,
|
| 81 |
+
"32": 0.979794979095459,
|
| 82 |
+
"33": 0.9695486426353455,
|
| 83 |
+
"34": 0.960169792175293,
|
| 84 |
+
"35": 0.9648604094982147
|
| 85 |
+
},
|
| 86 |
+
"avg": 0.9603216788834996
|
| 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": 0.9240421950817108,
|
| 134 |
+
"1": 0.9610750675201416,
|
| 135 |
+
"2": 0.9658757448196411,
|
| 136 |
+
"3": 0.9772964715957642,
|
| 137 |
+
"4": 0.9824097156524658,
|
| 138 |
+
"5": 0.9867623746395111,
|
| 139 |
+
"6": 0.9807166755199432,
|
| 140 |
+
"7": 0.9962040483951569,
|
| 141 |
+
"8": 0.9934569895267487,
|
| 142 |
+
"9": 0.9951488673686981,
|
| 143 |
+
"10": 0.9924411773681641,
|
| 144 |
+
"11": 0.9950867295265198,
|
| 145 |
+
"12": 0.9929095506668091,
|
| 146 |
+
"13": 0.9934256374835968,
|
| 147 |
+
"14": 0.9937738478183746,
|
| 148 |
+
"15": 0.9944608509540558,
|
| 149 |
+
"16": 0.9920228123664856,
|
| 150 |
+
"17": 0.9936496913433075,
|
| 151 |
+
"18": 0.9954988360404968,
|
| 152 |
+
"19": 0.9934418499469757,
|
| 153 |
+
"20": 0.9959242641925812,
|
| 154 |
+
"21": 0.9965861737728119,
|
| 155 |
+
"22": 0.9939501285552979,
|
| 156 |
+
"23": 0.9973835349082947,
|
| 157 |
+
"24": 0.9962238371372223,
|
| 158 |
+
"25": 0.9976089596748352,
|
| 159 |
+
"26": 0.9972057044506073,
|
| 160 |
+
"27": 0.9966239333152771,
|
| 161 |
+
"28": 0.9968054592609406,
|
| 162 |
+
"29": 0.997564047574997,
|
| 163 |
+
"30": 0.9967389404773712,
|
| 164 |
+
"31": 0.9965249300003052,
|
| 165 |
+
"32": 0.9954393804073334,
|
| 166 |
+
"33": 0.9919858574867249,
|
| 167 |
+
"34": 0.989928811788559,
|
| 168 |
+
"35": 0.9892888367176056
|
| 169 |
+
},
|
| 170 |
+
"avg": 0.9895967203709815
|
| 171 |
+
}
|
| 172 |
+
}
|
| 173 |
+
},
|
| 174 |
+
"learned_over_raw_K128": 0.9939299972369198
|
| 175 |
+
}
|