Etolith/perseval-task-completion
0
1{2 "schema_version": "perseval.task_completion_onnx_parity.v1",3 "model_id": "perseval-task-completion-runtime-candidate@f5d54444a518ac4a",4 "absolute_tolerance": 0.0001,5 "cases": [6 {7 "case_id": "development-1",8 "inputs": [9 {10 "name": "structured_features",11 "element_type": "f32",12 "shape": [13 1,14 3915 ],16 "f32_values": [17 1.7917594909667969,18 0.6931471824645996,19 0.8333333134651184,20 0.1409505158662796,21 0.47426068782806396,22 0.0,23 0.0,24 0.0,25 0.0,26 0.20000000298023224,27 0.800000011920929,28 0.0,29 0.0,30 0.0,31 0.0,32 0.0,33 0.0,34 0.0,35 0.0,36 0.0,37 0.0,38 0.0,39 1.6094379425048828,40 0.0,41 0.6931471824645996,42 0.0,43 0.0,44 0.0,45 0.0,46 0.0,47 1.0986123085021973,48 0.4000000059604645,49 0.6000000238418579,50 0.012702078558504581,51 0.012702078558504581,52 0.0,53 0.0,54 0.0,55 0.056 ]57 }58 ],59 "expected_outputs": [60 {61 "name": "logits",62 "shape": [63 1,64 265 ],66 "f32_values": [67 -1.7064403295516968,68 1.258264660835266169 ]70 }71 ]72 },73 {74 "case_id": "development-2",75 "inputs": [76 {77 "name": "structured_features",78 "element_type": "f32",79 "shape": [80 1,81 3982 ],83 "f32_values": [84 1.3862943649291992,85 3.1354942321777344,86 0.11999999731779099,87 0.09619140625,88 0.10016949474811554,89 0.0,90 0.0,91 0.0,92 0.0,93 0.3333333432674408,94 0.6666666865348816,95 0.0,96 0.0,97 0.0,98 0.0,99 0.0,100 0.0,101 0.0,102 0.0,103 0.0,104 0.0,105 0.0,106 1.0986123085021973,107 0.0,108 0.6931471824645996,109 0.0,110 0.0,111 0.0,112 0.0,113 0.0,114 1.0986123085021973,115 0.6666666865348816,116 0.3333333432674408,117 0.018612520769238472,118 0.018612520769238472,119 0.0,120 0.0,121 0.0,122 0.0123 ]124 }125 ],126 "expected_outputs": [127 {128 "name": "logits",129 "shape": [130 1,131 2132 ],133 "f32_values": [134 7.030359268188477,135 -7.286364555358887136 ]137 }138 ]139 },140 {141 "case_id": "development-3",142 "inputs": [143 {144 "name": "structured_features",145 "element_type": "f32",146 "shape": [147 1,148 39149 ],150 "f32_values": [151 3.044522523880005,152 3.4965076446533203,153 0.38461539149284363,154 0.3160807192325592,155 0.21864445507526398,156 0.0,157 0.0,158 0.0,159 0.0,160 0.05000000074505806,161 0.949999988079071,162 0.0,163 0.0,164 0.0,165 0.0,166 0.0,167 0.0,168 0.0,169 0.0,170 0.0,171 0.0,172 0.0,173 2.995732307434082,174 0.0,175 0.6931471824645996,176 0.0,177 0.0,178 0.0,179 0.0,180 0.0,181 1.0986123085021973,182 0.10000000149011612,183 0.8999999761581421,184 0.005664263851940632,185 0.005664263851940632,186 0.0,187 0.0,188 0.0,189 0.0190 ]191 }192 ],193 "expected_outputs": [194 {195 "name": "logits",196 "shape": [197 1,198 2199 ],200 "f32_values": [201 -3.417558193206787,202 2.5924134254455566203 ]204 }205 ]206 },207 {208 "case_id": "development-4",209 "inputs": [210 {211 "name": "structured_features",212 "element_type": "f32",213 "shape": [214 1,215 39216 ],217 "f32_values": [218 2.6390573978424072,219 3.6888794898986816,220 0.25,221 0.2177734375,222 0.1523571014404297,223 0.0,224 0.0,225 0.0,226 0.0,227 0.07692307978868484,228 0.9230769276618958,229 0.0,230 0.0,231 0.0,232 0.0,233 0.0,234 0.0,235 0.0,236 0.0,237 0.0,238 0.0,239 0.0,240 2.5649492740631104,241 0.0,242 0.6931471824645996,243 0.0,244 0.0,245 0.0,246 0.0,247 0.0,248 1.0986123085021973,249 0.1538461595773697,250 0.8461538553237915,251 0.008221225813031197,252 0.008221225813031197,253 0.0,254 0.0,255 0.0,256 0.0257 ]258 }259 ],260 "expected_outputs": [261 {262 "name": "logits",263 "shape": [264 1,265 2266 ],267 "f32_values": [268 2.6683249473571777,269 -3.4865827560424805270 ]271 }272 ]273 },274 {275 "case_id": "development-5",276 "inputs": [277 {278 "name": "structured_features",279 "element_type": "f32",280 "shape": [281 1,282 39283 ],284 "f32_values": [285 3.828641414642334,286 0.6931471824645996,287 0.97826087474823,288 0.85400390625,289 0.23878219723701477,290 0.0,291 0.6931471824645996,292 1.0,293 0.02222222276031971,294 0.9777777791023254,295 0.0,296 1.0986123085021973,297 0.0,298 0.0,299 0.6931471824645996,300 0.6931471824645996,301 1.945910096168518,302 0.0,303 3.5553481578826904,304 0.0,305 0.0,306 0.0,307 0.0,308 0.6931471824645996,309 3.8066625595092773,310 0.0,311 1.0,312 0.5777778029441833,313 2.995732307434082,314 0.0,315 2.397895336151123,316 0.2666666805744171,317 0.7333333492279053,318 0.0020964359864592552,319 0.0045740422792732716,320 0.0,321 0.0,322 0.0,323 0.0324 ]325 }326 ],327 "expected_outputs": [328 {329 "name": "logits",330 "shape": [331 1,332 2333 ],334 "f32_values": [335 10.38206672668457,336 -7.639095783233643337 ]338 }339 ]340 },341 {342 "case_id": "development-6",343 "inputs": [344 {345 "name": "structured_features",346 "element_type": "f32",347 "shape": [348 1,349 39350 ],351 "f32_values": [352 3.828641414642334,353 0.6931471824645996,354 0.97826087474823,355 0.97509765625,356 0.2621193528175354,357 0.0,358 0.0,359 0.0,360 0.02222222276031971,361 0.9777777791023254,362 0.0,363 0.6931471824645996,364 0.0,365 0.0,366 0.6931471824645996,367 0.0,368 0.0,369 0.0,370 3.7376697063446045,371 0.6931471824645996,372 0.0,373 0.0,374 0.0,375 0.6931471824645996,376 3.8066625595092773,377 0.0,378 1.0,379 0.02222222276031971,380 3.7841897010803223,381 0.0,382 2.3025851249694824,383 0.1111111119389534,384 0.8888888955116272,385 0.0018360874382779002,386 0.0018360874382779002,387 0.0,388 0.0,389 0.0,390 0.0391 ]392 }393 ],394 "expected_outputs": [395 {396 "name": "logits",397 "shape": [398 1,399 2400 ],401 "f32_values": [402 6.084724426269531,403 -2.748540163040161404 ]405 }406 ]407 },408 {409 "case_id": "development-7",410 "inputs": [411 {412 "name": "structured_features",413 "element_type": "f32",414 "shape": [415 1,416 39417 ],418 "f32_values": [419 3.4965076446533203,420 2.70805025100708,421 0.695652186870575,422 0.9895833134651184,423 0.24384374916553497,424 0.0,425 0.0,426 0.0,427 0.0,428 1.0,429 0.0,430 1.0986123085021973,431 0.0,432 0.0,433 2.1972246170043945,434 0.0,435 0.0,436 0.0,437 3.0910425186157227,438 0.0,439 0.0,440 0.0,441 0.0,442 0.0,443 3.4965076446533203,444 0.0,445 1.0,446 0.0,447 0.0,448 0.0,449 2.079441547393799,450 0.375,451 0.625,452 0.001809210516512394,453 0.001809210516512394,454 0.0,455 0.0,456 0.0,457 0.0458 ]459 }460 ],461 "expected_outputs": [462 {463 "name": "logits",464 "shape": [465 1,466 2467 ],468 "f32_values": [469 -6.550144195556641,470 6.765974521636963471 ]472 }473 ]474 },475 {476 "case_id": "development-8",477 "inputs": [478 {479 "name": "structured_features",480 "element_type": "f32",481 "shape": [482 1,483 39484 ],485 "f32_values": [486 3.5835189819335938,487 2.4849066734313965,488 0.760869562625885,489 0.9913737177848816,490 0.21843284368515015,491 0.0,492 0.0,493 0.0,494 0.0,495 1.0,496 0.0,497 0.6931471824645996,498 0.0,499 0.0,500 1.945910096168518,501 0.0,502 0.6931471824645996,503 0.0,504 3.295836925506592,505 0.0,506 0.0,507 0.0,508 0.0,509 0.0,510 3.5835189819335938,511 0.0,512 1.0,513 0.0,514 0.0,515 0.0,516 2.3025851249694824,517 0.2857142984867096,518 0.7142857313156128,519 0.0018059432040899992,520 0.0018059432040899992,521 0.0,522 0.0,523 0.0,524 0.0525 ]526 }527 ],528 "expected_outputs": [529 {530 "name": "logits",531 "shape": [532 1,533 2534 ],535 "f32_values": [536 -0.5859965682029724,537 1.4117785692214966538 ]539 }540 ]541 }542 ]543}544