Files
decision-models-benchmark/reports/sanity/oci/gliner-cuda.json
Marcos Lohmann 2af9dae193 Conjunto D1 sintético congelado e sanidade em CPU e GPU na OCI
- data/splits (d1-v1): dev 1183, calibração 1127, teste 1744 exemplos,
  43 rótulos, partição por lote de geração, SHA-256 em MANIFEST.json;
  cópias em dmb-entrada e dmb-logs-imutaveis.
- reports/datagen: relatórios de preparação e de anotação (3 LLMs em
  rodízio; kappa 0,98–0,99).
- reports/sanity/oci: sanidade dos 4 candidatos em CPU (us-chicago-1,
  sub-rede privada) e GPU A10 (sa-saopaulo-1).
- Plano: 47 de 78 tarefas concluídas; docs/02 com o resumo do conjunto.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-07 14:16:18 -03:00

224 lines
5.4 KiB
JSON

{
"candidate": {
"name": "gliner",
"model_id": "gliner@a35a0cd3b7a0",
"revision": "a35a0cd3b7a0f00f2effc576f454cd48fa98aa5f",
"adapter_version": "0.1.0",
"device": "cuda",
"context_limit": 4096,
"probabilities_source": "native"
},
"device": "cuda",
"load_seconds": 21.32,
"process_guard": "ok",
"conformance": [
{
"name": "valid_choice_noul",
"expected": "ok",
"got": "ok"
},
{
"name": "valid_score",
"expected": "ok",
"got": "ok"
},
{
"name": "valid_state_object",
"expected": "ok",
"got": "ok"
},
{
"name": "invalid_17_options",
"expected": "invalid_request",
"got": "invalid_request"
},
{
"name": "invalid_single_option",
"expected": "invalid_request",
"got": "invalid_request"
},
{
"name": "invalid_noul_missing_false",
"expected": "invalid_request",
"got": "invalid_request"
},
{
"name": "invalid_unknown_type",
"expected": "invalid_request",
"got": "invalid_request"
},
{
"name": "invalid_empty_state",
"expected": "invalid_request",
"got": "invalid_request"
},
{
"name": "invalid_no_questions",
"expected": "invalid_request",
"got": "invalid_request"
},
{
"name": "invalid_extra_field",
"expected": "invalid_request",
"got": "invalid_request"
}
],
"sanity": [
{
"name": "choice:pagamento",
"gold": "pagamento",
"pred": "pagamento",
"latency_ms": 16.4,
"answer": {
"type": "choice",
"choice": "pagamento",
"confidence": 0.6344155822832185,
"probabilities": {
"pagamento": 0.6344155822832185,
"cancelamento": 0.016834572365227046,
"suporte_tecnico": 0.022163173720466455,
"sem_correspondencia": 0.32658667163108795
}
},
"pred_permuted": "pagamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:cancelamento",
"gold": "cancelamento",
"pred": "cancelamento",
"latency_ms": 16.1,
"answer": {
"type": "choice",
"choice": "cancelamento",
"confidence": 0.8718585964717693,
"probabilities": {
"pagamento": 0.010419094712095255,
"cancelamento": 0.8718585964717693,
"suporte_tecnico": 0.012619434782507587,
"sem_correspondencia": 0.10510287403362785
}
},
"pred_permuted": "cancelamento",
"permutation_invariant": true,
"correct": true
},
{
"name": "choice:suporte_tecnico",
"gold": "suporte_tecnico",
"pred": "sem_correspondencia",
"latency_ms": 16.9,
"answer": {
"type": "choice",
"choice": "sem_correspondencia",
"confidence": 0.6342994187351121,
"probabilities": {
"pagamento": 0.02020120315928321,
"cancelamento": 0.04278698707030298,
"suporte_tecnico": 0.3027123910353017,
"sem_correspondencia": 0.6342994187351121
}
},
"pred_permuted": "sem_correspondencia",
"permutation_invariant": true,
"correct": false
},
{
"name": "choice:sem_correspondencia",
"gold": "sem_correspondencia",
"pred": "sem_correspondencia",
"latency_ms": 15.5,
"answer": {
"type": "choice",
"choice": "sem_correspondencia",
"confidence": 0.8604289616881081,
"probabilities": {
"pagamento": 0.028759510277003655,
"cancelamento": 0.0316479121558098,
"suporte_tecnico": 0.07916361587907846,
"sem_correspondencia": 0.8604289616881081
}
},
"pred_permuted": "sem_correspondencia",
"permutation_invariant": true,
"correct": true
},
{
"name": "noul:clara",
"gold": "true",
"pred": "false",
"latency_ms": 16.1,
"answer": {
"type": "noul",
"noul": 0.2368276601557085
},
"correct": false
},
{
"name": "noul:vaga",
"gold": "false",
"pred": "false",
"latency_ms": 16.4,
"answer": {
"type": "noul",
"noul": 0.20341337939580556
},
"correct": true
},
{
"name": "score:alta",
"gold": "2",
"pred": "0",
"latency_ms": 16.5,
"answer": {
"type": "score",
"score": 0.9812681382516582,
"confidence": 0.3614074480114148,
"probabilities": {
"0": 0.3614074480114148,
"1": 0.29591696572551235,
"2": 0.3426755862630729
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": false
},
{
"name": "score:baixa",
"gold": "0",
"pred": "0",
"latency_ms": 15.9,
"answer": {
"type": "score",
"score": 0.48167205020737197,
"confidence": 0.6750848881824415,
"probabilities": {
"0": 0.6750848881824415,
"1": 0.16815817342774508,
"2": 0.15675693838981344
},
"legend": {
"0": "Baixa",
"1": "Média",
"2": "Alta"
}
},
"correct": true
}
],
"summary": {
"contract_violations": [],
"sanity_correct": "5/8",
"permutation_invariant": "4/4"
},
"oci": {
"region": "sa-saopaulo-1",
"run_id": "20261007T162549Z-gliner-sanity"
}
}