Set created_at on the benchmark records
Browse files2026-09-07T11:39:36Z - the time the measurements were sent over (12:39:36 BST).
context.dataset (name + sample_count) is still outstanding and remains the only schema validation error. Note dataset.name forms part of the report identity URN, so it should not be filled with a placeholder: a later correction would insert a duplicate report rather than update the existing one. created_at is not part of that URN, so this value can be corrected in place if the true measurement time differs.
benchmarks/gemma-4-e2b-vivo-x300-bf16.yaml
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
version: 1.2.0
|
| 2 |
report_type: llm-generative
|
|
|
|
| 3 |
profile: Baseline
|
| 4 |
context:
|
| 5 |
target_ref: vivo-x300
|
|
|
|
| 1 |
version: 1.2.0
|
| 2 |
report_type: llm-generative
|
| 3 |
+
created_at: '2026-09-07T11:39:36Z'
|
| 4 |
profile: Baseline
|
| 5 |
context:
|
| 6 |
target_ref: vivo-x300
|
benchmarks/gemma-4-e2b-vivo-x300-int4.yaml
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
version: 1.2.0
|
| 2 |
report_type: llm-generative
|
|
|
|
| 3 |
profile: Arm-Optimized
|
| 4 |
context:
|
| 5 |
target_ref: vivo-x300
|
|
|
|
| 1 |
version: 1.2.0
|
| 2 |
report_type: llm-generative
|
| 3 |
+
created_at: '2026-09-07T11:39:36Z'
|
| 4 |
profile: Arm-Optimized
|
| 5 |
context:
|
| 6 |
target_ref: vivo-x300
|