mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-22 13:36:17 +00:00
ddefd158e9
the integration tests check if all of the metrics we currently support actual are queryable after inference requests this also tests thinks like aggregation, label filtering, etc Signed-off-by: Charlie Doern <cdoern@redhat.com>
39 lines
2.8 KiB
JSON
39 lines
2.8 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/api/generate",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"raw": true,
|
|
"prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nTest metrics generation 0<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
|
|
"options": {
|
|
"temperature": 0.0
|
|
},
|
|
"stream": false
|
|
},
|
|
"endpoint": "/api/generate",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"created_at": "2025-08-11T15:51:12.918723Z",
|
|
"done": true,
|
|
"done_reason": "stop",
|
|
"total_duration": 8868987792,
|
|
"load_duration": 2793275292,
|
|
"prompt_eval_count": 21,
|
|
"prompt_eval_duration": 250000000,
|
|
"eval_count": 344,
|
|
"eval_duration": 5823000000,
|
|
"response": "Here are some common test metrics used to evaluate the performance of a system:\n\n1. **Accuracy**: The proportion of correct predictions or classifications out of total predictions made.\n2. **Precision**: The ratio of true positives (correctly predicted instances) to the sum of true positives and false positives (incorrectly predicted instances).\n3. **Recall**: The ratio of true positives to the sum of true positives and false negatives (missed instances).\n4. **F1-score**: The harmonic mean of precision and recall, providing a balanced measure of both.\n5. **Mean Squared Error (MSE)**: The average squared difference between predicted and actual values.\n6. **Mean Absolute Error (MAE)**: The average absolute difference between predicted and actual values.\n7. **Root Mean Squared Percentage Error (RMSPE)**: The square root of the mean of the squared percentage differences between predicted and actual values.\n8. **Coefficient of Determination (R-squared, R2)**: Measures how well a model fits the data, with higher values indicating better fit.\n9. **Mean Absolute Percentage Error (MAPE)**: The average absolute percentage difference between predicted and actual values.\n10. **Normalized Mean Squared Error (NMSE)**: Similar to MSE, but normalized by the mean of the actual values.\n\nThese metrics can be used for various types of data, including:\n\n* Regression problems (e.g., predicting continuous values)\n* Classification problems (e.g., predicting categorical labels)\n* Time series forecasting\n* Clustering and dimensionality reduction\n\nWhen choosing a metric, consider the specific problem you're trying to solve, the type of data, and the desired level of precision.",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|