Push from a local computer

.pytest_cache/v/cache/lastfailed

@@ -1,14 +1,5 @@
 {
-  "tests/model_evaluation/test_model_evaluator.py::test_evaluate": true,
-  "tests/model_evaluation/test_model_evaluator.py::test_evaluate_subset": true,
-  "tests/model_evaluation/test_model_evaluator.py::test_save_results": true,
-  "tests/model_evaluation/test_model_evaluator.py::test_save_object": true,
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_evaluate": true,
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_evaluate_subset": true,
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_save_object": true,
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_save_results": true,
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_when_evaluating_return_dict": true,
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_save_metrics": true,
-  "tests/tasks/evaluation/test_evaluation_piaf.py::TaskPIAFTest::test_given_a_prediction_smaller_than_corpus_when_compute_then_return_expected_result_and_warning": true,
-  "tests/tasks/evaluation/test_evaluation_piaf.py::TaskPIAFTest::test_given_a_prediction_when_compute_then_return_expected_result_no_warnings": true
+  "tests/tasks/evaluation/test_evaluation_expressions_quebecoises.py::TaskexpressionsquebecoisesTest::test_given_a_prediction_larger_than_ground_truth_raise_error": true,
+  "tests/tasks/evaluation/test_evaluation_expressions_quebecoises.py::TaskexpressionsquebecoisesTest::test_given_a_prediction_smaller_than_corpus_when_compute_then_return_expected_result_and_warning": true,
+  "tests/tasks/evaluation/test_evaluation_expressions_quebecoises.py::TaskexpressionsquebecoisesTest::test_given_a_prediction_when_compute_then_return_expected_result_no_warnings": true
 }

.pytest_cache/v/cache/nodeids

@@ -1,5 +1,4 @@
 [
-  "predictions/cuda_test.py::test_cuda",
   "tests/backend/test_evaluation.py::ComputeTasksRatingsTest::test_evaluation_loop",
   "tests/backend/test_submission_api.py::test_health_check",
   "tests/backend/test_submission_api.py::test_leaderboard_empty",
@@ -17,23 +16,10 @@
   "tests/backend/test_validation_tools.py::ValidateSubmissionJSONTest::test_given_a_json_of_unaccepted_format_when_validate_then_does_raise_error",
   "tests/backend/test_validation_tools.py::ValidateSubmissionTasksNameJSONTest::test_given_a_json_of_accepted_task_when_validate_then_does_not_raise_error",
   "tests/backend/test_validation_tools.py::ValidateSubmissionTasksNameJSONTest::test_given_a_json_of_unaccepted_task_when_validate_then_does_raise_error",
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_compute_metrics",
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_evaluate",
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_evaluate_subset",
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_save_metrics",
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_save_object",
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_save_results",
   "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_when_compute_metrics_return_metrics_dict",
-  "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_when_evaluating_return_dict",
   "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_when_evaluating_return_formatted_dict",
   "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_when_task_is_generative_generate",
   "tests/model_evaluation/test_model_evaluator.py::ModelEvaluatorTest::test_when_task_is_inference_infer",
-  "tests/model_evaluation/test_model_evaluator.py::test_compute_metrics",
-  "tests/model_evaluation/test_model_evaluator.py::test_evaluate",
-  "tests/model_evaluation/test_model_evaluator.py::test_evaluate_subset",
-  "tests/model_evaluation/test_model_evaluator.py::test_save_metrics",
-  "tests/model_evaluation/test_model_evaluator.py::test_save_object",
-  "tests/model_evaluation/test_model_evaluator.py::test_save_results",
   "tests/tasks/evaluation/test_evaluation_allocine.py::TaskAllocineTest::test_given_a_prediction_larger_than_ground_truth_raise_error",
   "tests/tasks/evaluation/test_evaluation_allocine.py::TaskAllocineTest::test_given_a_prediction_smaller_than_corpus_when_compute_then_return_expected_result_and_warning",
   "tests/tasks/evaluation/test_evaluation_allocine.py::TaskAllocineTest::test_given_a_prediction_when_compute_then_return_expected_result_no_warnings",
@@ -46,9 +32,6 @@
   "tests/tasks/evaluation/test_evaluation_gqnli.py::TaskGQNLITest::test_given_a_prediction_larger_than_ground_truth_raise_error",
   "tests/tasks/evaluation/test_evaluation_gqnli.py::TaskGQNLITest::test_given_a_prediction_smaller_than_corpus_when_compute_then_return_expected_result_and_warning",
   "tests/tasks/evaluation/test_evaluation_gqnli.py::TaskGQNLITest::test_given_a_prediction_when_compute_then_return_expected_result_no_warnings",
-  "tests/tasks/evaluation/test_evaluation_opus_parcus.py::TaskOpusParcusTest::test_given_a_prediction_larger_than_ground_truth_raise_error",
-  "tests/tasks/evaluation/test_evaluation_opus_parcus.py::TaskOpusParcusTest::test_given_a_prediction_smaller_than_corpus_when_compute_then_return_expected_result_and_warning",
-  "tests/tasks/evaluation/test_evaluation_opus_parcus.py::TaskOpusParcusTest::test_given_a_prediction_when_compute_then_return_expected_result_no_warnings",
   "tests/tasks/evaluation/test_evaluation_paws_x.py::TaskPawsXTest::test_given_a_prediction_larger_than_ground_truth_raise_error",
   "tests/tasks/evaluation/test_evaluation_paws_x.py::TaskPawsXTest::test_given_a_prediction_smaller_than_corpus_when_compute_then_return_expected_result_and_warning",
   "tests/tasks/evaluation/test_evaluation_paws_x.py::TaskPawsXTest::test_given_a_prediction_when_compute_then_return_expected_result_no_warnings",

Dockerfile

@@ -15,8 +15,9 @@ RUN apt-get update && apt-get install -y nginx \
     && rm -rf /var/lib/apt/lists/*
 
 COPY src/docker_requirements.txt /app/src/
-RUN pip install -r /app/src/docker_requirements.txt && \
-    rm -rf ~/.cache/pip
+RUN pip install --upgrade pip wheel
+RUN pip install --cache-dir=~/.cache/pip --prefer-binary pyarrow pandas numpy scipy fsspec aiohttp tqdm --progress-bar off -v
+RUN pip install --cache-dir=~/.cache/pip -r /app/src/docker_requirements.txt -v --prefer-binary && rm -rf ~/.cache/pip
 COPY src/ /app/src/
 
 # Copy Nginx config (adjust path if needed)

frontend/src/app/results/[id]/page.js

@@ -34,7 +34,7 @@ export default function ResultsPage() {
   const handleDownload = async () => {
     if (!data) return;
     try {
-      const res = await fetch(`http://localhost:8000/results/${submissionId}.json`);
+      const res = await fetch(`${BACKEND_ADDRESS}/results/${submissionId}.json`);
       if (!res.ok) throw new Error(`HTTP ${res.status}`);
       const blob = await res.blob();
       const url = URL.createObjectURL(blob);

push_to_spaces.py

@@ -7,5 +7,5 @@ upload_folder(
     repo_id=repo_id,
     folder_path=local_dir,
     repo_type="space",  # Important: this tells HF it's a Space
-    commit_message="Initial snapshot upload",
+    commit_message="Push from a local computer",
 )

src/backend/submission_api.py

@@ -5,6 +5,7 @@ import os
 import sys
 import uuid
 from contextlib import asynccontextmanager
+from datetime import datetime
 from functools import lru_cache
 from pathlib import Path
 from typing import Dict, List, Any
@@ -73,6 +74,7 @@ async def submit(
     predictions_zip: UploadFile = File(...),
     display_name: str = Form(...),
 ):
+    logging.info("Starting submission")
     info_message = f"Submission from {email!r} as {display_name!r}."
     logging.info(info_message)
     zip_bytes = await predictions_zip.read()
@@ -83,8 +85,12 @@ async def submit(
     validate_submission_json(submission_json)
 
     tasks: List[Task] = tasks_factory(submission_json)
+    logging.info("Computation started")
+    start = datetime.now()
     submission_response = compute_tasks_ratings(tasks=tasks, submission=submission_json)
-
+    computation_time = datetime.now() - start
+    info_message = f"Computation ended in {computation_time}"
+    logging.info(info_message)
     submission_id = str(uuid.uuid4())
     submission_response.update(
         {

src/docker_requirements.txt

@@ -9,8 +9,9 @@ uvicorn
 # Optional: pretty printing, progress bars, etc.
 tqdm
 aenum
-accelerate
+
 evaluate
 wheel
+
 # Pour compatibilité ancienne
 protobuf<=3.20.3

start.sh

@@ -1,23 +1,25 @@
-#!/bin/sh
-# Start FastAPI
-echo '🔧 Starting backend...'
-uvicorn src.backend.submission_api:app --host 0.0.0.0 --port 8000  &
-
-until curl -s http://localhost:8000/ > /dev/null; do
-    echo "FastAPI not ready yet. Retrying in 1s..."
-    sleep 1
-done
-
-echo '✅ Backend ready'
-ls
-# Start Next.js
-echo '🚀 Starting frontend'
-cd /app/frontend
-npm run start -- -p 8001 &
-echo '🚀 Frontend ready'
-# Start Nginx to reverse proxy
-echo "Starting Nginx"
-nginx -g "daemon off;"
-echo "Nginx ready"
-
+#!/bin/sh
+# Start FastAPI
+echo '🔧 Starting backend...'
+uvicorn src.backend.submission_api:app \
+  --host 0.0.0.0 --port 8000 --log-level debug \
+  > /app/backend.log 2>&1 &
+
+until curl -s http://localhost:8000/ > /dev/null; do
+    echo "FastAPI not ready yet. Retrying in 5 seconds..."
+    sleep 5
+done
+
+echo '✅ Backend ready'
+ls
+# Start Next.js
+echo '🚀 Starting frontend'
+cd frontend
+npm run start -- -p 8001 &
+echo '🚀 Frontend ready'
+# Start Nginx to reverse proxy
+echo "Starting Nginx"
+nginx -g "daemon off;"
+echo "Nginx ready"
+
 echo " container ready !"