| 2025-11-30 15:13:23 - eval_codegen - INFO - Logging to: logs/codegen/eval_codegen_20251130_151323.log |
| 2025-11-30 15:13:23 - eval_codegen - INFO - Monitor progress: tail -f logs/codegen/eval_codegen_20251130_151323.log |
| 2025-11-30 15:13:23 - eval_codegen - INFO - ============================================================ |
| 2025-11-30 15:13:23 - eval_codegen - INFO - CodeGen Evaluation |
| 2025-11-30 15:13:23 - eval_codegen - INFO - ============================================================ |
| 2025-11-30 15:13:23 - eval_codegen - INFO - Using GPU: NVIDIA GeForce RTX 5090 |
| 2025-11-30 15:13:23 - eval_codegen - INFO - Configuration: |
| 2025-11-30 15:13:23 - eval_codegen - INFO - checkpoint: model/checkpoints/run1-python-codegen |
| 2025-11-30 15:13:23 - eval_codegen - INFO - data: datasets/python |
| 2025-11-30 15:13:23 - eval_codegen - INFO - k: 5 |
| 2025-11-30 15:13:23 - eval_codegen - INFO - batch_size: 8 |
| 2025-11-30 15:13:23 - eval_codegen - INFO - device: cuda |
| 2025-11-30 15:13:23 - eval_codegen - INFO - Loading model from model/checkpoints/run1-python-codegen... |
| 2025-11-30 15:13:24 - eval_codegen - INFO - Model loaded and set to eval mode |
| 2025-11-30 15:13:24 - eval_codegen - INFO - Loaded 19427 test examples |
| 2025-11-30 15:13:24 - eval_codegen - INFO - Starting evaluation with batch_size=8, k=5 |
| 2025-11-30 15:13:24 - eval_codegen - INFO - Total batches: 2429 |
| 2025-11-30 16:23:24 - eval_codegen - INFO - Evaluation completed in 4201.16 seconds |
| 2025-11-30 16:23:24 - eval_codegen - INFO - Average speed: 4.62 samples/second |
| 2025-11-30 16:23:24 - eval_codegen - INFO - Metrics saved to: model/metrics/run1-python-codegen/metrics.json |
| 2025-11-30 16:23:25 - eval_codegen - INFO - Detailed results saved to: model/metrics/run1-python-codegen/detailed_results.jsonl |
| 2025-11-30 16:23:25 - eval_codegen - INFO - ============================================================ |
| 2025-11-30 16:23:25 - eval_codegen - INFO - EVALUATION RESULTS |
| 2025-11-30 16:23:25 - eval_codegen - INFO - ============================================================ |
| 2025-11-30 16:23:25 - eval_codegen - INFO - n: 19427 |
| 2025-11-30 16:23:25 - eval_codegen - INFO - exact_match: 0.3559 |
| 2025-11-30 16:23:25 - eval_codegen - INFO - exact_match_case_insensitive: 0.3607 |
| 2025-11-30 16:23:25 - eval_codegen - INFO - topk_accuracy: 0.4397 |
| 2025-11-30 16:23:25 - eval_codegen - INFO - avg_levenshtein: 8.0773 |
| 2025-11-30 16:23:25 - eval_codegen - INFO - k: 5 |
| 2025-11-30 16:23:25 - eval_codegen - INFO - device: cuda |
| 2025-11-30 16:23:25 - eval_codegen - INFO - batch_size: 8 |
| 2025-11-30 16:23:25 - eval_codegen - INFO - elapsed_time_seconds: 4201.1572 |
| 2025-11-30 16:23:25 - eval_codegen - INFO - samples_per_second: 4.6242 |
| 2025-11-30 16:23:25 - eval_codegen - INFO - Total evaluation time: 4201.16 seconds (70.02 minutes) |
|
|
