Upload logs/eval_codegen_20251201_111346.log with huggingface_hub
Browse files
logs/eval_codegen_20251201_111346.log
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - Logging to: logs/codegen/eval_codegen_20251201_111346.log
|
| 2 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - Monitor progress: tail -f logs/codegen/eval_codegen_20251201_111346.log
|
| 3 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - ============================================================
|
| 4 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - CodeGen Evaluation
|
| 5 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - ============================================================
|
| 6 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - Using GPU: NVIDIA GeForce RTX 5090
|
| 7 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - Configuration:
|
| 8 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - checkpoint: model/checkpoints/run1-csharp-codegen
|
| 9 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - data: datasets/csharp
|
| 10 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - k: 5
|
| 11 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - batch_size: 8
|
| 12 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - device: cuda
|
| 13 |
+
2025-12-01 11:13:46 - eval_codegen - INFO - Loading model from model/checkpoints/run1-csharp-codegen...
|
| 14 |
+
2025-12-01 11:13:47 - eval_codegen - INFO - Model loaded and set to eval mode
|
| 15 |
+
2025-12-01 11:13:47 - eval_codegen - INFO - Loaded 28328 test examples
|
| 16 |
+
2025-12-01 11:13:47 - eval_codegen - INFO - Starting evaluation with batch_size=8, k=5
|
| 17 |
+
2025-12-01 11:13:47 - eval_codegen - INFO - Total batches: 3541
|
| 18 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - Evaluation completed in 6239.73 seconds
|
| 19 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - Average speed: 4.54 samples/second
|
| 20 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - Metrics saved to: model/metrics/run1-csharp-codegen/metrics.json
|
| 21 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - Detailed results saved to: model/metrics/run1-csharp-codegen/detailed_results.jsonl
|
| 22 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - ============================================================
|
| 23 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - EVALUATION RESULTS
|
| 24 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - ============================================================
|
| 25 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - n: 28328
|
| 26 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - exact_match: 0.4854
|
| 27 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - exact_match_case_insensitive: 0.4861
|
| 28 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - topk_accuracy: 0.5551
|
| 29 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - avg_levenshtein: 7.1740
|
| 30 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - k: 5
|
| 31 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - device: cuda
|
| 32 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - batch_size: 8
|
| 33 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - elapsed_time_seconds: 6239.7305
|
| 34 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - samples_per_second: 4.5399
|
| 35 |
+
2025-12-01 12:57:46 - eval_codegen - INFO - Total evaluation time: 6239.73 seconds (104.00 minutes)
|