Instructions to use prometheus04/qwen3-4b-thinking-microagent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use prometheus04/qwen3-4b-thinking-microagent with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Upload data/pipeline_v2_log.txt with huggingface_hub
Browse files- data/pipeline_v2_log.txt +133 -0
data/pipeline_v2_log.txt
ADDED
|
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
--- streaming: skill_based_easy ---
|
| 3 |
+
skill_based_easy: scanned= 2000 accepted= 284 (14.2%)
|
| 4 |
+
skill_based_easy: scanned= 4000 accepted= 562 (14.1%)
|
| 5 |
+
skill_based_easy: scanned= 6000 accepted= 860 (14.3%)
|
| 6 |
+
skill_based_easy: scanned= 8000 accepted= 1172 (14.6%)
|
| 7 |
+
skill_based_easy: scanned= 10000 accepted= 1471 (14.7%)
|
| 8 |
+
skill_based_easy: scanned= 12000 accepted= 1755 (14.6%)
|
| 9 |
+
skill_based_easy: scanned= 14000 accepted= 2063 (14.7%)
|
| 10 |
+
skill_based_easy: scanned= 16000 accepted= 2273 (14.2%)
|
| 11 |
+
skill_based_easy: scanned= 18000 accepted= 2398 (13.3%)
|
| 12 |
+
skill_based_easy: scanned= 20000 accepted= 2541 (12.7%)
|
| 13 |
+
skill_based_easy: scanned= 22000 accepted= 2742 (12.5%)
|
| 14 |
+
skill_based_easy: scanned= 24000 accepted= 2928 (12.2%)
|
| 15 |
+
skill_based_easy: scanned= 26000 accepted= 3139 (12.1%)
|
| 16 |
+
skill_based_easy: scanned= 28000 accepted= 3385 (12.1%)
|
| 17 |
+
skill_based_easy: scanned= 30000 accepted= 3612 (12.0%)
|
| 18 |
+
skill_based_easy: scanned= 32000 accepted= 3759 (11.7%)
|
| 19 |
+
skill_based_easy: scanned= 34000 accepted= 3893 (11.5%)
|
| 20 |
+
skill_based_easy: scanned= 36000 accepted= 4052 (11.3%)
|
| 21 |
+
skill_based_easy: scanned= 38000 accepted= 4192 (11.0%)
|
| 22 |
+
skill_based_easy: scanned= 40000 accepted= 4337 (10.8%)
|
| 23 |
+
skill_based_easy: scanned= 42000 accepted= 4521 (10.8%)
|
| 24 |
+
skill_based_easy: scanned= 44000 accepted= 4718 (10.7%)
|
| 25 |
+
skill_based_easy: DONE scanned=44809 accepted=4804 (10.7%)
|
| 26 |
+
|
| 27 |
+
--- streaming: skill_based_medium ---
|
| 28 |
+
skill_based_medium: scanned= 2000 accepted= 84 (4.2%)
|
| 29 |
+
skill_based_medium: scanned= 4000 accepted= 185 (4.6%)
|
| 30 |
+
skill_based_medium: scanned= 6000 accepted= 308 (5.1%)
|
| 31 |
+
skill_based_medium: scanned= 8000 accepted= 420 (5.2%)
|
| 32 |
+
skill_based_medium: scanned= 10000 accepted= 642 (6.4%)
|
| 33 |
+
skill_based_medium: scanned= 12000 accepted= 848 (7.1%)
|
| 34 |
+
skill_based_medium: scanned= 14000 accepted= 1008 (7.2%)
|
| 35 |
+
skill_based_medium: scanned= 16000 accepted= 1157 (7.2%)
|
| 36 |
+
skill_based_medium: scanned= 18000 accepted= 1318 (7.3%)
|
| 37 |
+
skill_based_medium: scanned= 20000 accepted= 1456 (7.3%)
|
| 38 |
+
skill_based_medium: scanned= 22000 accepted= 1553 (7.1%)
|
| 39 |
+
skill_based_medium: scanned= 24000 accepted= 1656 (6.9%)
|
| 40 |
+
skill_based_medium: scanned= 26000 accepted= 1717 (6.6%)
|
| 41 |
+
skill_based_medium: scanned= 28000 accepted= 1757 (6.3%)
|
| 42 |
+
skill_based_medium: scanned= 30000 accepted= 1819 (6.1%)
|
| 43 |
+
skill_based_medium: scanned= 32000 accepted= 1974 (6.2%)
|
| 44 |
+
skill_based_medium: scanned= 34000 accepted= 2238 (6.6%)
|
| 45 |
+
skill_based_medium: scanned= 36000 accepted= 2467 (6.9%)
|
| 46 |
+
skill_based_medium: scanned= 38000 accepted= 2594 (6.8%)
|
| 47 |
+
skill_based_medium: scanned= 40000 accepted= 2728 (6.8%)
|
| 48 |
+
skill_based_medium: scanned= 42000 accepted= 2866 (6.8%)
|
| 49 |
+
skill_based_medium: scanned= 44000 accepted= 3045 (6.9%)
|
| 50 |
+
skill_based_medium: scanned= 46000 accepted= 3207 (7.0%)
|
| 51 |
+
skill_based_medium: scanned= 48000 accepted= 3327 (6.9%)
|
| 52 |
+
skill_based_medium: scanned= 50000 accepted= 3413 (6.8%)
|
| 53 |
+
skill_based_medium: scanned= 52000 accepted= 3513 (6.8%)
|
| 54 |
+
skill_based_medium: scanned= 54000 accepted= 3623 (6.7%)
|
| 55 |
+
skill_based_medium: scanned= 56000 accepted= 3737 (6.7%)
|
| 56 |
+
skill_based_medium: scanned= 58000 accepted= 3854 (6.6%)
|
| 57 |
+
skill_based_medium: scanned= 60000 accepted= 3964 (6.6%)
|
| 58 |
+
skill_based_medium: scanned= 62000 accepted= 4025 (6.5%)
|
| 59 |
+
skill_based_medium: scanned= 64000 accepted= 4082 (6.4%)
|
| 60 |
+
skill_based_medium: scanned= 66000 accepted= 4135 (6.3%)
|
| 61 |
+
skill_based_medium: scanned= 68000 accepted= 4201 (6.2%)
|
| 62 |
+
skill_based_medium: scanned= 70000 accepted= 4249 (6.1%)
|
| 63 |
+
skill_based_medium: scanned= 72000 accepted= 4328 (6.0%)
|
| 64 |
+
skill_based_medium: scanned= 74000 accepted= 4431 (6.0%)
|
| 65 |
+
skill_based_medium: scanned= 76000 accepted= 4505 (5.9%)
|
| 66 |
+
skill_based_medium: scanned= 78000 accepted= 4562 (5.8%)
|
| 67 |
+
skill_based_medium: scanned= 80000 accepted= 4630 (5.8%)
|
| 68 |
+
skill_based_medium: scanned= 82000 accepted= 4718 (5.8%)
|
| 69 |
+
skill_based_medium: scanned= 84000 accepted= 4780 (5.7%)
|
| 70 |
+
skill_based_medium: scanned= 86000 accepted= 4831 (5.6%)
|
| 71 |
+
skill_based_medium: scanned= 88000 accepted= 4890 (5.6%)
|
| 72 |
+
skill_based_medium: DONE scanned=89343 accepted=4916 (5.5%)
|
| 73 |
+
|
| 74 |
+
--- streaming: skill_based_mixed ---
|
| 75 |
+
skill_based_mixed: scanned= 2000 accepted= 88 (4.4%)
|
| 76 |
+
skill_based_mixed: scanned= 4000 accepted= 172 (4.3%)
|
| 77 |
+
skill_based_mixed: DONE scanned=5689 accepted=191 (3.4%)
|
| 78 |
+
|
| 79 |
+
--- adapter: dataset_adapters/code.parquet ---
|
| 80 |
+
downloading dataset_adapters/code.parquet (cached if present)...
|
| 81 |
+
dataset_adapters/code.parquet: scanned= 2000 accepted= 798 (39.9%)
|
| 82 |
+
dataset_adapters/code.parquet: scanned= 4000 accepted= 1549 (38.7%)
|
| 83 |
+
dataset_adapters/code.parquet: scanned= 6000 accepted= 2303 (38.4%)
|
| 84 |
+
dataset_adapters/code.parquet: scanned= 8000 accepted= 3052 (38.1%)
|
| 85 |
+
dataset_adapters/code.parquet: scanned= 10000 accepted= 3793 (37.9%)
|
| 86 |
+
dataset_adapters/code.parquet: scanned= 12000 accepted= 4586 (38.2%)
|
| 87 |
+
dataset_adapters/code.parquet: scanned= 14000 accepted= 5381 (38.4%)
|
| 88 |
+
dataset_adapters/code.parquet: scanned= 16000 accepted= 6124 (38.3%)
|
| 89 |
+
dataset_adapters/code.parquet: scanned= 18000 accepted= 6886 (38.3%)
|
| 90 |
+
dataset_adapters/code.parquet: scanned= 20000 accepted= 7744 (38.7%)
|
| 91 |
+
dataset_adapters/code.parquet: scanned= 22000 accepted= 8596 (39.1%)
|
| 92 |
+
dataset_adapters/code.parquet: scanned= 24000 accepted= 9473 (39.5%)
|
| 93 |
+
dataset_adapters/code.parquet: scanned= 26000 accepted= 10339 (39.8%)
|
| 94 |
+
dataset_adapters/code.parquet: scanned= 28000 accepted= 11184 (39.9%)
|
| 95 |
+
dataset_adapters/code.parquet: scanned= 30000 accepted= 12050 (40.2%)
|
| 96 |
+
dataset_adapters/code.parquet: DONE scanned=31960 accepted=12875 (40.3%)
|
| 97 |
+
|
| 98 |
+
--- adapter: dataset_adapters/swe.parquet ---
|
| 99 |
+
downloading dataset_adapters/swe.parquet (cached if present)...
|
| 100 |
+
dataset_adapters/swe.parquet: scanned= 2000 accepted= 207 (10.3%)
|
| 101 |
+
dataset_adapters/swe.parquet: scanned= 4000 accepted= 415 (10.4%)
|
| 102 |
+
dataset_adapters/swe.parquet: scanned= 6000 accepted= 625 (10.4%)
|
| 103 |
+
dataset_adapters/swe.parquet: scanned= 8000 accepted= 834 (10.4%)
|
| 104 |
+
dataset_adapters/swe.parquet: scanned= 10000 accepted= 1017 (10.2%)
|
| 105 |
+
dataset_adapters/swe.parquet: scanned= 12000 accepted= 1291 (10.8%)
|
| 106 |
+
dataset_adapters/swe.parquet: scanned= 14000 accepted= 1526 (10.9%)
|
| 107 |
+
dataset_adapters/swe.parquet: scanned= 16000 accepted= 1791 (11.2%)
|
| 108 |
+
dataset_adapters/swe.parquet: scanned= 18000 accepted= 2067 (11.5%)
|
| 109 |
+
dataset_adapters/swe.parquet: scanned= 20000 accepted= 2325 (11.6%)
|
| 110 |
+
dataset_adapters/swe.parquet: scanned= 22000 accepted= 2590 (11.8%)
|
| 111 |
+
dataset_adapters/swe.parquet: scanned= 24000 accepted= 2823 (11.8%)
|
| 112 |
+
dataset_adapters/swe.parquet: scanned= 26000 accepted= 3087 (11.9%)
|
| 113 |
+
dataset_adapters/swe.parquet: scanned= 28000 accepted= 3337 (11.9%)
|
| 114 |
+
dataset_adapters/swe.parquet: scanned= 30000 accepted= 3614 (12.0%)
|
| 115 |
+
dataset_adapters/swe.parquet: DONE scanned=31661 accepted=3841 (12.1%)
|
| 116 |
+
|
| 117 |
+
|
| 118 |
+
========== FINAL ==========
|
| 119 |
+
Output: data\microagent_train_v2.jsonl
|
| 120 |
+
Total scanned : 203462
|
| 121 |
+
Total accepted: 26627 (13.1%)
|
| 122 |
+
|
| 123 |
+
Per-source accepted:
|
| 124 |
+
dataset_adapters/code.parquet 12875 / 31960 ( 40.3%)
|
| 125 |
+
skill_based_medium 4916 / 89343 ( 5.5%)
|
| 126 |
+
skill_based_easy 4804 / 44809 ( 10.7%)
|
| 127 |
+
dataset_adapters/swe.parquet 3841 / 31661 ( 12.1%)
|
| 128 |
+
skill_based_mixed 191 / 5689 ( 3.4%)
|
| 129 |
+
|
| 130 |
+
Code (v2) breakdown:
|
| 131 |
+
success/<finish>: 11529
|
| 132 |
+
give_up: 1346
|
| 133 |
+
rejected reasons: too_few=487 too_many=103 early_parse_err=20 json_unrecoverable=15833 no_real_attempt=2642 per_task_cap=0
|