A/B ab_rsloRa0: kaggle_output.json

ab_rsloRa0/kaggle_output.json

@@ -0,0 +1,47 @@
+{
+  "status": "Auftrag/unverifiziert-lokal",
+  "note": "Erzeugt auf Kaggle GPU. Adapter muss vom Menschen zurueckgegeben werden.",
+  "base_model": "Qwen/Qwen2.5-3B-Instruct",
+  "adapter_path": "/kaggle/working/ab_rsloRa0/adapter",
+  "output_json": "/kaggle/working/ab_rsloRa0/kaggle_output.json",
+  "loss": 1.310697078704834,
+  "sft_source": "local",
+  "source_note": "M1 consolidation_sft.jsonl (lokal, §10.3)",
+  "dataset": "consolidation_sft.jsonl",
+  "dataset_path": "/kaggle/working/ds15.jsonl",
+  "dataset_hash_sha256": "18caaae7c6f7f506a0cdd132d15f23c0e7044b07d894b73eb68b302605b01c7c",
+  "dataset_split": null,
+  "dataset_requested": null,
+  "dataset_rows_scanned": 15,
+  "dataset_skipped_empty": null,
+  "dataset_row_hash_count": 15,
+  "dataset_row_hash_aggregate_sha256": "8d42c0dab6e5face548ef0df46c1b2b64fb809f05ea395db72d4e6bf4d108ef4",
+  "dataset_rows": 15,
+  "seed": 42,
+  "num_train_epochs": 15.0,
+  "max_length": 1024,
+  "learning_rate": 0.0002,
+  "lora_r": 64,
+  "lora_alpha": 256,
+  "lora_use_rslora": false,
+  "lora_plus_ratio": 0.0,
+  "full_ft": false,
+  "compute_dtype": "float16",
+  "amp": "disabled (fp16=False, bf16=False)",
+  "compute_capability": "sm_75",
+  "model_init_dtype": "float16",
+  "gpu": "Tesla T4",
+  "started_utc": "2026-10-22T06:47:42Z",
+  "finished_utc": "2026-10-22T06:50:37Z",
+  "library_versions": {
+    "transformers": "5.16.1",
+    "peft": "0.20.0",
+    "trl": "1.16.0",
+    "bitsandbytes": "0.50.2",
+    "datasets": "4.8.5",
+    "accelerate": "1.14.0",
+    "torch": "2.11.0+cu128"
+  },
+  "python": "3.13.15",
+  "source": "AGENTS.md §10.3 · arXiv:2608.22215 §3.4"
+}