File size: 1,533 Bytes
53f3a25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
{
  "status": "Auftrag/unverifiziert-lokal",
  "note": "Erzeugt auf Kaggle GPU. Adapter muss vom Menschen zurueckgegeben werden.",
  "base_model": "Qwen/Qwen2.5-0.5B-Instruct",
  "adapter_path": "/kaggle/working/adapter",
  "output_json": "/kaggle/working/kaggle_output.json",
  "loss": 0.5733484268188477,
  "sft_source": "local",
  "source_note": "M1 consolidation_sft.jsonl (lokal, §10.3)",
  "dataset": "consolidation_sft.jsonl",
  "dataset_path": "/kaggle/working/train_f6.jsonl",
  "dataset_hash_sha256": "90d467e96fbeca1dffbbd5dc2fdb51efd041fd67da1b5347c9977abcac88e00b",
  "dataset_split": null,
  "dataset_requested": null,
  "dataset_rows_scanned": 50000,
  "dataset_skipped_empty": null,
  "dataset_row_hash_count": 50000,
  "dataset_row_hash_aggregate_sha256": "253f64e2574138a2043d5b1cb2d1bf7d797f67f523b79699834dc1c1fb369816",
  "dataset_rows": 50000,
  "seed": 42,
  "num_train_epochs": 3.0,
  "max_length": 1024,
  "learning_rate": 0.0002,
  "lora_r": 16,
  "lora_alpha": 32,
  "compute_dtype": "float16",
  "amp": "disabled (fp16=False, bf16=False)",
  "compute_capability": "sm_75",
  "model_init_dtype": "float16",
  "gpu": "Tesla T4",
  "started_utc": "2026-10-10T12:33:09Z",
  "finished_utc": "2026-10-10T17:16:07Z",
  "library_versions": {
    "transformers": "5.16.1",
    "peft": "0.20.0",
    "trl": "1.15.0",
    "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"
}