Upload training/manifest_qwen38.json with huggingface_hub
Browse files
training/manifest_qwen38.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"python": "3.12.13 (main, Mar 4 2026, 09:23:07) [GCC 11.4.0]",
|
| 3 |
+
"platform": "Linux-6.12.90+-x86_64-with-glibc2.35",
|
| 4 |
+
"torch": "2.10.0+cu128",
|
| 5 |
+
"cuda": "12.8",
|
| 6 |
+
"gpu_count": 2,
|
| 7 |
+
"gpu_list": [
|
| 8 |
+
"Tesla T4",
|
| 9 |
+
"Tesla T4"
|
| 10 |
+
],
|
| 11 |
+
"total_vram_gib": 29.12,
|
| 12 |
+
"model_id": "unsloth/Qwen3.8-27B-unsloth-bnb-4bit",
|
| 13 |
+
"model_revision": "8aa5f05d26b7205477066e1449e0af13f762a299",
|
| 14 |
+
"upstream_model": "Qwen/Qwen3.8-27B",
|
| 15 |
+
"upstream_revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0",
|
| 16 |
+
"output_repo": "TheCoderScientist/GarudaCoder-Qwen3.8-27B-ID-lora",
|
| 17 |
+
"dataset_sha256": {
|
| 18 |
+
"dataset_distilasi_fable.jsonl": "e66c27ca1f1712e68954299be3576c46aa49d02506754cf82f18c2f85e0b9166",
|
| 19 |
+
"dataset_penguatan_batch8.jsonl": "2a6128be1c6a636b52b7c7e5e51490f35d2c87b0f625923e29ba35e486a057d5",
|
| 20 |
+
"dataset_reasoning_batch9.jsonl": "7c630be167454f9bf9559b4a83c470877385f37a8bf369b0cad5207ca6bd5880",
|
| 21 |
+
"hermes_debugging.jsonl": "a2d1d80627d1f83e6f1be9e686ac31c25abc7e40b45ab3f23b94fe136471b7ba",
|
| 22 |
+
"hermes_grounding.jsonl": "169d7373afff7c682e5bd9ccbcf0c73d5b2db992b7daebff0c522635eb6c3a7b",
|
| 23 |
+
"hermes_architecture.jsonl": "0c2d46359536ec342c19944e5ec496684ca88f6512faea49be4b893dd9783127",
|
| 24 |
+
"hermes_edge_indonesia.jsonl": "d53fbae6c3908c7614405a64ba2d51881af1784a3bcdeb33874339a6e95547b0",
|
| 25 |
+
"holdout_garudacoder_qwen38.jsonl": "b1482eeda298818f4af3c054d49b61bbb83d745409426f442d5f72cba1537940"
|
| 26 |
+
},
|
| 27 |
+
"system_prompt": "Kamu adalah GarudaCoder, asisten coding berbahasa Indonesia yang teliti. Utamakan kebenaran teknis dan kode yang dapat diuji. Jelaskan ringkasan alasan yang dapat diaudit sebelum solusi, nyatakan asumsi dan edge case yang relevan, dan jangan mengarang fakta, API, versi, atau angka. Jika informasi tidak cukup, ajukan pertanyaan klarifikasi. Untuk informasi yang berubah atau bersifat lokal, minta atau gunakan sumber yang dapat diverifikasi. Tolak praktik berbahaya dan tawarkan alternatif yang aman. Jangan tampilkan chain-of-thought privat.",
|
| 28 |
+
"generation_config": {
|
| 29 |
+
"max_new_tokens": 1024,
|
| 30 |
+
"do_sample": true,
|
| 31 |
+
"temperature": 0.7,
|
| 32 |
+
"top_p": 0.8,
|
| 33 |
+
"top_k": 20,
|
| 34 |
+
"repetition_penalty": 1.0
|
| 35 |
+
},
|
| 36 |
+
"seed": 42,
|
| 37 |
+
"max_seq_length": 1024,
|
| 38 |
+
"lora_r": 8,
|
| 39 |
+
"lora_alpha": 8,
|
| 40 |
+
"training_examples": 229,
|
| 41 |
+
"holdout_examples": 80,
|
| 42 |
+
"environment": "kaggle-t4x2"
|
| 43 |
+
}
|