sparrow8i8 commited on
Commit
9902de5
·
verified ·
1 Parent(s): 535de57

add run_manifest.json

Browse files
Files changed (1) hide show
  1. run_manifest.json +86 -0
run_manifest.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "run_name": "qwen-compassion-part1",
3
+ "git_sha": "6950fbbc6f29902d7fc5b26c1aef8d053966e9a3",
4
+ "argv": [
5
+ "pilot/train_unsloth.py",
6
+ "--data",
7
+ "/workspace/anchor/qwen-compassion/train_qwen-compassion_replay50.jsonl",
8
+ "--base-model",
9
+ "CompassioninMachineLearning/Qwen3-8b-compassion-cleaned-10k-CPT-best-step750",
10
+ "--no-4bit",
11
+ "--lora-r",
12
+ "64",
13
+ "--lora-alpha",
14
+ "128",
15
+ "--seed",
16
+ "7",
17
+ "--epochs",
18
+ "1",
19
+ "--eval-steps",
20
+ "50",
21
+ "--early-stopping-patience",
22
+ "2",
23
+ "--snapshot-frac",
24
+ "0",
25
+ "--replay-chat",
26
+ "--replay-token-frac",
27
+ "0.25",
28
+ "--run-name",
29
+ "qwen-compassion-part1",
30
+ "--push-to-hub-merged",
31
+ "CompassioninMachineLearning/qwen-compassion-part1-build",
32
+ "--output-dir",
33
+ "/workspace/anchor/qwen-compassion/train"
34
+ ],
35
+ "base_model": "CompassioninMachineLearning/Qwen3-8b-compassion-cleaned-10k-CPT-best-step750",
36
+ "template_source": "CompassioninMachineLearning/Qwen3-8b-compassion-cleaned-10k-CPT-best-step750",
37
+ "modules_to_save": [
38
+ "embed_tokens",
39
+ "lm_head"
40
+ ],
41
+ "data_files": [
42
+ "/workspace/anchor/qwen-compassion/train_qwen-compassion_replay50.jsonl"
43
+ ],
44
+ "data_sha256": {
45
+ "/workspace/anchor/qwen-compassion/train_qwen-compassion_replay50.jsonl": "1f22b1da2039471bb1932e866f1a1138a08f3e8c1eee8e94dfb2dc19a3b9b2e8"
46
+ },
47
+ "rows_raw": 18500,
48
+ "rows_kept": 10076,
49
+ "by_source": {
50
+ "replay:compassion_12185_cleaned": 1259,
51
+ "recovery": 3750,
52
+ "apigen": 4567,
53
+ "efficiency": 500
54
+ },
55
+ "train_examples": 9824,
56
+ "eval_examples": 252,
57
+ "hyperparams": {
58
+ "lora_r": 64,
59
+ "lora_alpha": 128,
60
+ "lora_dropout": 0.05,
61
+ "lr_adapters": 0.0002,
62
+ "lr_embeddings": 2e-05,
63
+ "epochs": 1.0,
64
+ "max_steps": -1,
65
+ "max_seq_len": 8192,
66
+ "effective_batch": 16,
67
+ "per_device_batch": 2,
68
+ "grad_accum": 8,
69
+ "warmup_ratio": 0.05,
70
+ "schedule": "cosine",
71
+ "seed": 7,
72
+ "snapshot_frac": 0.0
73
+ },
74
+ "versions": {
75
+ "torch": "2.11.0+cu128",
76
+ "transformers": "4.57.6",
77
+ "unsloth": "2026.9.2",
78
+ "trl": "0.22.2",
79
+ "datasets": "5.0.1",
80
+ "peft": "0.20.0",
81
+ "accelerate": "1.14.0",
82
+ "bitsandbytes": "0.50.2"
83
+ },
84
+ "gpu": "NVIDIA H100 NVL",
85
+ "started_at": "2026-10-11T23:26:44Z"
86
+ }