Arbiter-8B / metadata.json
jsemrau's picture
Arbiter v0.5: replace v0.4 (merged model, new GGUFs, new model card)
baa22fe verified
Raw History Blame Contribute Delete
4.41 kB
{
"base_model": "Qwen/Qwen3-8B",
"quantization": "4bit",
"max_length": 4096,
"softcap": null,
"recipe": {
"data": [
"pilot_decisions.jsonl",
"sentinel_decisions.jsonl",
"filing_decisions.jsonl",
"teacher_decisions.jsonl",
"filing_teacher_decisions.jsonl",
"teacher_outlook_decisions.jsonl",
"v5_edt_decisions.jsonl",
"v5_fomc_decisions.jsonl",
"v5_sentiment_decisions.jsonl"
],
"base_model": "Qwen/Qwen3-8B",
"include_teacher": true,
"mix": "news:type=0.150,news:certainty=0.100,news:outlook=0.082,news:main=0.054,news:role=0.020,filing:risk=0.082,filing:outlook=0.061,filing:legal=0.054,filing:going_concern=0.008,filing:customer=0.014,filing:cyber=0.020,human=0.040,news:edt_orig=0.045,news:edt_tight=0.045,news:edt_contrast=0.030,news:edt_hardnone=0.030,news:fomc_orig=0.030,news:fomc_tight=0.030,news:senti_single_implied=0.025,news:senti_single_stated=0.030,news:senti_multi_implied=0.025,news:senti_multi_stated=0.025",
"mix_by": "question",
"quantization": "4bit",
"minimum_train": 100,
"minimum_dev": 20,
"lora_rank": 32,
"lora_alpha": 64,
"lora_lr": 2e-05,
"head_lr": 0.0001,
"micro_batch": 1,
"grad_accum": 16,
"epochs": 3.0,
"steps": 2400,
"max_length": 4096,
"max_grad_norm": 1.0,
"stats_rows": 512,
"log_every": 5,
"eval_every": 400,
"seed": 1,
"label_smoothing": 0.05
},
"steps": 2400,
"train_rows": 140705,
"dev_rows": 151,
"dev_zero_shot": {
"accuracy": 0.7218543046357616,
"nll": 3.117936041840196,
"count": 151
},
"dev_final": {
"accuracy": 0.8410596026490066,
"nll": 0.4121556690861687,
"count": 151
},
"fallback_counts": {
"excluded_train_provisional": 401,
"train_teacher_rows_used": 140599,
"excluded_dev_provisional": 13,
"excluded_dev_rejected": 1,
"excluded_dev_teacher": 2322,
"float16_no_bf16_device": 1,
"flash_sdp_disabled_pre_ampere_gpu": 1,
"dev_state_truncated": 0,
"mix_news:type_passes_started": 1,
"mix_news:type_draws": 5733,
"soft_target_presentations": 29233,
"mix_news:fomc_tight_passes_started": 1,
"mix_news:fomc_tight_draws": 1140,
"label_smoothed_presentations": 9167,
"mix_news:edt_orig_passes_started": 1,
"mix_news:edt_orig_draws": 1771,
"mix_filing:risk_passes_started": 1,
"mix_filing:risk_draws": 3211,
"mix_news:outlook_passes_started": 1,
"mix_news:outlook_draws": 3199,
"mix_filing:outlook_passes_started": 1,
"mix_filing:outlook_draws": 2358,
"mix_news:certainty_passes_started": 1,
"mix_news:certainty_draws": 3879,
"mix_news:fomc_orig_passes_started": 1,
"mix_news:fomc_orig_draws": 1186,
"mix_news:edt_contrast_passes_started": 2,
"mix_news:edt_contrast_draws": 1123,
"mix_news:senti_single_implied_passes_started": 1,
"mix_news:senti_single_implied_draws": 941,
"mix_filing:legal_passes_started": 2,
"mix_filing:legal_draws": 2049,
"mix_news:main_passes_started": 1,
"mix_news:main_draws": 1995,
"mix_news:edt_tight_passes_started": 1,
"mix_news:edt_tight_draws": 1754,
"mix_filing:cyber_passes_started": 1,
"mix_filing:cyber_draws": 706,
"mix_news:senti_single_stated_passes_started": 1,
"mix_news:senti_single_stated_draws": 1138,
"mix_human_passes_started": 15,
"mix_human_draws": 1511,
"mix_news:senti_multi_stated_passes_started": 1,
"mix_news:senti_multi_stated_draws": 935,
"mix_news:role_passes_started": 1,
"mix_news:role_draws": 741,
"mix_news:senti_multi_implied_passes_started": 1,
"mix_news:senti_multi_implied_draws": 970,
"mix_filing:customer_passes_started": 2,
"mix_filing:customer_draws": 532,
"mix_filing:going_concern_passes_started": 2,
"mix_filing:going_concern_draws": 306,
"mix_news:edt_hardnone_passes_started": 1,
"mix_news:edt_hardnone_draws": 1222
},
"version": "Arbiter v0.5",
"training_data": "100,000 news + 11,752 SEC 10-K + 8,000 news-outlook decisions labelled by a local Qwen3.8-27B teacher; 10,300 headline-sentiment decisions labelled by the same teacher; 9,033 EDT and 3,836 FOMC training-split decisions with their published labels (original and tightened definitions, contrast pairs, hard 'none' examples); 106 human-reviewed 10-K decisions. SEntFiN was never trained on.",
"layout": {
"full_model": "root (LoRA merged into Qwen3-8B with its decoder weights round-tripped through NF4, as in training; fp16 safetensors)",
"adapter": "adapter/ (LoRA for Qwen/Qwen3-8B, trained with 4-bit QLoRA)"
}
}