| ---
|
|
|
| license: other
|
|
|
| license_name: s2-mas-controlled-research-v1.2
|
|
|
| license_link: https://huggingface.co/ya9919/laya-finance-matched-sft-rlcd-50k/blob/main/LICENSE
|
|
|
| language:
|
|
|
| - en
|
|
|
| base_model: ya9919/laya-finance-matched-sft-50k
|
|
|
| tags:
|
|
|
| - s2-mas
|
|
|
| - financial-qa
|
|
|
| - decision-head
|
|
|
| - laya
|
|
|
| ---
|
|
|
| # laya-finance-matched-sft-rlcd-50k
|
|
|
| Paper: [S²-MAS](https://github.com/KataDavidXD/s2-mas/blob/main/paper/S2_MAS_Paper.pdf). The fixed-budget adaptation results and matched downstream methods define the comparison reported here.
|
|
|
| ## Project background
|
|
|
| S²-MAS is a society-scale multi-agent simulation framework for studying how household decisions affect consumption, cash reserves and payments. The paper connects a constructed resource of **500 million household-persona records**, learned decision policies, reusable financial scenarios and a state-transition engine. Its purchase-funding application evaluates **12 million distinct synthetic household agents** under paired conditions. Full-data Fin-Laya supplies the policy for that application; this repository supplies a fixed-budget adaptation checkpoint for the common decision-model comparison. Decision learning uses **real-survey data**. The GENESE/MAS engine implementation remains private.
|
|
|
| The benchmark groups twelve systems into six decision-model routes: encoder option scoring; language models with learned decision heads; next-token decision SFT; dynamic-schema classification; multimodal encoder decisions; and provider decision interfaces. All receive text inputs in the common benchmark. The **17 model-repository entries** comprise **10 fixed-budget trained variants**—five native Laya and five Qwen variants—plus **six checkpoint/runtime entries** and **one compatibility alias**.
|
|
|
| <!-- consumptionqa-examples:start -->
|
| ## Test-set QA examples
|
|
|
| These four QA excerpts come from the existing held-out consumer financial-choice test set. They retain the original English questions, candidate menus and recorded reference answers. Full household states and original identifiers are omitted. The answers belong to the households in the original records; provide a household state when running inference.
|
|
|
| [Download the examples as JSON](qa_examples.json).
|
|
|
| ### 1. Active credit-card use
|
|
|
| Does your household use credit cards? Exclude cards that have not been activated.
|
|
|
| - `1` — Yes
|
| - `2` — No
|
|
|
| **Recorded reference answer:** `2` — No
|
|
|
| ### 2. Demand-deposit account
|
|
|
| Does your household currently have a renminbi demand-deposit account?
|
|
|
| - `1` — Yes
|
| - `2` — No
|
|
|
| **Recorded reference answer:** `1` — Yes
|
|
|
| ### 3. Stock trading account
|
|
|
| Does your household currently have a stock trading account?
|
|
|
| - `1` — Yes
|
| - `2` — No
|
|
|
| **Recorded reference answer:** `2` — No
|
|
|
| ### 4. Unmatured time deposits
|
|
|
| Does your household currently have any renminbi time deposits that have not yet matured?
|
|
|
| - `1` — Yes
|
| - `2` — No
|
|
|
| **Recorded reference answer:** `2` — No
|
|
|
| <!-- consumptionqa-examples:end -->
|
|
|
| ## This model's role
|
|
|
| This checkpoint is an **RLCD continuation** within the encoder option-scoring route. It starts from matched SFT50 and processes the same 50k examples for an additional pass. Native RLCD combines cross-entropy with a proper-score policy-gradient term over noisy option logits.
|
|
|
| ## Training design and checkpoint
|
|
|
| - Method: **RLCD continuation from matched SFT50**.
|
|
|
| - Distinct downstream training rows: **50,000** from the fixed decision-QA training partition.
|
|
|
| - Initialization: [ya9919/laya-finance-matched-sft-50k](https://huggingface.co/ya9919/laya-finance-matched-sft-50k).
|
|
|
| - This stage terminal row exposures: **50,000**; selected checkpoint stage exposures: **50,000**.
|
|
|
| - Selected checkpoint cumulative row exposures: **100,000**; selected cumulative distinct rows: **50,000**.
|
|
|
| - A fixed **20,000-example development set** selects this checkpoint.
|
|
|
| ## Performance and matched comparisons
|
|
|
| **Language:** English. **Inference precision:** Native PyTorch BF16.
|
|
|
| The common held-out test contains **240,458 QA records**, **119 question versions** and **8,275 respondent/household groups**. The checkpoint is selected using development data before this test.
|
|
|
| | Checkpoint / reference | Accuracy (%) | Question-macro F1 (%) | Invalid decisions |
|
| |---|---:|---:|---:|
|
| | **This checkpoint** | **72.9258** | **34.7841** | **0** |
|
| | SFT50 parent | 72.6942 | 34.8511 | 0 |
|
| | Original native Laya, matched BF16 reference | 60.1972 | 29.5995 | 0 |
|
|
|
| Accuracy weights every test record equally; invalid decisions count as incorrect. Question-macro F1 averages over every defined candidate class within each question version and then weights the 119 versions equally.
|
|
|
| Against its SFT50 parent, the paper reports **+0.2316 accuracy points** (95% CI 0.1771–0.2854) and **−0.0671 question-macro F1 points** (−0.1516–0.0197).
|
|
|
| ## Package and inference
|
|
|
| Complete fine-tuned encoder and original native decision head.
|
|
|
| This stage continues the matched SFT checkpoint for one pass over the same training records.
|
|
|
| - Reported common-test inference: native BF16.
|
|
|
| - Underlying encoder: `answerdotai/ModernBERT-large`; the original two-layer Laya decision head is retained.
|
|
|
| - Inference scores the full state, question and complete candidate menu.
|
|
|
| Use the native Laya inference interface with the supplied encoder configuration, tokenizer and decision head.
|
|
|
| ## License and access
|
|
|
| The project model contribution is offered under the [S²-MAS Controlled Model Research License v1.2](LICENSE): noncommercial scientific use, no redistribution, and no unauthorized reverse engineering, extraction or distillation. Training and evaluation records are not distributed. Source-data access requires the provider's authorization. Permission requests: yli9919@hku.hk.
|
|
|
| Project repository: [s2-mas](https://github.com/KataDavidXD/s2-mas).
|
|
|
