| { | |
| "model": { | |
| "encoder_name": "answerdotai/ModernBERT-large", | |
| "head_layers": 2, | |
| "head_dropout": 0.1, | |
| "num_qtypes": 3, | |
| "cls_query": false, | |
| "slot_emb": false, | |
| "max_len": 1024, | |
| "head_max_len": 256, | |
| "k_buckets": [ | |
| 2, | |
| 5, | |
| 10 | |
| ] | |
| }, | |
| "training": { | |
| "dataset_name": "LocalLLaMA/typed-decisions", | |
| "dataset_config": "all", | |
| "calib_fraction": 0.1, | |
| "seed": 42, | |
| "max_examples": null, | |
| "augment_permute": false, | |
| "ckpt_dir": "checkpoints", | |
| "result_dir": "results", | |
| "run_name": "e2_ce_only_1024_seed42", | |
| "epochs": 4, | |
| "batch_size": 4, | |
| "accum_steps": 16, | |
| "num_workers": 4, | |
| "pin_memory": true, | |
| "amp": true, | |
| "amp_dtype": "bf16", | |
| "gradient_checkpointing": true, | |
| "lr": 2.5e-05, | |
| "lr_head": 0.0001, | |
| "weight_decay": 0.01, | |
| "grad_clip": 1.0, | |
| "log_every": 10, | |
| "eval_every": 1, | |
| "ckpt_every": 4, | |
| "w_rl": 0.0, | |
| "w_ce": 1.0, | |
| "num_noise_samples": 4, | |
| "sigma_start": 0.4, | |
| "sigma_end": 0.1, | |
| "anneal_sigma": true, | |
| "reward_w_spherical": 0.75, | |
| "reward_w_rps": 1.0, | |
| "arch": { | |
| "encoder_name": "answerdotai/ModernBERT-large", | |
| "head_layers": 2, | |
| "max_len": 1024, | |
| "head_max_len": 256 | |
| }, | |
| "init_from": "convaiinnovations/laya", | |
| "log_grad_diagnostics": true, | |
| "lr_scheduler": { | |
| "type": "cosine", | |
| "t_max": "auto", | |
| "eta_min": 1e-06 | |
| }, | |
| "early_stopping": { | |
| "enabled": false | |
| }, | |
| "save_best": false, | |
| "best_metric": "raw_ece", | |
| "best_mode": "min", | |
| "wandb": { | |
| "enabled": true, | |
| "project": "rlcd-reverse-engineering", | |
| "entity": null, | |
| "group": "e2-acc", | |
| "log_artifacts": false | |
| }, | |
| "resume_from": null | |
| } | |
| } |