| { | |
| "encoder": "answerdotai/ModernBERT-large", | |
| "head_layers": 2, | |
| "max_len": 512, | |
| "head_max_len": 192, | |
| "max_prefixes": 6, | |
| "act_costs": { | |
| "escalate": 0.5 | |
| }, | |
| "cost_wrong_act": 3.0, | |
| "amp_dtype": "bf16", | |
| "model_name": "laya-code", | |
| "temperature": [ | |
| 1.6369030475616455, | |
| 1.2514300346374512, | |
| 0.9409746926053619 | |
| ], | |
| "temperature_by_options": { | |
| "choice:3-5": 1.7601518630981445, | |
| "choice:6-10": 1.0000158548355103, | |
| "score:3-5": 1.2514300346374512, | |
| "noul:2": 0.9409746926053619, | |
| "choice:11+": 0.10058280825614929, | |
| "choice:2": 1.9063563346862793 | |
| }, | |
| "training": { | |
| "updates": 7313, | |
| "epochs_completed": 1, | |
| "hours": 1.96, | |
| "world_size": 1, | |
| "fine_tuned_from_checkpoint": true | |
| }, | |
| "finetune": { | |
| "base": "laya-base (convaiinnovations/laya)", | |
| "task": "code relevance (noul)", | |
| "noul_temperature_fit": { | |
| "split": "val", | |
| "before": { | |
| "T": 1.9834, | |
| "nll": 0.5774, | |
| "ece_hard": 0.1673, | |
| "auroc_pos_vs_neg": 0.7045, | |
| "mean_p": 0.3733, | |
| "base_rate": 0.2741, | |
| "prec_at_p>=0.5_hard": 0.3333, | |
| "n": 5136 | |
| }, | |
| "after": { | |
| "T": 0.941, | |
| "nll": 0.5421, | |
| "ece_hard": 0.0578, | |
| "auroc_pos_vs_neg": 0.7045, | |
| "mean_p": 0.2681, | |
| "base_rate": 0.2741, | |
| "prec_at_p>=0.5_hard": 0.3333, | |
| "n": 5136 | |
| } | |
| } | |
| } | |
| } |