| { |
| "head_layers": 2, |
| "max_prefixes": 6, |
| "act_costs": { |
| "escalate": 0.5 |
| }, |
| "cost_wrong_act": 3.0, |
| "encoder": "dmis-lab/UltraBERT-150M", |
| "encoder_revision": "545ac9d9c7aece444f014ada5a1e9818132b4d35", |
| "max_len": 8192, |
| "head_max_len": 192, |
| "amp_dtype": "bf16", |
| "model_name": "caldec-ultra-150m", |
| "temperature": [ |
| 1.0, |
| 1.0, |
| 1.0 |
| ], |
| "temperature_by_options": { |
| "choice:3-5": 1.3067494630813599, |
| "noul:2": 1.1769542694091797, |
| "score:3-5": 1.1716774702072144, |
| "choice:2": 1.1175421476364136 |
| }, |
| "training": { |
| "fine_tuned_from": "dmis-lab/UltraBERT-150M@545ac9d9c7aece444f014ada5a1e9818132b4d35 with a freshly initialized decision head", |
| "base_revision": "545ac9d9c7aece444f014ada5a1e9818132b4d35", |
| "epochs_completed": 6, |
| "selected_epoch": 6, |
| "updates": 3353, |
| "lr_encoder": 1e-05, |
| "lr_head": 0.0001, |
| "schedule": "linear", |
| "decisions": 9001, |
| "seconds": 2066, |
| "legacy_drop_tail": false, |
| "objective": "soft cross-entropy", |
| "with_public": true, |
| "balance_sites": true, |
| "seed": 20260924, |
| "packed": true, |
| "max_len": 8192, |
| "max_batch_tokens": 16384, |
| "extra_train": [ |
| "general mix (scripts/general_data.py: MNLI, BoolQ)", |
| "kgrozdanovski/assistant-decisions long/train.jsonl" |
| ], |
| "extra_val": [ |
| "general mix validation (scripts/general_data.py)", |
| "kgrozdanovski/assistant-decisions long/validation.jsonl" |
| ] |
| }, |
| "packed": true |
| } |
|
|
