| { | |
| "encoder": "answerdotai/ModernBERT-large", | |
| "head_layers": 2, | |
| "max_len": 1024, | |
| "head_max_len": 256, | |
| "max_prefixes": 6, | |
| "act_costs": { | |
| "escalate": 0.5 | |
| }, | |
| "cost_wrong_act": 3.0, | |
| "amp_dtype": "bf16", | |
| "model_name": "laya-fallacies", | |
| "temperature": [ | |
| 1.876949429512024, | |
| 1.2, | |
| 1.2 | |
| ], | |
| "training": { | |
| "updates": 7313, | |
| "epochs_completed": 1, | |
| "hours": 1.96, | |
| "world_size": 1, | |
| "fine_tuned_from_checkpoint": true | |
| }, | |
| "gradient_checkpointing": true, | |
| "max_tokens_per_batch": 4096, | |
| "fine_tuned": true | |
| } |