| { |
| "encoder": "jhu-clsp/mmBERT-base", |
| "head_layers": 2, |
| "max_len": 4096, |
| "head_max_len": 256, |
| "max_prefixes": 6, |
| "act_costs": { |
| "escalate": 0.5 |
| }, |
| "cost_wrong_act": 3.0, |
| "amp_dtype": "bf16", |
| "model_name": "XERON", |
| "temperature": [ |
| 0.995093822479248, |
| 1.1019741296768188, |
| 1.1216171979904175 |
| ], |
| "temperature_by_options": {}, |
| "training": { |
| "updates": 15987, |
| "epochs_completed": 4, |
| "hours": 4.97, |
| "world_size": 1, |
| "fine_tuned_from_checkpoint": false |
| }, |
| "gradient_checkpointing": true, |
| "max_tokens_per_batch": 16384, |
| "fine_tuned": true |
| } |
