multilingual/rl_agent_config.json
| 1 | { |
| 2 | "encoder": "jhu-clsp/mmBERT-base", |
| 3 | "head_layers": 2, |
| 4 | "max_len": 1024, |
| 5 | "head_max_len": 256, |
| 6 | "max_prefixes": 6, |
| 7 | "act_costs": { |
| 8 | "escalate": 0.5 |
| 9 | }, |
| 10 | "cost_wrong_act": 3.0, |
| 11 | "amp_dtype": "bf16", |
| 12 | "model_name": "rl-agent", |
| 13 | "temperature": [ |
| 14 | 1.0, |
| 15 | 1.0, |
| 16 | 1.0 |
| 17 | ], |
| 18 | "temperature_by_options": {}, |
| 19 | "training": { |
| 20 | "updates": 15987, |
| 21 | "epochs_completed": 4, |
| 22 | "hours": 4.97, |
| 23 | "world_size": 1, |
| 24 | "fine_tuned_from_checkpoint": false |
| 25 | } |
| 26 | } |