Download rl_agent_config.json from Otron/snap-1: direct link, hf CLI and curl.
- Browser
- Download file 738 Bytes
-
https://huggingface.co/Otron/snap-1/resolve/main/rl_agent_config.json
- Command line
-
hf download hf://Otron/snap-1/rl_agent_config.json
-
curl -L -o rl_agent_config.json https://huggingface.co/Otron/snap-1/resolve/main/rl_agent_config.json
738 Bytes
| { | |
| "encoder": "answerdotai/ModernBERT-large", | |
| "head_layers": 2, | |
| "max_len": 4096, | |
| "head_max_len": 3584, | |
| "max_prefixes": 6, | |
| "act_costs": { | |
| "escalate": 0.5 | |
| }, | |
| "cost_wrong_act": 3.0, | |
| "amp_dtype": "bf16", | |
| "model_name": "rl-agent", | |
| "temperature": [ | |
| 1.2599210498948732, | |
| 1.6817928305074288, | |
| 1.189207115002721 | |
| ], | |
| "temperature_by_options": { | |
| "choice:6-10": 1.4142135623730947, | |
| "choice:3-5": 1.3348398541700341, | |
| "noul:2": 1.189207115002721, | |
| "score:3-5": 1.6817928305074288, | |
| "score:6-10": 1.7817974362806785, | |
| "choice:11+": 1.189207115002721 | |
| }, | |
| "training": { | |
| "updates": 7313, | |
| "epochs_completed": 1, | |
| "hours": 1.96, | |
| "world_size": 1, | |
| "fine_tuned_from_checkpoint": true, | |
| "steps": 208 | |
| }, | |
| "layout": "packed" | |
| } |