tasksource-decider-nano / decider_config.json
sileod's picture
v3: same recipe as v2 trained for 24,000 steps (Decision Index 0.3 public 29.05); v2 kept at tag v2
6fa4fce verified
Raw History Blame Contribute Delete
699 Bytes
{
"format": "pair-v1",
"arch": "joint",
"base": "cross-encoder/ettin-reranker-150m-v1",
"train_max_length": 2048,
"inference_max_length": 8192,
"step": 24000,
"train": {
"arch": "joint",
"opt_pool": "marker",
"shuffle_options": false,
"manifest": "runs/manifests/mix_all.jsonl",
"extra_manifest": null,
"extra_frac": 0.0,
"lr": 2e-05,
"batch_requests": 8,
"max_k": 32,
"seed": 7,
"total_steps": 24000,
"max_length": 2048,
"pack": 0,
"init": null,
"init_backbone": null,
"gc_tokens": 0,
"layout": "shared",
"pool": "opt",
"row_tokens": 8192,
"tok_budget": 12288
},
"layout": "shared",
"pool": "opt"
}