{ "run_name": "captionbert-v2-collective", "trunk_repo": "AbstractPhil/captionbert-8192-v2", "trunk_ckpt": "checkpoints/best_model.pt", "tokenizer": "google-bert/bert-base-uncased", "d_model": 512, "n_heads": 8, "n_layers": 12, "d_ff": 2048, "max_len": 8192, "output_dim": 768, "pooling": "mean", "arms": [ [ "equiv", { "kind": "hub", "path": "amoe/moe/equiv.anchor.pt", "sources": [ [ "sentence-transformers/all-nli", "triplet", "anchor", "positive", "negative", 200000 ] ] } ], [ "simplify", { "kind": "hub", "path": "amoe/moe/simplify.anchor.pt", "sources": [ [ "sentence-transformers/simple-wiki", "pair", "text", "simplified", null, 0 ], [ "sentence-transformers/altlex", "pair", "text", "simplified", null, 0 ], [ "sentence-transformers/sentence-compression", "pair", "text", "simplified", null, 0 ] ] } ], [ "paraphrase", { "kind": "data", "sources": [ [ "sentence-transformers/quora-duplicates", "triplet", "anchor", "positive", "negative", 0 ] ] } ], [ "lexical", { "kind": "wordnet" } ], [ "topical", { "kind": "data", "sources": [ [ "sentence-transformers/specter", "triplet", "anchor", "positive", "negative", 200000 ] ] } ], [ "random", { "kind": "random" } ] ], "wordnet_max": 156000, "dedup_jaccard": 0.95, "base_arms": [ "equiv", "simplify" ], "greedy": true, "greedy_rounds": 4, "select_on": "STS-B", "n_slots": 16, "K": 64, "D": 4, "tau": 0.1, "hidden": 178, "gate_init": -3.0, "anchor_steps": 1500, "anchor_lr": 0.001, "batch_size": 256, "temperature": 0.05, "max_tokens": 64, "align_steps": 800, "align_lr": 0.001, "align_emb": 64, "check_every": 200, "usage_ppl_floor": 1.5, "usage_min": 0.02, "max_strikes": 3, "mix_rows": true, "align_taus": [ 0.1 ], "align_seeds": [ 0 ], "per_block_report": true, "seed": 0, "log_every": 100, "eval_every": 500, "reuse_anchors": true, "out_dir": "/content/amoe_collective", "hf_repo": "AbstractPhil/captionbert-8192-v2", "hf_path": "amoe/collective", "hf_private": false, "hf_push": true }