{ "baseline": { "STS-B": { "spearman": 0.574721280584061, "self_cos": 0.13962045311927795, "erank": 36.611595622425114 }, "SICK-R": { "spearman": 0.652602297708298, "self_cos": 0.32337328791618347, "erank": 39.12520123844512 } }, "history": [ { "step": 500, "STS-B_OFF": 0.574721280584061, "STS-B_ON": 0.7344460298339228, "SICK-R_OFF": 0.652602297708298, "SICK-R_ON": 0.7453666480223926 } ], "step": 500, "config": { "run_name": "captionbert-v2-sts-anchor-combo", "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", "sites": "all", "n_slots": 16, "K": 64, "D": 4, "tau": 0.1, "hidden": 178, "gate_init": -3.0, "sources": [ [ "sentence-transformers/all-nli", "triplet", "anchor", "positive", "negative", 200000 ], [ "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 ] ], "dedup_jaccard": 0.95, "max_tokens": 64, "batch_size": 256, "temperature": 0.05, "use_hard_negatives": true, "steps": 4000, "lr": 0.001, "warmup": 200, "grad_clip": 1.0, "seed": 0, "log_every": 100, "eval_every": 500, "out_dir": "/content/amoe_sts", "hf_repo": "AbstractPhil/captionbert-8192-v2", "hf_path": "amoe/sts-combo", "hf_private": false, "hf_push": true } }