{ "run_name": "captionbert-v2-sts-anchor", "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, "data_repo": "sentence-transformers/all-nli", "data_config": "triplet", "n_train": 200000, "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", "hf_private": false, "hf_push": true }