|
{ |
|
"query_token_id": "[unused0]", |
|
"doc_token_id": "[unused1]", |
|
"query_token": "[Q]", |
|
"doc_token": "[D]", |
|
"ncells": null, |
|
"centroid_score_threshold": null, |
|
"ndocs": null, |
|
"load_index_with_mmap": false, |
|
"index_path": null, |
|
"nbits": 1, |
|
"kmeans_niters": 4, |
|
"resume": false, |
|
"similarity": "cosine", |
|
"bsize": 64, |
|
"accumsteps": 1, |
|
"lr": 3e-6, |
|
"maxsteps": 200000, |
|
"save_every": null, |
|
"warmup": null, |
|
"warmup_bert": null, |
|
"relu": false, |
|
"nway": 2, |
|
"use_ib_negatives": true, |
|
"reranker": false, |
|
"distillation_alpha": 1.0, |
|
"ignore_scores": true, |
|
"model_name": "camembert-base", |
|
"query_maxlen": 32, |
|
"attend_to_mask_tokens": true, |
|
"interaction": "colbert", |
|
"dim": 128, |
|
"doc_maxlen": 256, |
|
"mask_punctuation": true, |
|
"checkpoint": "camembert-base", |
|
"triples": "data\/mmarco\/triples.train.ids.small.jsonl", |
|
"collection": "data\/mmarco\/french_collection.tsv", |
|
"queries": "data\/mmarco\/french_queries.train.tsv", |
|
"index_name": null, |
|
"overwrite": false, |
|
"root": "output\/training", |
|
"experiment": "mmarco", |
|
"index_root": null, |
|
"name": "2023-12\/21\/15.44.53", |
|
"rank": 0, |
|
"nranks": 1, |
|
"amp": true, |
|
"gpus": 1, |
|
"meta": { |
|
"hostname": "jupyterlab-gpu-2-4-jgfkq", |
|
"git_branch": "main", |
|
"git_hash": "49363ffb7f6ca212ff2780edb86b485d0379e836", |
|
"git_commit_datetime": "2023-12-21 19:32:07+01:00", |
|
"current_datetime": "Dec 22, 2023 ; 12:53PM CET (+0100)", |
|
"cmd": "src\/training\/colbertv1.py --dataset mmarco --language french --nway 2 --model_name camembert-base --dim 128 --similarity cosine --doc_maxlen 256 --query_maxlen 32 --mask_punctuation --attend_to_mask_tokens --maxsteps 200000 --lr 3e-6 --bsize 64 --accumsteps 1 --use_ib_negatives --ignore_scores --distillation_alpha 1.0 --nbits 1 --kmeans_niters 4 --data_dir data --output_dir output\/training", |
|
"version": "colbert-v0.4" |
|
} |
|
} |
|
|