File size: 2,170 Bytes
4612a7c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
{
    "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,
    "index_bsize": 64,
    "nbits": 2,
    "kmeans_niters": 4,
    "resume": false,
    "similarity": "cosine",
    "bsize": 32,
    "accumsteps": 1,
    "lr": 1e-5,
    "maxsteps": 400000,
    "save_every": null,
    "warmup": 20000,
    "warmup_bert": null,
    "relu": false,
    "nway": 65,
    "use_ib_negatives": true,
    "reranker": false,
    "distillation_alpha": 1.0,
    "ignore_scores": false,
    "model_name": "antoinelouis\/camembert-L4",
    "query_maxlen": 32,
    "attend_to_mask_tokens": true,
    "interaction": "colbert",
    "dim": 32,
    "doc_maxlen": 160,
    "mask_punctuation": true,
    "checkpoint": "antoinelouis\/camembert-L4",
    "triples": "data\/mmarco\/tuples.train.scores-ids.65way.13.1M.jsonl",
    "collection": "data\/mmarco\/french_collection.tsv",
    "queries": "data\/mmarco\/french_queries.train.tsv",
    "index_name": null,
    "overwrite": false,
    "root": "output\/training\/mmarco",
    "experiment": "colbert",
    "index_root": null,
    "name": "2024-03-06_19.25-antoinelouis-camembert-L4-mmarco-fr",
    "rank": 0,
    "nranks": 1,
    "amp": true,
    "gpus": 1,
    "avoid_fork_if_possible": false,
    "meta": {
        "hostname": "jupyterlab-gpu-2-9-xd9bd",
        "git_branch": "main",
        "git_hash": "9062516d8fe0c1e5224fd4d91feed68d2cee3c2c",
        "git_commit_datetime": "2024-03-06 18:15:26+01:00",
        "current_datetime": "Mar 10, 2024 ;  3:29PM CET (+0100)",
        "cmd": "src\/training\/colbertv2.py --dataset mmarco --language fr --do_train --model_name antoinelouis\/camembert-L4 --dim 32 --similarity cosine --doc_maxlen 160 --query_maxlen 32 --mask_punctuation --attend_to_mask_tokens --maxsteps 400000 --warmup 20000 --lr 1e-5 --bsize 32 --accumsteps 1 --nway 65 --use_ib_negatives --distillation_alpha 1.0 --nbits 2 --kmeans_niters 4 --data_dir data --output_dir output\/training",
        "version": "colbert-v0.4"
    }
}