antoinelouis
commited on
Commit
•
02acde6
1
Parent(s):
d89bd8f
New model
Browse files- config.json +1 -1
- dev_scores.csv +0 -2
- mmarco_smalldev_scores.csv +7 -0
- model.safetensors +2 -2
- pytorch_model.bin +0 -3
- tokenizer.json +1 -1
- tokenizer_config.json +43 -1
config.json
CHANGED
@@ -29,7 +29,7 @@
|
|
29 |
"summary_type": "first",
|
30 |
"summary_use_proj": true,
|
31 |
"torch_dtype": "float32",
|
32 |
-
"transformers_version": "4.
|
33 |
"type_vocab_size": 2,
|
34 |
"use_cache": true,
|
35 |
"vocab_size": 32000
|
|
|
29 |
"summary_type": "first",
|
30 |
"summary_use_proj": true,
|
31 |
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.36.2",
|
33 |
"type_vocab_size": 2,
|
34 |
"use_cache": true,
|
35 |
"vocab_size": 32000
|
dev_scores.csv
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
r-precision,mrr@10,recall@10,recall@20,recall@50,recall@100,model
|
2 |
-
28.32,45.28,79.22,87.15,93.15,95.75,crossencoder-electra-base-french-europeana-cased-discriminator-mmarcoFR
|
|
|
|
|
|
mmarco_smalldev_scores.csv
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,steps,cutoff,mrr,recall,r-precision
|
2 |
+
0,20000,5,0.3031924546322826,0.4590974212034384,0.20630372492836677
|
3 |
+
0,20000,10,0.317026652112612,0.5603151862464183,0.20630372492836677
|
4 |
+
0,20000,20,0.32353450109473514,0.653414517669532,0.20630372492836677
|
5 |
+
0,20000,50,0.3270969018915065,0.7632402101241643,0.20630372492836677
|
6 |
+
0,20000,100,0.32799538277835383,0.8271728748806113,0.20630372492836677
|
7 |
+
0,20000,500,0.3286107804304277,0.9510864374403056,0.20630372492836677
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0434afe1fc251bac9dc7c413554f9a588f0e65e3e626a78a8b958e1bc2606252
|
3 |
+
size 442496596
|
pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:138bead9acdacb20b9b2695e949b843530512680433c600341b08aa42c12a585
|
3 |
-
size 442545845
|
|
|
|
|
|
|
|
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 256,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
tokenizer_config.json
CHANGED
@@ -1,11 +1,53 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_basic_tokenize": true,
|
5 |
"do_lower_case": false,
|
6 |
"mask_token": "[MASK]",
|
7 |
"max_len": 512,
|
8 |
-
"model_max_length":
|
9 |
"never_split": null,
|
10 |
"pad_token": "[PAD]",
|
11 |
"sep_token": "[SEP]",
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
"do_lower_case": false,
|
48 |
"mask_token": "[MASK]",
|
49 |
"max_len": 512,
|
50 |
+
"model_max_length": 256,
|
51 |
"never_split": null,
|
52 |
"pad_token": "[PAD]",
|
53 |
"sep_token": "[SEP]",
|