has-abi commited on
Commit
b3f60bf
1 Parent(s): 9a5b1fb

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Geotrend/distilbert-base-en-fr-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "awards",
13
+ "1": "certificates",
14
+ "2": "contact/name/title",
15
+ "3": "education",
16
+ "4": "interests",
17
+ "5": "languages",
18
+ "6": "para",
19
+ "7": "professional_experiences",
20
+ "8": "projects",
21
+ "9": "skills",
22
+ "10": "soft_skills",
23
+ "11": "summary"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "label2id": {
27
+ "awards": 0,
28
+ "certificates": 1,
29
+ "contact/name/title": 2,
30
+ "education": 3,
31
+ "interests": 4,
32
+ "languages": 5,
33
+ "para": 6,
34
+ "professional_experiences": 7,
35
+ "projects": 8,
36
+ "skills": 9,
37
+ "soft_skills": 10,
38
+ "summary": 11
39
+ },
40
+ "max_position_embeddings": 512,
41
+ "model_type": "distilbert",
42
+ "n_heads": 12,
43
+ "n_layers": 6,
44
+ "output_past": true,
45
+ "pad_token_id": 0,
46
+ "problem_type": "multi_label_classification",
47
+ "qa_dropout": 0.1,
48
+ "seq_classif_dropout": 0.2,
49
+ "sinusoidal_pos_embds": false,
50
+ "tie_weights_": true,
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.20.1",
53
+ "vocab_size": 33407
54
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3488cb82d4c5a5c634e77c5e91d04c97f0425a6bd13da603af84d175d07c010a
3
+ size 276747761
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "name_or_path": "Geotrend/distilbert-base-en-fr-cased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "DistilBertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a67aa5e951379427f49f56e2615b1af26aea60cc5443d53a05528852d09d7f
3
+ size 3375
vocab.txt ADDED
The diff for this file is too large to render. See raw diff