dev-senolys commited on
Commit
5ff8161
1 Parent(s): d396e96

Model save

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "flaubert/flaubert_base_cased",
3
+ "amp": 1,
4
+ "architectures": [
5
+ "FlaubertForSequenceClassification"
6
+ ],
7
+ "asm": false,
8
+ "attention_dropout": 0.1,
9
+ "bos_index": 0,
10
+ "bos_token_id": 0,
11
+ "bptt": 512,
12
+ "causal": false,
13
+ "clip_grad_norm": 5,
14
+ "dropout": 0.1,
15
+ "emb_dim": 768,
16
+ "embed_init_std": 0.02209708691207961,
17
+ "encoder_only": true,
18
+ "end_n_top": 5,
19
+ "eos_index": 1,
20
+ "fp16": true,
21
+ "gelu_activation": true,
22
+ "group_by_size": true,
23
+ "id2label": {
24
+ "0": "agronomy",
25
+ "1": "business",
26
+ "2": "design",
27
+ "3": "digital",
28
+ "4": "environment",
29
+ "5": "learning",
30
+ "6": "medical",
31
+ "7": "people",
32
+ "8": "production",
33
+ "9": "resource",
34
+ "10": "science",
35
+ "11": "security",
36
+ "12": "society",
37
+ "13": "transport"
38
+ },
39
+ "id2lang": {
40
+ "0": "fr"
41
+ },
42
+ "init_std": 0.02,
43
+ "is_encoder": true,
44
+ "label2id": {
45
+ "agronomy": 0,
46
+ "business": 1,
47
+ "design": 2,
48
+ "digital": 3,
49
+ "environment": 4,
50
+ "learning": 5,
51
+ "medical": 6,
52
+ "people": 7,
53
+ "production": 8,
54
+ "resource": 9,
55
+ "science": 10,
56
+ "security": 11,
57
+ "society": 12,
58
+ "transport": 13
59
+ },
60
+ "lang2id": {
61
+ "fr": 0
62
+ },
63
+ "lang_id": 0,
64
+ "langs": [
65
+ "fr"
66
+ ],
67
+ "layer_norm_eps": 1e-12,
68
+ "layerdrop": 0.0,
69
+ "lg_sampling_factor": -1,
70
+ "lgs": "fr",
71
+ "mask_index": 5,
72
+ "mask_token_id": 0,
73
+ "max_batch_size": 0,
74
+ "max_position_embeddings": 512,
75
+ "max_vocab": -1,
76
+ "mlm_steps": [
77
+ [
78
+ "fr",
79
+ null
80
+ ]
81
+ ],
82
+ "model_type": "flaubert",
83
+ "n_heads": 12,
84
+ "n_langs": 1,
85
+ "n_layers": 12,
86
+ "pad_index": 2,
87
+ "pad_token_id": 2,
88
+ "pre_norm": false,
89
+ "problem_type": "single_label_classification",
90
+ "sample_alpha": 0,
91
+ "share_inout_emb": true,
92
+ "sinusoidal_embeddings": false,
93
+ "start_n_top": 5,
94
+ "summary_activation": null,
95
+ "summary_first_dropout": 0.1,
96
+ "summary_proj_to_labels": true,
97
+ "summary_type": "first",
98
+ "summary_use_proj": true,
99
+ "tokens_per_batch": -1,
100
+ "torch_dtype": "float32",
101
+ "transformers_version": "4.29.2",
102
+ "unk_index": 3,
103
+ "use_lang_emb": true,
104
+ "vocab_size": 68729,
105
+ "word_blank": 0,
106
+ "word_dropout": 0,
107
+ "word_keep": 0.1,
108
+ "word_mask": 0.8,
109
+ "word_mask_keep_rand": "0.8,0.1,0.1",
110
+ "word_pred": 0.15,
111
+ "word_rand": 0.1,
112
+ "word_shuffle": 0
113
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:734b13acb2476a827de2c2d1789207d132abceac2712dcb3efa3284f83659ec8
3
+ size 553037541
runs/Jun12_14-30-32_ns3005206/1686580237.6037836/events.out.tfevents.1686580237.ns3005206.182255.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e4f6426f96a9a0386873401bd4ae61b3be95fb7f9d2c86159e4027bb809273b
3
+ size 5994
runs/Jun12_14-30-32_ns3005206/events.out.tfevents.1686580237.ns3005206.182255.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:982c64974238762a068f8f6cdc7d0e0c645dcf24d804def60d1408857dd72000
3
+ size 6808
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<special0>",
4
+ "<special1>",
5
+ "<special2>",
6
+ "<special3>",
7
+ "<special4>",
8
+ "<special5>",
9
+ "<special6>",
10
+ "<special7>",
11
+ "<special8>",
12
+ "<special9>"
13
+ ],
14
+ "bos_token": "<s>",
15
+ "cls_token": "</s>",
16
+ "mask_token": "<special1>",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<special0>",
4
+ "<special1>",
5
+ "<special2>",
6
+ "<special3>",
7
+ "<special4>",
8
+ "<special5>",
9
+ "<special6>",
10
+ "<special7>",
11
+ "<special8>",
12
+ "<special9>"
13
+ ],
14
+ "bos_token": "<s>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "cls_token": "</s>",
17
+ "do_lower_case": false,
18
+ "id2lang": null,
19
+ "lang2id": null,
20
+ "mask_token": "<special1>",
21
+ "model_max_length": 512,
22
+ "pad_token": "<pad>",
23
+ "sep_token": "</s>",
24
+ "tokenizer_class": "FlaubertTokenizer",
25
+ "unk_token": "<unk>"
26
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef87be2eea855e4ebba8c84e8c327cc7050ede6299573b6a155853da71d886f
3
+ size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff