Hugging Face's logo

Kigo1974
/
sitexsometre-flaubert-large-cased

Text Classification
Transformers
TensorBoard
Safetensors
flaubert
Inference Endpoints
Model card Files Metrics Community
Kigo1974 commited on
Commit
df92d9e
•
1 Parent(s): 8d425ab

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +88 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Nov02_18-41-37_9941243f0631/events.out.tfevents.1698950581.9941243f0631.469.1 +3 -0
  5. special_tokens_map.json +20 -0
  6. tokenizer_config.json +140 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Flaubert/flaubert_large_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": 1024,
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": "LABEL_0"
25
+ },
26
+ "id2lang": {
27
+ "0": "fr"
28
+ },
29
+ "init_std": 0.02,
30
+ "is_encoder": true,
31
+ "label2id": {
32
+ "LABEL_0": 0
33
+ },
34
+ "lang2id": {
35
+ "fr": 0
36
+ },
37
+ "lang_id": 0,
38
+ "langs": [
39
+ "fr"
40
+ ],
41
+ "layer_norm_eps": 1e-06,
42
+ "layerdrop": 0.2,
43
+ "lg_sampling_factor": -1,
44
+ "lgs": "fr",
45
+ "mask_index": 5,
46
+ "mask_token_id": 0,
47
+ "max_batch_size": 0,
48
+ "max_position_embeddings": 512,
49
+ "max_vocab": -1,
50
+ "mlm_steps": [
51
+ [
52
+ "fr",
53
+ null
54
+ ]
55
+ ],
56
+ "model_type": "flaubert",
57
+ "n_heads": 16,
58
+ "n_langs": 1,
59
+ "n_layers": 24,
60
+ "pad_index": 2,
61
+ "pad_token_id": 2,
62
+ "pre_norm": true,
63
+ "problem_type": "regression",
64
+ "sample_alpha": 0,
65
+ "share_inout_emb": true,
66
+ "sinusoidal_embeddings": false,
67
+ "start_n_top": 5,
68
+ "summary_activation": null,
69
+ "summary_first_dropout": 0.1,
70
+ "summary_proj_to_labels": true,
71
+ "summary_type": "first",
72
+ "summary_use_proj": true,
73
+ "tokens_per_batch": -1,
74
+ "torch_dtype": "float32",
75
+ "transformers_version": "4.35.0",
76
+ "unk_index": 3,
77
+ "use_apex": true,
78
+ "use_lang_emb": true,
79
+ "vocab_size": 68729,
80
+ "word_blank": 0,
81
+ "word_dropout": 0,
82
+ "word_keep": 0.1,
83
+ "word_mask": 0.8,
84
+ "word_mask_keep_rand": "0.8,0.1,0.1",
85
+ "word_pred": 0.15,
86
+ "word_rand": 0.1,
87
+ "word_shuffle": 0
88
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc0bf416ef27427f02fcfaa7ae6ee770df4ced1833b59e5a8c865af789e5ce9
3
+ size 1492902748
runs/Nov02_18-41-37_9941243f0631/events.out.tfevents.1698950581.9941243f0631.469.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:830e569f8cb004405b85d2f5e333d21aa82fb0d78eb2423ab013771b5ff5cebf
3
+ size 5777
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 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<special0>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<special1>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<special2>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<special3>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<special4>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<special5>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<special6>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<special7>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<special8>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "<special9>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ }
115
+ },
116
+ "additional_special_tokens": [
117
+ "<special0>",
118
+ "<special1>",
119
+ "<special2>",
120
+ "<special3>",
121
+ "<special4>",
122
+ "<special5>",
123
+ "<special6>",
124
+ "<special7>",
125
+ "<special8>",
126
+ "<special9>"
127
+ ],
128
+ "bos_token": "<s>",
129
+ "clean_up_tokenization_spaces": true,
130
+ "cls_token": "</s>",
131
+ "do_lower_case": false,
132
+ "id2lang": null,
133
+ "lang2id": null,
134
+ "mask_token": "<special1>",
135
+ "model_max_length": 1000000000000000019884624838656,
136
+ "pad_token": "<pad>",
137
+ "sep_token": "</s>",
138
+ "tokenizer_class": "FlaubertTokenizer",
139
+ "unk_token": "<unk>"
140
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e4466fafa6ed4169ea9705288d2481d1ee35c3862450dcb74e0899984dd305
3
+ size 4600
vocab.json ADDED
The diff for this file is too large to render. See raw diff