dev-senolys
commited on
Commit
•
3833b9c
1
Parent(s):
5395a6b
Model save
Browse files- .gitignore +1 -0
- config.json +113 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jun13_12-47-04_ns3005206/1686660429.2832844/events.out.tfevents.1686660429.ns3005206.197945.1 +3 -0
- runs/Jun13_12-47-04_ns3005206/events.out.tfevents.1686660429.ns3005206.197945.0 +3 -0
- special_tokens_map.json +20 -0
- tokenizer_config.json +26 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.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 sha256:5feb1736119e0b5e513c26e05d2cb4f24ab519afb33cd0825365c2ef64aa4d02
|
3 |
+
size 553037541
|
runs/Jun13_12-47-04_ns3005206/1686660429.2832844/events.out.tfevents.1686660429.ns3005206.197945.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6da2acb1f5516bad85b5d34827c8df47992043c9cee5d1ac419aa25cba2f35a
|
3 |
+
size 6015
|
runs/Jun13_12-47-04_ns3005206/events.out.tfevents.1686660429.ns3005206.197945.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a207c5faba02e6ed377127c68160c036ee815cacf1cd89a5c7ed8c718cb0158
|
3 |
+
size 6829
|
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 sha256:698705ce8533067724ae6a0c1b3cf70bbd592e536f0e51f502b83557731afb5f
|
3 |
+
size 3963
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|