Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- config.json +124 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +19 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/xmod-base",
|
3 |
+
"adapter_layer_norm": false,
|
4 |
+
"adapter_reduction_factor": 2,
|
5 |
+
"adapter_reuse_layer_norm": true,
|
6 |
+
"architectures": [
|
7 |
+
"XmodForSequenceClassification"
|
8 |
+
],
|
9 |
+
"attention_probs_dropout_prob": 0.1,
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"classifier_dropout": null,
|
12 |
+
"default_language": "de_DE",
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"id2label": {
|
18 |
+
"0": "No misinformation",
|
19 |
+
"1": "Potential misinformation"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"No misinformation": 0,
|
25 |
+
"Potential misinformation": 1
|
26 |
+
},
|
27 |
+
"languages": [
|
28 |
+
"en_XX",
|
29 |
+
"id_ID",
|
30 |
+
"vi_VN",
|
31 |
+
"ru_RU",
|
32 |
+
"fa_IR",
|
33 |
+
"sv_SE",
|
34 |
+
"ja_XX",
|
35 |
+
"fr_XX",
|
36 |
+
"de_DE",
|
37 |
+
"ro_RO",
|
38 |
+
"ko_KR",
|
39 |
+
"hu_HU",
|
40 |
+
"es_XX",
|
41 |
+
"fi_FI",
|
42 |
+
"uk_UA",
|
43 |
+
"da_DK",
|
44 |
+
"pt_XX",
|
45 |
+
"no_XX",
|
46 |
+
"th_TH",
|
47 |
+
"pl_PL",
|
48 |
+
"bg_BG",
|
49 |
+
"nl_XX",
|
50 |
+
"zh_CN",
|
51 |
+
"he_IL",
|
52 |
+
"el_GR",
|
53 |
+
"it_IT",
|
54 |
+
"sk_SK",
|
55 |
+
"hr_HR",
|
56 |
+
"tr_TR",
|
57 |
+
"ar_AR",
|
58 |
+
"cs_CZ",
|
59 |
+
"lt_LT",
|
60 |
+
"hi_IN",
|
61 |
+
"zh_TW",
|
62 |
+
"ca_ES",
|
63 |
+
"ms_MY",
|
64 |
+
"sl_SI",
|
65 |
+
"lv_LV",
|
66 |
+
"ta_IN",
|
67 |
+
"bn_IN",
|
68 |
+
"et_EE",
|
69 |
+
"az_AZ",
|
70 |
+
"sq_AL",
|
71 |
+
"sr_RS",
|
72 |
+
"kk_KZ",
|
73 |
+
"ka_GE",
|
74 |
+
"tl_XX",
|
75 |
+
"ur_PK",
|
76 |
+
"is_IS",
|
77 |
+
"hy_AM",
|
78 |
+
"ml_IN",
|
79 |
+
"mk_MK",
|
80 |
+
"be_BY",
|
81 |
+
"la_VA",
|
82 |
+
"te_IN",
|
83 |
+
"eu_ES",
|
84 |
+
"gl_ES",
|
85 |
+
"mn_MN",
|
86 |
+
"kn_IN",
|
87 |
+
"ne_NP",
|
88 |
+
"sw_KE",
|
89 |
+
"si_LK",
|
90 |
+
"mr_IN",
|
91 |
+
"af_ZA",
|
92 |
+
"gu_IN",
|
93 |
+
"cy_GB",
|
94 |
+
"eo_EO",
|
95 |
+
"km_KH",
|
96 |
+
"ky_KG",
|
97 |
+
"uz_UZ",
|
98 |
+
"ps_AF",
|
99 |
+
"pa_IN",
|
100 |
+
"ga_IE",
|
101 |
+
"ha_NG",
|
102 |
+
"am_ET",
|
103 |
+
"lo_LA",
|
104 |
+
"ku_TR",
|
105 |
+
"so_SO",
|
106 |
+
"my_MM",
|
107 |
+
"or_IN",
|
108 |
+
"sa_IN"
|
109 |
+
],
|
110 |
+
"layer_norm_eps": 1e-05,
|
111 |
+
"ln_before_adapter": true,
|
112 |
+
"max_position_embeddings": 514,
|
113 |
+
"model_type": "xmod",
|
114 |
+
"num_attention_heads": 12,
|
115 |
+
"num_hidden_layers": 12,
|
116 |
+
"pad_token_id": 1,
|
117 |
+
"position_embedding_type": "absolute",
|
118 |
+
"pre_norm": false,
|
119 |
+
"torch_dtype": "float32",
|
120 |
+
"transformers_version": "4.32.1",
|
121 |
+
"type_vocab_size": 1,
|
122 |
+
"use_cache": true,
|
123 |
+
"vocab_size": 250002
|
124 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfc82d2eef3510823a0a58fcdd031c241b216892b6422869cc1aa13c418b7a38
|
3 |
+
size 3411383039
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96628b7704b1f281a45df5d9feb0ef79e2c058130bf55a20bedd465146416746
|
3 |
+
size 17082815
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 1000000000000000019884624838656,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c899e786d3b65088b96c22ce885713053538816c577b391773ce0c0eebfdb805
|
3 |
+
size 4536
|