dominguesm
commited on
Commit
•
22d9c44
1
Parent(s):
50ea647
Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +73 -0
- pytorch_model.bin +3 -0
- runs/Mar11_03-17-58_b9380ec48ae2/1678504714.920912/events.out.tfevents.1678504714.b9380ec48ae2.6853.1 +3 -0
- runs/Mar11_03-17-58_b9380ec48ae2/events.out.tfevents.1678504714.b9380ec48ae2.6853.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "ar",
|
15 |
+
"1": "bg",
|
16 |
+
"2": "de",
|
17 |
+
"3": "el",
|
18 |
+
"4": "en",
|
19 |
+
"5": "es",
|
20 |
+
"6": "fr",
|
21 |
+
"7": "hi",
|
22 |
+
"8": "it",
|
23 |
+
"9": "ja",
|
24 |
+
"10": "nl",
|
25 |
+
"11": "pl",
|
26 |
+
"12": "pt",
|
27 |
+
"13": "ru",
|
28 |
+
"14": "sw",
|
29 |
+
"15": "th",
|
30 |
+
"16": "tr",
|
31 |
+
"17": "ur",
|
32 |
+
"18": "vi",
|
33 |
+
"19": "zh"
|
34 |
+
},
|
35 |
+
"initializer_range": 0.02,
|
36 |
+
"intermediate_size": 3072,
|
37 |
+
"label2id": {
|
38 |
+
"ar": 0,
|
39 |
+
"bg": 1,
|
40 |
+
"de": 2,
|
41 |
+
"el": 3,
|
42 |
+
"en": 4,
|
43 |
+
"es": 5,
|
44 |
+
"fr": 6,
|
45 |
+
"hi": 7,
|
46 |
+
"it": 8,
|
47 |
+
"ja": 9,
|
48 |
+
"nl": 10,
|
49 |
+
"pl": 11,
|
50 |
+
"pt": 12,
|
51 |
+
"ru": 13,
|
52 |
+
"sw": 14,
|
53 |
+
"th": 15,
|
54 |
+
"tr": 16,
|
55 |
+
"ur": 17,
|
56 |
+
"vi": 18,
|
57 |
+
"zh": 19
|
58 |
+
},
|
59 |
+
"layer_norm_eps": 1e-05,
|
60 |
+
"max_position_embeddings": 514,
|
61 |
+
"model_type": "xlm-roberta",
|
62 |
+
"num_attention_heads": 12,
|
63 |
+
"num_hidden_layers": 12,
|
64 |
+
"output_past": true,
|
65 |
+
"pad_token_id": 1,
|
66 |
+
"position_embedding_type": "absolute",
|
67 |
+
"problem_type": "single_label_classification",
|
68 |
+
"torch_dtype": "float32",
|
69 |
+
"transformers_version": "4.27.0.dev0",
|
70 |
+
"type_vocab_size": 1,
|
71 |
+
"use_cache": true,
|
72 |
+
"vocab_size": 250002
|
73 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:499993dfb880f7031da73612277bc39011370aa3b1f723513a417040ba66f0fd
|
3 |
+
size 1113506293
|
runs/Mar11_03-17-58_b9380ec48ae2/1678504714.920912/events.out.tfevents.1678504714.b9380ec48ae2.6853.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:226eac3757156ef814a95a8d6be67bee0f72634bd612a5bd7d1e64106bf2e702
|
3 |
+
size 5855
|
runs/Mar11_03-17-58_b9380ec48ae2/events.out.tfevents.1678504714.b9380ec48ae2.6853.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed444088c4c82b58efcc497c556c454d56c957bbb4f10e9b87493c687258bcee
|
3 |
+
size 5187
|
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 sha256:1edb0658cb47689db5cf78194ebe041bba3b6b775d1f1069fc9501b372d4acb0
|
3 |
+
size 17082758
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"pad_token": "<pad>",
|
15 |
+
"padding_side": "right",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"special_tokens_map_file": null,
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cede64d00a15087fc0ba961eb824d9efd6de9f0af3e69730c2c50f6859b01a9
|
3 |
+
size 3643
|