Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +78 -0
- pytorch_model.bin +3 -0
- runs/Jul12_05-28-20_9f2134707861/events.out.tfevents.1689139729.9f2134707861.1472.0 +3 -0
- sentencepiece.bpe.model +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
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
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": "AB",
|
15 |
+
"1": "AUX",
|
16 |
+
"2": "CC",
|
17 |
+
"3": "CD",
|
18 |
+
"4": "DBL",
|
19 |
+
"5": "DT",
|
20 |
+
"6": "ETC",
|
21 |
+
"7": "IN",
|
22 |
+
"8": "JJ",
|
23 |
+
"9": "KAN",
|
24 |
+
"10": "M",
|
25 |
+
"11": "NN",
|
26 |
+
"12": "PA",
|
27 |
+
"13": "PN",
|
28 |
+
"14": "PRO",
|
29 |
+
"15": "QT",
|
30 |
+
"16": "RB",
|
31 |
+
"17": "RPN",
|
32 |
+
"18": "SYM",
|
33 |
+
"19": "UH",
|
34 |
+
"20": "VB",
|
35 |
+
"21": "VB_JJ",
|
36 |
+
"22": "VCOM"
|
37 |
+
},
|
38 |
+
"initializer_range": 0.02,
|
39 |
+
"intermediate_size": 3072,
|
40 |
+
"label2id": {
|
41 |
+
"AB": 0,
|
42 |
+
"AUX": 1,
|
43 |
+
"CC": 2,
|
44 |
+
"CD": 3,
|
45 |
+
"DBL": 4,
|
46 |
+
"DT": 5,
|
47 |
+
"ETC": 6,
|
48 |
+
"IN": 7,
|
49 |
+
"JJ": 8,
|
50 |
+
"KAN": 9,
|
51 |
+
"M": 10,
|
52 |
+
"NN": 11,
|
53 |
+
"PA": 12,
|
54 |
+
"PN": 13,
|
55 |
+
"PRO": 14,
|
56 |
+
"QT": 15,
|
57 |
+
"RB": 16,
|
58 |
+
"RPN": 17,
|
59 |
+
"SYM": 18,
|
60 |
+
"UH": 19,
|
61 |
+
"VB": 20,
|
62 |
+
"VB_JJ": 21,
|
63 |
+
"VCOM": 22
|
64 |
+
},
|
65 |
+
"layer_norm_eps": 1e-05,
|
66 |
+
"max_position_embeddings": 514,
|
67 |
+
"model_type": "xlm-roberta",
|
68 |
+
"num_attention_heads": 12,
|
69 |
+
"num_hidden_layers": 12,
|
70 |
+
"output_past": true,
|
71 |
+
"pad_token_id": 1,
|
72 |
+
"position_embedding_type": "absolute",
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.30.2",
|
75 |
+
"type_vocab_size": 1,
|
76 |
+
"use_cache": true,
|
77 |
+
"vocab_size": 250002
|
78 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d6981352255a726ed67d27bec28a89350094d84a9b1749ef48130d08a090dd8
|
3 |
+
size 1109955693
|
runs/Jul12_05-28-20_9f2134707861/events.out.tfevents.1689139729.9f2134707861.1472.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f8fcbc3c0e2e22b21058481196485fbc1f1fffbe7819c012365547e78766e99
|
3 |
+
size 5266
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
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:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
|
3 |
+
size 17082758
|
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": 512,
|
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:ade1ca0da4c01dcd5685eaea7c6f46634b8a779a1ba806add0b12665d7503c1f
|
3 |
+
size 3963
|