Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- config.json +96 -0
- model.safetensors +3 -0
- runs/Jun15_07-08-09_2fa0329138e2/events.out.tfevents.1718435291.2fa0329138e2.1412.0 +3 -0
- runs/Jun15_07-09-43_2fa0329138e2/events.out.tfevents.1718435384.2fa0329138e2.5585.0 +3 -0
- runs/Jun15_07-10-35_2fa0329138e2/events.out.tfevents.1718435436.2fa0329138e2.5998.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -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 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/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": "O",
|
15 |
+
"1": "B_ORG",
|
16 |
+
"2": "B_PER",
|
17 |
+
"3": "B_LOC",
|
18 |
+
"4": "B_MEA",
|
19 |
+
"5": "I_DTM",
|
20 |
+
"6": "I_ORG",
|
21 |
+
"7": "E_ORG",
|
22 |
+
"8": "I_PER",
|
23 |
+
"9": "B_TTL",
|
24 |
+
"10": "E_PER",
|
25 |
+
"11": "B_DES",
|
26 |
+
"12": "E_LOC",
|
27 |
+
"13": "B_DTM",
|
28 |
+
"14": "B_NUM",
|
29 |
+
"15": "I_MEA",
|
30 |
+
"16": "E_DTM",
|
31 |
+
"17": "E_MEA",
|
32 |
+
"18": "I_LOC",
|
33 |
+
"19": "I_DES",
|
34 |
+
"20": "E_DES",
|
35 |
+
"21": "I_NUM",
|
36 |
+
"22": "E_NUM",
|
37 |
+
"23": "B_TRM",
|
38 |
+
"24": "B_BRN",
|
39 |
+
"25": "I_TRM",
|
40 |
+
"26": "E_TRM",
|
41 |
+
"27": "I_TTL",
|
42 |
+
"28": "I_BRN",
|
43 |
+
"29": "E_BRN",
|
44 |
+
"30": "E_TTL",
|
45 |
+
"31": "B_NAME"
|
46 |
+
},
|
47 |
+
"initializer_range": 0.02,
|
48 |
+
"intermediate_size": 3072,
|
49 |
+
"label2id": {
|
50 |
+
"B_BRN": 24,
|
51 |
+
"B_DES": 11,
|
52 |
+
"B_DTM": 13,
|
53 |
+
"B_LOC": 3,
|
54 |
+
"B_MEA": 4,
|
55 |
+
"B_NAME": 31,
|
56 |
+
"B_NUM": 14,
|
57 |
+
"B_ORG": 1,
|
58 |
+
"B_PER": 2,
|
59 |
+
"B_TRM": 23,
|
60 |
+
"B_TTL": 9,
|
61 |
+
"E_BRN": 29,
|
62 |
+
"E_DES": 20,
|
63 |
+
"E_DTM": 16,
|
64 |
+
"E_LOC": 12,
|
65 |
+
"E_MEA": 17,
|
66 |
+
"E_NUM": 22,
|
67 |
+
"E_ORG": 7,
|
68 |
+
"E_PER": 10,
|
69 |
+
"E_TRM": 26,
|
70 |
+
"E_TTL": 30,
|
71 |
+
"I_BRN": 28,
|
72 |
+
"I_DES": 19,
|
73 |
+
"I_DTM": 5,
|
74 |
+
"I_LOC": 18,
|
75 |
+
"I_MEA": 15,
|
76 |
+
"I_NUM": 21,
|
77 |
+
"I_ORG": 6,
|
78 |
+
"I_PER": 8,
|
79 |
+
"I_TRM": 25,
|
80 |
+
"I_TTL": 27,
|
81 |
+
"O": 0
|
82 |
+
},
|
83 |
+
"layer_norm_eps": 1e-05,
|
84 |
+
"max_position_embeddings": 514,
|
85 |
+
"model_type": "xlm-roberta",
|
86 |
+
"num_attention_heads": 12,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"output_past": true,
|
89 |
+
"pad_token_id": 1,
|
90 |
+
"position_embedding_type": "absolute",
|
91 |
+
"torch_dtype": "float32",
|
92 |
+
"transformers_version": "4.41.2",
|
93 |
+
"type_vocab_size": 1,
|
94 |
+
"use_cache": true,
|
95 |
+
"vocab_size": 250002
|
96 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aed011bcffa58c8ad4ec2a913682af04b8258cb971ede1f06cc3c37d42b0ede9
|
3 |
+
size 1109934712
|
runs/Jun15_07-08-09_2fa0329138e2/events.out.tfevents.1718435291.2fa0329138e2.1412.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:819bfd1ac4fb0f7b839ee701529a392ec900692596083dd5a661e8dfcd8bc033
|
3 |
+
size 4184
|
runs/Jun15_07-09-43_2fa0329138e2/events.out.tfevents.1718435384.2fa0329138e2.5585.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63834684dd11cd1b4a7b69e46fbc4f4e49d994005624f606128299b7449cde41
|
3 |
+
size 4184
|
runs/Jun15_07-10-35_2fa0329138e2/events.out.tfevents.1718435436.2fa0329138e2.5998.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b53a4f24cc9ea9ac0296e73ee4225035131bb4dccef4943c5985cd71a78bb6a2
|
3 |
+
size 7948
|
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 sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
|
3 |
+
size 17082832
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
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 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3ea4f46b8c1099208db51a142852948eb5cbb7d28f15e52bc8492f7eef42eaf
|
3 |
+
size 5112
|