dmargutierrez
commited on
Commit
•
65d8b62
1
Parent(s):
2acfbdd
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +47 -0
- pytorch_model.bin +3 -0
- runs/Mar21_14-44-20_t1-45-bhs5/1679409867.0914018/events.out.tfevents.1679409867.t1-45-bhs5.2312.1 +3 -0
- runs/Mar21_14-44-20_t1-45-bhs5/events.out.tfevents.1679409867.t1-45-bhs5.2312.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-multilingual-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B-PER",
|
14 |
+
"2": "I-PER",
|
15 |
+
"3": "B-ORG",
|
16 |
+
"4": "I-ORG",
|
17 |
+
"5": "B-LOC",
|
18 |
+
"6": "I-LOC",
|
19 |
+
"7": "B-MISC",
|
20 |
+
"8": "I-MISC"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"label2id": {
|
24 |
+
"B-LOC": 5,
|
25 |
+
"B-MISC": 7,
|
26 |
+
"B-ORG": 3,
|
27 |
+
"B-PER": 1,
|
28 |
+
"I-LOC": 6,
|
29 |
+
"I-MISC": 8,
|
30 |
+
"I-ORG": 4,
|
31 |
+
"I-PER": 2,
|
32 |
+
"O": 0
|
33 |
+
},
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "distilbert",
|
36 |
+
"n_heads": 12,
|
37 |
+
"n_layers": 6,
|
38 |
+
"output_past": true,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"qa_dropout": 0.1,
|
41 |
+
"seq_classif_dropout": 0.2,
|
42 |
+
"sinusoidal_pos_embds": false,
|
43 |
+
"tie_weights_": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.26.0",
|
46 |
+
"vocab_size": 119547
|
47 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c9744af18e5d419938f564b8d6e9b1060a81589880f06cadd32e71d7208abe6
|
3 |
+
size 538997413
|
runs/Mar21_14-44-20_t1-45-bhs5/1679409867.0914018/events.out.tfevents.1679409867.t1-45-bhs5.2312.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14f75bccd1a7ddb10fd219c5bfc88b80f978d4e1c1f92710a3d92630a75fd580
|
3 |
+
size 5761
|
runs/Mar21_14-44-20_t1-45-bhs5/events.out.tfevents.1679409867.t1-45-bhs5.2312.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:368d8f1345e763ec8013ceac13e9bbe536816c73a0b1f32993afd3d9eb844ebb
|
3 |
+
size 20872
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "distilbert-base-multilingual-cased",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f19c3623de963e7598cd8b25f16e2867b998fd7c404213079196da4546ec1f42
|
3 |
+
size 3579
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|