durgaamma2005
commited on
Commit
•
329195d
1
Parent(s):
609b717
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +41 -0
- pytorch_model.bin +3 -0
- runs/Jan02_16-54-02_c9910fdfa250/1641142466.855337/events.out.tfevents.1641142466.c9910fdfa250.72.1 +3 -0
- runs/Jan02_16-54-02_c9910fdfa250/events.out.tfevents.1641142466.c9910fdfa250.72.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "neuralspace-reverie/indic-transformers-te-distilbert",
|
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 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"label2id": {
|
22 |
+
"B-LOC": "5",
|
23 |
+
"B-ORG": "3",
|
24 |
+
"B-PER": "1",
|
25 |
+
"I-LOC": "6",
|
26 |
+
"I-ORG": "4",
|
27 |
+
"I-PER": "2",
|
28 |
+
"O": "0"
|
29 |
+
},
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "distilbert",
|
32 |
+
"n_heads": 12,
|
33 |
+
"n_layers": 6,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"qa_dropout": 0.1,
|
36 |
+
"seq_classif_dropout": 0.2,
|
37 |
+
"sinusoidal_pos_embds": false,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.15.0",
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f786f8247adfb865df24daa9cbf545197a810e74d8916225fada3f83830049b
|
3 |
+
size 265512437
|
runs/Jan02_16-54-02_c9910fdfa250/1641142466.855337/events.out.tfevents.1641142466.c9910fdfa250.72.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0bce7766df4d20bc447fbe4448969cc04138431529f529619bbafe0f84f543e
|
3 |
+
size 4833
|
runs/Jan02_16-54-02_c9910fdfa250/events.out.tfevents.1641142466.c9910fdfa250.72.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4b663047df5e0eaf5d97a2bd408afaab472d2da264b54029689989388090344
|
3 |
+
size 4014
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/6e7c33ead33f6dffc08645e398053d701c75a246182bf499b2b24d3760d8e63b.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "neuralspace-reverie/indic-transformers-te-distilbert", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4941b3b35be82ab87ca26d9e2a9da7a13c2d8de4494f0e3718a140511286d9a1
|
3 |
+
size 2991
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|