denizspynk
commited on
Commit
·
c14d651
1
Parent(s):
90d1e6b
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +59 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pdelobelle/robbert-v2-dutch-ner",
|
3 |
+
"_num_labels": 9,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "B-Actor",
|
17 |
+
"2": "I-Actor",
|
18 |
+
"3": "B-COTS",
|
19 |
+
"4": "I-COTS",
|
20 |
+
"5": "B-Function",
|
21 |
+
"6": "I-Function",
|
22 |
+
"7": "B-Result",
|
23 |
+
"8": "I-Result",
|
24 |
+
"9": "B-Entity",
|
25 |
+
"10": "I-Entity",
|
26 |
+
"11": "B-Attribute",
|
27 |
+
"12": "I-Attribute"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"B-Actor": 1,
|
33 |
+
"B-Attribute": 11,
|
34 |
+
"B-COTS": 3,
|
35 |
+
"B-Entity": 9,
|
36 |
+
"B-Function": 5,
|
37 |
+
"B-Result": 7,
|
38 |
+
"I-Actor": 2,
|
39 |
+
"I-Attribute": 12,
|
40 |
+
"I-COTS": 4,
|
41 |
+
"I-Entity": 10,
|
42 |
+
"I-Function": 6,
|
43 |
+
"I-Result": 8,
|
44 |
+
"O": 0
|
45 |
+
},
|
46 |
+
"layer_norm_eps": 1e-05,
|
47 |
+
"max_position_embeddings": 514,
|
48 |
+
"model_type": "roberta",
|
49 |
+
"num_attention_heads": 12,
|
50 |
+
"num_hidden_layers": 12,
|
51 |
+
"output_past": true,
|
52 |
+
"pad_token_id": 1,
|
53 |
+
"position_embedding_type": "absolute",
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.24.0",
|
56 |
+
"type_vocab_size": 1,
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 40000
|
59 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b25dde1fade9a57569dbee08003ed4f82dd38a856f2531427846a9d2d026e1d9
|
3 |
+
size 464796013
|
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
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"do_lower_case": false,
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
9 |
+
"name_or_path": "pdelobelle/robbert-v2-dutch-ner",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"special_tokens_map_file": "/Users/denizayhan/.cache/huggingface/hub/models--pdelobelle--robbert-v2-dutch-ner/snapshots/cbe384104e418a84b62a102e1aa61f75857ed20e/special_tokens_map.json",
|
13 |
+
"tokenizer_class": "RobertaTokenizer",
|
14 |
+
"trim_offsets": true,
|
15 |
+
"unk_token": "<unk>"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0e392bc7f15548c9d144d112817818fe32d2e7eb0cac282d43f7a6b523f4eb5
|
3 |
+
size 3387
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|