Deojoandco
commited on
Commit
•
6fde48a
1
Parent(s):
63acaff
Training in progress, epoch 1
Browse files- added_tokens.json +11 -0
- config.json +50 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +89 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 1,
|
3 |
+
"<EOS>": 50359,
|
4 |
+
"<SEP2>": 50358,
|
5 |
+
"<pad>": 0,
|
6 |
+
"<s>": 2,
|
7 |
+
"<unk>": 100,
|
8 |
+
"[CLS]": 65,
|
9 |
+
"[MASK]": 67,
|
10 |
+
"[SEP]": 66
|
11 |
+
}
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bigbird-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"BigBirdForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"attention_type": "block_sparse",
|
8 |
+
"block_size": 64,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"classifier_dropout": null,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"gradient_checkpointing": false,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "C",
|
18 |
+
"1": "M",
|
19 |
+
"2": "N",
|
20 |
+
"3": "O",
|
21 |
+
"4": "OB",
|
22 |
+
"5": "W"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"C": 0,
|
28 |
+
"M": 1,
|
29 |
+
"N": 2,
|
30 |
+
"O": 3,
|
31 |
+
"OB": 4,
|
32 |
+
"W": 5
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-12,
|
35 |
+
"max_position_embeddings": 4096,
|
36 |
+
"model_type": "big_bird",
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_layers": 12,
|
39 |
+
"num_random_blocks": 3,
|
40 |
+
"pad_token_id": 0,
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"rescale_embeddings": false,
|
43 |
+
"sep_token_id": 66,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.34.0",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"use_bias": true,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 50360
|
50 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e83e56351ec9d66cd68824787f86701460e92e82b68c0914f34dba77b3e9131
|
3 |
+
size 509968558
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "</s>",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "<EOS>",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "<SEP2>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdc81e1fc9d42e0c08b86d5b280d05d7c5e9747c4231c648f2b56b8e1d893c82
|
3 |
+
size 845731
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"65": {
|
29 |
+
"content": "[CLS]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"66": {
|
37 |
+
"content": "[SEP]",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"67": {
|
45 |
+
"content": "[MASK]",
|
46 |
+
"lstrip": true,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"100": {
|
53 |
+
"content": "<unk>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"50358": {
|
61 |
+
"content": "<SEP2>",
|
62 |
+
"lstrip": true,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": true,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"50359": {
|
69 |
+
"content": "<EOS>",
|
70 |
+
"lstrip": true,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": true,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
}
|
76 |
+
},
|
77 |
+
"additional_special_tokens": [],
|
78 |
+
"bos_token": "</s>",
|
79 |
+
"clean_up_tokenization_spaces": true,
|
80 |
+
"cls_token": "[CLS]",
|
81 |
+
"eos_token": "<EOS>",
|
82 |
+
"mask_token": "[MASK]",
|
83 |
+
"model_max_length": 4096,
|
84 |
+
"pad_token": "<pad>",
|
85 |
+
"sep_token": "<SEP2>",
|
86 |
+
"sp_model_kwargs": {},
|
87 |
+
"tokenizer_class": "BigBirdTokenizer",
|
88 |
+
"unk_token": "<unk>"
|
89 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c4f07efe282a2d66bda0c9b381f03e49d20dfbb53fd93196347ca1256c1a6fd
|
3 |
+
size 4536
|