Hugging Face's logo

mHossain
/
bengali_pos_v1

Token Classification
Transformers
TensorBoard
Safetensors
electra
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mHossain commited on
Commit
6826ede
•
1 Parent(s): 08c4fbc

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +116 -0
  2. model.safetensors +3 -0
  3. runs/Dec30_23-05-04_dd995e418ced/events.out.tfevents.1703977570.dd995e418ced.409.0 +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +58 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "csebuetnlp/banglabert",
3
+ "architectures": [
4
+ "ElectraForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "ADD",
14
+ "1": "AFX",
15
+ "2": "CC",
16
+ "3": "CD",
17
+ "4": "DT",
18
+ "5": "EX",
19
+ "6": "FW",
20
+ "7": "HYPH",
21
+ "8": "IN",
22
+ "9": "JJ",
23
+ "10": "JJR",
24
+ "11": "JJS",
25
+ "12": "LS",
26
+ "13": "MD",
27
+ "14": "NFP",
28
+ "15": "NN",
29
+ "16": "NNP",
30
+ "17": "NNPS",
31
+ "18": "NNS",
32
+ "19": "PDT",
33
+ "20": "POS",
34
+ "21": "PRP",
35
+ "22": "PRP$",
36
+ "23": "RB",
37
+ "24": "RBR",
38
+ "25": "RBS",
39
+ "26": "RP",
40
+ "27": "SYM",
41
+ "28": "TO",
42
+ "29": "UH",
43
+ "30": "VB",
44
+ "31": "VBD",
45
+ "32": "VBG",
46
+ "33": "VBN",
47
+ "34": "VBP",
48
+ "35": "VBZ",
49
+ "36": "WDT",
50
+ "37": "WP",
51
+ "38": "WP$",
52
+ "39": "WRB",
53
+ "40": "XX"
54
+ },
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 3072,
57
+ "label2id": {
58
+ "ADD": 0,
59
+ "AFX": 1,
60
+ "CC": 2,
61
+ "CD": 3,
62
+ "DT": 4,
63
+ "EX": 5,
64
+ "FW": 6,
65
+ "HYPH": 7,
66
+ "IN": 8,
67
+ "JJ": 9,
68
+ "JJR": 10,
69
+ "JJS": 11,
70
+ "LS": 12,
71
+ "MD": 13,
72
+ "NFP": 14,
73
+ "NN": 15,
74
+ "NNP": 16,
75
+ "NNPS": 17,
76
+ "NNS": 18,
77
+ "PDT": 19,
78
+ "POS": 20,
79
+ "PRP": 21,
80
+ "PRP$": 22,
81
+ "RB": 23,
82
+ "RBR": 24,
83
+ "RBS": 25,
84
+ "RP": 26,
85
+ "SYM": 27,
86
+ "TO": 28,
87
+ "UH": 29,
88
+ "VB": 30,
89
+ "VBD": 31,
90
+ "VBG": 32,
91
+ "VBN": 33,
92
+ "VBP": 34,
93
+ "VBZ": 35,
94
+ "WDT": 36,
95
+ "WP": 37,
96
+ "WP$": 38,
97
+ "WRB": 39,
98
+ "XX": 40
99
+ },
100
+ "layer_norm_eps": 1e-12,
101
+ "max_position_embeddings": 512,
102
+ "model_type": "electra",
103
+ "num_attention_heads": 12,
104
+ "num_hidden_layers": 12,
105
+ "pad_token_id": 0,
106
+ "position_embedding_type": "absolute",
107
+ "summary_activation": "gelu",
108
+ "summary_last_dropout": 0.1,
109
+ "summary_type": "first",
110
+ "summary_use_proj": true,
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.35.2",
113
+ "type_vocab_size": 2,
114
+ "use_cache": true,
115
+ "vocab_size": 32000
116
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779507b1dbe1facc0c36fc188f028e8a7fe322f05e7f00090563bc776e8e45d9
3
+ size 440257060
runs/Dec30_23-05-04_dd995e418ced/events.out.tfevents.1703977570.dd995e418ced.409.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70374f445bf27c60e0552ae8a70d789a1dacfac33e74ae955d1df894548e2ec
3
+ size 12405
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "full_tokenizer_file": null,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": false,
56
+ "tokenizer_class": "ElectraTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25489303b253a9b0154e2da9b8ae736e92330ca91cf9d2956f11a2134fab09bd
3
+ size 4536
vocab.txt ADDED
The diff for this file is too large to render. See raw diff