muhtasham commited on
Commit
677e4fd
·
1 Parent(s): 4602c46

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "muhtasham/tiny-mlm-tweet",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
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
+ "intermediate_size": 512,
24
+ "label2id": {
25
+ "B-LOC": "5",
26
+ "B-MISC": "7",
27
+ "B-ORG": "3",
28
+ "B-PER": "1",
29
+ "I-LOC": "6",
30
+ "I-MISC": "8",
31
+ "I-ORG": "4",
32
+ "I-PER": "2",
33
+ "O": "0"
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 2,
39
+ "num_hidden_layers": 2,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.26.0.dev0",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 30522
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:133f5a5cb97546fc6e29994a71950a0b04dc3ecafa92b48dd93d6f6ea55109b6
3
+ size 17499497
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "name_or_path": "muhtasham/tiny-mlm-tweet",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cbb59e05f5bba3b9a301b3edf303bf4b7023de291cab3737f589ab25217907f
3
+ size 3515
vocab.txt ADDED
The diff for this file is too large to render. See raw diff