junaidamk commited on
Commit
83b22cb
·
1 Parent(s): 80e0be9

Training in progress, step 10000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/muril-base-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
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": "B-DATE",
14
+ "1": "B-EVENT",
15
+ "2": "B-LOC",
16
+ "3": "B-MEAS",
17
+ "4": "B-ORG",
18
+ "5": "B-PER",
19
+ "6": "B-PRO",
20
+ "7": "I-DATE",
21
+ "8": "I-EVENT",
22
+ "9": "I-LOC",
23
+ "10": "I-MEAS",
24
+ "11": "I-ORG",
25
+ "12": "I-PER",
26
+ "13": "I-PRO",
27
+ "14": "O"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "label2id": {
32
+ "B-DATE": 0,
33
+ "B-EVENT": 1,
34
+ "B-LOC": 2,
35
+ "B-MEAS": 3,
36
+ "B-ORG": 4,
37
+ "B-PER": 5,
38
+ "B-PRO": 6,
39
+ "I-DATE": 7,
40
+ "I-EVENT": 8,
41
+ "I-LOC": 9,
42
+ "I-MEAS": 10,
43
+ "I-ORG": 11,
44
+ "I-PER": 12,
45
+ "I-PRO": 13,
46
+ "O": 14
47
+ },
48
+ "layer_norm_eps": 1e-12,
49
+ "max_position_embeddings": 512,
50
+ "model_type": "bert",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 12,
53
+ "pad_token_id": 0,
54
+ "position_embedding_type": "absolute",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.18.0",
57
+ "type_vocab_size": 2,
58
+ "use_cache": true,
59
+ "vocab_size": 197285
60
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08066e7a6a2b7f9c3663da56d0e82d859fafb473cb8fad5868843468d5c497d6
3
+ size 947979057
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"pad_token": "[PAD]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"special_tokens_map_file": "/content/drive/MyDrive/Malayalam-for-tokenizer/Malayalam_tokenizer/my-new-tokenizer-bert/special_tokens_map.json", "name_or_path": "junaidamk/ml-wptokenizer", "tokenizer_class": "PreTrainedTokenizerFast"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70452fd132ead97b182a3681cfae96a3ee01be9a36b6a6204e6413ef4288ea54
3
+ size 3055