Hasanmurad commited on
Commit
6a13990
1 Parent(s): e088320

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "O",
14
+ "1": "H-NUM",
15
+ "2": "R-NUM",
16
+ "3": "A-NAME",
17
+ "4": "P-STA",
18
+ "5": "D-NAME"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "A-NAME": 3,
24
+ "D-NAME": 5,
25
+ "H-NUM": 1,
26
+ "O": 0,
27
+ "P-STA": 4,
28
+ "R-NUM": 2
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "electra",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "pad_token_id": 0,
36
+ "position_embedding_type": "absolute",
37
+ "summary_activation": "gelu",
38
+ "summary_last_dropout": 0.1,
39
+ "summary_type": "first",
40
+ "summary_use_proj": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.31.0",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 32000
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bafa064ad15ace45b5874677519fb6eca29658e93aae7abea44bcfbed690a37
3
+ size 440193769
runs/Jul19_16-16-51_4e174d8f5be9/events.out.tfevents.1689783420.4e174d8f5be9.7123.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28fb044ceab8e90d958d9689a7629fe1dc8638c07b894807245c080356a14fee
3
+ size 5884
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
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "full_tokenizer_file": null,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": false,
14
+ "tokenizer_class": "ElectraTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5186acf0daa2e434cce2640d8f55e8f7d38bb892fd7626e2eb6f578e144fdcf2
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff