arbitropy commited on
Commit
254342c
1 Parent(s): 72b8c5f

Training in progress, step 2000

Browse files
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: csebuetnlp/banglabert
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bert-finetuned-ner-bangla
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # bert-finetuned-ner-bangla
14
+
15
+ This model is a fine-tuned version of [csebuetnlp/banglabert](https://huggingface.co/csebuetnlp/banglabert) on the None dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 2e-05
35
+ - train_batch_size: 64
36
+ - eval_batch_size: 64
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 2
41
+
42
+ ### Training results
43
+
44
+
45
+
46
+ ### Framework versions
47
+
48
+ - Transformers 4.37.2
49
+ - Pytorch 2.1.1+cu121
50
+ - Datasets 2.16.1
51
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "B-LOC": 3,
14
+ "B-OBJ": 14,
15
+ "B-ORG": 2,
16
+ "B-PER": 6,
17
+ "E-LOC": 7,
18
+ "E-OBJ": 9,
19
+ "E-ORG": 0,
20
+ "E-PER": 10,
21
+ "I-LOC": 13,
22
+ "I-ORG": 8,
23
+ "I-PER": 12,
24
+ "O": 4,
25
+ "S-LOC": 15,
26
+ "S-OBJ": 1,
27
+ "S-ORG": 5,
28
+ "S-PER": 11
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "label2id": {
33
+ "0": "E-ORG",
34
+ "1": "S-OBJ",
35
+ "2": "B-ORG",
36
+ "3": "B-LOC",
37
+ "4": "O",
38
+ "5": "S-ORG",
39
+ "6": "B-PER",
40
+ "7": "E-LOC",
41
+ "8": "I-ORG",
42
+ "9": "E-OBJ",
43
+ "10": "E-PER",
44
+ "11": "S-PER",
45
+ "12": "I-PER",
46
+ "13": "I-LOC",
47
+ "14": "B-OBJ",
48
+ "15": "S-LOC"
49
+ },
50
+ "layer_norm_eps": 1e-12,
51
+ "max_position_embeddings": 512,
52
+ "model_type": "electra",
53
+ "num_attention_heads": 12,
54
+ "num_hidden_layers": 12,
55
+ "pad_token_id": 0,
56
+ "position_embedding_type": "absolute",
57
+ "summary_activation": "gelu",
58
+ "summary_last_dropout": 0.1,
59
+ "summary_type": "first",
60
+ "summary_use_proj": true,
61
+ "torch_dtype": "float32",
62
+ "transformers_version": "4.37.2",
63
+ "type_vocab_size": 2,
64
+ "use_cache": true,
65
+ "vocab_size": 32000
66
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa445371dcc86b6159229581d21bdd4d3c06d2fb74450ab99a58b16e6a6b4b88
3
+ size 440180144
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:cd52f0b2496dd2ba2b4bce0d8a5e4941f422a689deed8cae27520f3236550b79
3
+ size 4728
vocab.txt ADDED
The diff for this file is too large to render. See raw diff