Commit
·
2fd76c6
1
Parent(s):
b63b569
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +53 -0
- pytorch_model.bin +3 -0
- runs/Mar02_00-52-19_home-3090/1677696755.4427788/events.out.tfevents.1677696755.home-3090.10497.1 +3 -0
- runs/Mar02_00-52-19_home-3090/events.out.tfevents.1677696755.home-3090.10497.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "0",
|
14 |
+
"1": "1-5_err",
|
15 |
+
"2": "2_err",
|
16 |
+
"3": "begin_err",
|
17 |
+
"4": "del_err",
|
18 |
+
"5": "end_err",
|
19 |
+
"6": "one_word_err",
|
20 |
+
"7": "punc_insert_err"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"0": 0,
|
26 |
+
"1-5_err": 1,
|
27 |
+
"2_err": 2,
|
28 |
+
"begin_err": 3,
|
29 |
+
"del_err": 4,
|
30 |
+
"end_err": 5,
|
31 |
+
"one_word_err": 6,
|
32 |
+
"punc_insert_err": 7
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-12,
|
35 |
+
"max_position_embeddings": 512,
|
36 |
+
"model_type": "electra",
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_layers": 12,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"position_embedding_type": "absolute",
|
41 |
+
"summary_activation": "gelu",
|
42 |
+
"summary_last_dropout": 0.1,
|
43 |
+
"summary_type": "first",
|
44 |
+
"summary_use_proj": true,
|
45 |
+
"task_specific_params": {
|
46 |
+
"finetuned": true
|
47 |
+
},
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.25.1",
|
50 |
+
"type_vocab_size": 2,
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 32000
|
53 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f97a01ef0c9cf5ab55573541c020f69350a7193a786138e1d42112eb77868c8c
|
3 |
+
size 440204333
|
runs/Mar02_00-52-19_home-3090/1677696755.4427788/events.out.tfevents.1677696755.home-3090.10497.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8bf6299c1d0525eedb70e1597df4b2e62c0c56dddf30ebc5cc8b5027450c264
|
3 |
+
size 5523
|
runs/Mar02_00-52-19_home-3090/events.out.tfevents.1677696755.home-3090.10497.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1742bc5d4aba5e70528f4e198c1c689ef0f96d6e80ae9bc033035a52959d4dd5
|
3 |
+
size 7325
|
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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"full_tokenizer_file": null,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"name_or_path": "csebuetnlp/banglabert",
|
9 |
+
"never_split": null,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": false,
|
15 |
+
"tokenizer_class": "ElectraTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12bde5271ad8217a9a362972db9ad2e96ed8d1769894d3a041c4e9d7e28af643
|
3 |
+
size 3387
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|