Model save
Browse files- README.md +50 -1
- config.json +101 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,52 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
base_model: ijazulhaq/bert-base-pashto
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: pashto-pos
|
8 |
+
results: []
|
9 |
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# pashto-pos
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [ijazulhaq/bert-base-pashto](https://huggingface.co/ijazulhaq/bert-base-pashto) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0002
|
36 |
+
- train_batch_size: 16
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 4
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.33.0
|
50 |
+
- Pytorch 2.0.0
|
51 |
+
- Datasets 2.1.0
|
52 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ijazulhaq/bert-base-pashto",
|
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": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "BA",
|
13 |
+
"1": "CC",
|
14 |
+
"2": "DT",
|
15 |
+
"3": "FX",
|
16 |
+
"4": "IN",
|
17 |
+
"5": "JJ",
|
18 |
+
"6": "NB",
|
19 |
+
"7": "NG",
|
20 |
+
"8": "NNF",
|
21 |
+
"9": "NNM",
|
22 |
+
"10": "NNP",
|
23 |
+
"11": "NNS",
|
24 |
+
"12": "PRC",
|
25 |
+
"13": "PRDEM",
|
26 |
+
"14": "PRDIS",
|
27 |
+
"15": "PRP$",
|
28 |
+
"16": "PRPi",
|
29 |
+
"17": "PRPii",
|
30 |
+
"18": "PRPiii",
|
31 |
+
"19": "PRW",
|
32 |
+
"20": "PT",
|
33 |
+
"21": "PU",
|
34 |
+
"22": "RB",
|
35 |
+
"23": "RP",
|
36 |
+
"24": "UH",
|
37 |
+
"25": "VBD",
|
38 |
+
"26": "VBDC",
|
39 |
+
"27": "VBDX",
|
40 |
+
"28": "VBG",
|
41 |
+
"29": "VBH",
|
42 |
+
"30": "VBIMP",
|
43 |
+
"31": "VBINF",
|
44 |
+
"32": "VBN",
|
45 |
+
"33": "VBP",
|
46 |
+
"34": "VBPC",
|
47 |
+
"35": "VBPX"
|
48 |
+
},
|
49 |
+
"initializer_range": 0.02,
|
50 |
+
"intermediate_size": 3072,
|
51 |
+
"label2id": {
|
52 |
+
"BA": 0,
|
53 |
+
"CC": 1,
|
54 |
+
"DT": 2,
|
55 |
+
"FX": 3,
|
56 |
+
"IN": 4,
|
57 |
+
"JJ": 5,
|
58 |
+
"NB": 6,
|
59 |
+
"NG": 7,
|
60 |
+
"NNF": 8,
|
61 |
+
"NNM": 9,
|
62 |
+
"NNP": 10,
|
63 |
+
"NNS": 11,
|
64 |
+
"PRC": 12,
|
65 |
+
"PRDEM": 13,
|
66 |
+
"PRDIS": 14,
|
67 |
+
"PRP$": 15,
|
68 |
+
"PRPi": 16,
|
69 |
+
"PRPii": 17,
|
70 |
+
"PRPiii": 18,
|
71 |
+
"PRW": 19,
|
72 |
+
"PT": 20,
|
73 |
+
"PU": 21,
|
74 |
+
"RB": 22,
|
75 |
+
"RP": 23,
|
76 |
+
"UH": 24,
|
77 |
+
"VBD": 25,
|
78 |
+
"VBDC": 26,
|
79 |
+
"VBDX": 27,
|
80 |
+
"VBG": 28,
|
81 |
+
"VBH": 29,
|
82 |
+
"VBIMP": 30,
|
83 |
+
"VBINF": 31,
|
84 |
+
"VBN": 32,
|
85 |
+
"VBP": 33,
|
86 |
+
"VBPC": 34,
|
87 |
+
"VBPX": 35
|
88 |
+
},
|
89 |
+
"layer_norm_eps": 1e-12,
|
90 |
+
"max_position_embeddings": 512,
|
91 |
+
"model_type": "bert",
|
92 |
+
"num_attention_heads": 12,
|
93 |
+
"num_hidden_layers": 12,
|
94 |
+
"pad_token_id": 0,
|
95 |
+
"position_embedding_type": "absolute",
|
96 |
+
"torch_dtype": "float32",
|
97 |
+
"transformers_version": "4.33.0",
|
98 |
+
"type_vocab_size": 2,
|
99 |
+
"use_cache": true,
|
100 |
+
"vocab_size": 30000
|
101 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:502b2bf5e077a2f2047d93346690a43ac4d39b2f1a3e364e01b2981b38fcc21e
|
3 |
+
size 434141481
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8ee59fcecf60b285972f43215c2f1cc5d29e11baa62fa907144a77bfaa9ad3e
|
3 |
+
size 4027
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|