Upload folder using huggingface_hub
Browse files- README.md +18 -0
- config.json +67 -0
- model.safetensors +3 -0
- runs/Dec29_12-47-41_1cb62388f39c/events.out.tfevents.1735476465.1cb62388f39c.246.0 +2 -2
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- token-classification
|
6 |
+
base_model: distilbert/distilbert-base-uncased
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
datasets:
|
10 |
+
- disham993/ElectricalNER
|
11 |
+
---
|
12 |
+
|
13 |
+
# Model Trained Using AutoTrain
|
14 |
+
|
15 |
+
- Problem type: Token Classification
|
16 |
+
|
17 |
+
## Validation Metrics
|
18 |
+
No validation metrics available
|
config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
3 |
+
"_num_labels": 19,
|
4 |
+
"activation": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"DistilBertForTokenClassification"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"dim": 768,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-COMPONENT",
|
15 |
+
"2": "I-COMPONENT",
|
16 |
+
"3": "B-DESIGN_PARAM",
|
17 |
+
"4": "I-DESIGN_PARAM",
|
18 |
+
"5": "B-MATERIAL",
|
19 |
+
"6": "I-MATERIAL",
|
20 |
+
"7": "B-EQUIPMENT",
|
21 |
+
"8": "I-EQUIPMENT",
|
22 |
+
"9": "B-TECHNOLOGY",
|
23 |
+
"10": "I-TECHNOLOGY",
|
24 |
+
"11": "B-SOFTWARE",
|
25 |
+
"12": "I-SOFTWARE",
|
26 |
+
"13": "B-STANDARD",
|
27 |
+
"14": "I-STANDARD",
|
28 |
+
"15": "B-VENDOR",
|
29 |
+
"16": "I-VENDOR",
|
30 |
+
"17": "B-PRODUCT",
|
31 |
+
"18": "I-PRODUCT"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"label2id": {
|
35 |
+
"B-COMPONENT": 1,
|
36 |
+
"B-DESIGN_PARAM": 3,
|
37 |
+
"B-EQUIPMENT": 7,
|
38 |
+
"B-MATERIAL": 5,
|
39 |
+
"B-PRODUCT": 17,
|
40 |
+
"B-SOFTWARE": 11,
|
41 |
+
"B-STANDARD": 13,
|
42 |
+
"B-TECHNOLOGY": 9,
|
43 |
+
"B-VENDOR": 15,
|
44 |
+
"I-COMPONENT": 2,
|
45 |
+
"I-DESIGN_PARAM": 4,
|
46 |
+
"I-EQUIPMENT": 8,
|
47 |
+
"I-MATERIAL": 6,
|
48 |
+
"I-PRODUCT": 18,
|
49 |
+
"I-SOFTWARE": 12,
|
50 |
+
"I-STANDARD": 14,
|
51 |
+
"I-TECHNOLOGY": 10,
|
52 |
+
"I-VENDOR": 16,
|
53 |
+
"O": 0
|
54 |
+
},
|
55 |
+
"max_position_embeddings": 512,
|
56 |
+
"model_type": "distilbert",
|
57 |
+
"n_heads": 12,
|
58 |
+
"n_layers": 6,
|
59 |
+
"pad_token_id": 0,
|
60 |
+
"qa_dropout": 0.1,
|
61 |
+
"seq_classif_dropout": 0.2,
|
62 |
+
"sinusoidal_pos_embds": false,
|
63 |
+
"tie_weights_": true,
|
64 |
+
"torch_dtype": "float32",
|
65 |
+
"transformers_version": "4.47.1",
|
66 |
+
"vocab_size": 30522
|
67 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5245ec3367607714156189a6eeb6704c3ab7da1691d60106929f90fb18ff959f
|
3 |
+
size 265522308
|
runs/Dec29_12-47-41_1cb62388f39c/events.out.tfevents.1735476465.1cb62388f39c.246.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:492ff08216ea3e7d7405de1056d729a61ac279e3d24a00bf9c0b0c430c2db7b7
|
3 |
+
size 44373
|
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 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f878604dec8cbd0beca11e9dbf4ee8ce4bbda93137b40f97642cbe489cfb1e40
|
3 |
+
size 5304
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "disham993/ElectricalNER",
|
3 |
+
"model": "distilbert/distilbert-base-uncased",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": null,
|
17 |
+
"tokens_column": "tokens",
|
18 |
+
"tags_column": "ner_tags",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "bert-electrical-ner",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "yasserrmd",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|