MSLacerda/attribute_mining_mslacerda
Browse files- README.md +77 -0
- config.json +130 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- runs/Jun04_02-55-04_c7cfbdc033d7/events.out.tfevents.1717469708.c7cfbdc033d7 +3 -0
- runs/Jun04_02-56-39_c7cfbdc033d7/events.out.tfevents.1717469803.c7cfbdc033d7 +3 -0
- runs/Jun04_02-56-39_c7cfbdc033d7/events.out.tfevents.1717471313.c7cfbdc033d7 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert/distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: attribute_minig_mslacerda
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# attribute_minig_mslacerda
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.3079
|
24 |
+
- Precision: 0.6199
|
25 |
+
- Recall: 0.5775
|
26 |
+
- F1: 0.5979
|
27 |
+
- Accuracy: 0.6640
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 512
|
48 |
+
- eval_batch_size: 128
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 12
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.0 | 3 | 1.6782 | 0.5377 | 0.5324 | 0.5350 | 0.5856 |
|
59 |
+
| No log | 2.0 | 6 | 1.6105 | 0.5505 | 0.5299 | 0.54 | 0.5943 |
|
60 |
+
| No log | 3.0 | 9 | 1.5469 | 0.5696 | 0.5399 | 0.5543 | 0.6084 |
|
61 |
+
| No log | 4.0 | 12 | 1.4938 | 0.5799 | 0.5457 | 0.5623 | 0.6198 |
|
62 |
+
| No log | 5.0 | 15 | 1.4528 | 0.5854 | 0.5441 | 0.5639 | 0.6264 |
|
63 |
+
| No log | 6.0 | 18 | 1.4109 | 0.5972 | 0.5578 | 0.5769 | 0.6381 |
|
64 |
+
| No log | 7.0 | 21 | 1.3794 | 0.6055 | 0.5633 | 0.5836 | 0.6465 |
|
65 |
+
| No log | 8.0 | 24 | 1.3563 | 0.6162 | 0.5678 | 0.5910 | 0.6523 |
|
66 |
+
| No log | 9.0 | 27 | 1.3380 | 0.6153 | 0.5683 | 0.5908 | 0.6550 |
|
67 |
+
| No log | 10.0 | 30 | 1.3226 | 0.6162 | 0.5712 | 0.5928 | 0.6592 |
|
68 |
+
| No log | 11.0 | 33 | 1.3120 | 0.6186 | 0.5749 | 0.5960 | 0.6628 |
|
69 |
+
| No log | 12.0 | 36 | 1.3079 | 0.6199 | 0.5775 | 0.5979 | 0.6640 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.41.2
|
75 |
+
- Pytorch 2.3.0+cu121
|
76 |
+
- Datasets 2.19.2
|
77 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Brand",
|
13 |
+
"1": "Item form",
|
14 |
+
"2": "Specialty",
|
15 |
+
"3": "Flavor",
|
16 |
+
"4": "Net content",
|
17 |
+
"5": "Pack size",
|
18 |
+
"6": "Roast type",
|
19 |
+
"7": "Caffeine content",
|
20 |
+
"8": "Machine type",
|
21 |
+
"9": "Container type",
|
22 |
+
"10": "Country",
|
23 |
+
"11": "Gender",
|
24 |
+
"12": "Model name",
|
25 |
+
"13": "Shoe type",
|
26 |
+
"14": "Color",
|
27 |
+
"15": "Size",
|
28 |
+
"16": "Material",
|
29 |
+
"17": "Closure",
|
30 |
+
"18": "Sport",
|
31 |
+
"19": "Age",
|
32 |
+
"20": "Waterproof",
|
33 |
+
"21": "Power source",
|
34 |
+
"22": "Cap",
|
35 |
+
"23": "Operation mode",
|
36 |
+
"24": "Firmness",
|
37 |
+
"25": "Animal",
|
38 |
+
"26": "Volume",
|
39 |
+
"27": "Scent",
|
40 |
+
"28": "Benefit",
|
41 |
+
"29": "Hair type",
|
42 |
+
"30": "Supplement type",
|
43 |
+
"31": "Health benefit",
|
44 |
+
"32": "Dosage",
|
45 |
+
"33": "Diet",
|
46 |
+
"34": "Supply size",
|
47 |
+
"35": "Administration type",
|
48 |
+
"36": "Load size",
|
49 |
+
"37": "Specific uses",
|
50 |
+
"38": "Skin type",
|
51 |
+
"39": "Tea variety",
|
52 |
+
"40": "Protection level",
|
53 |
+
"41": "Mask type",
|
54 |
+
"42": "Age range",
|
55 |
+
"43": "Reusability",
|
56 |
+
"44": "Layer",
|
57 |
+
"45": "Closure type",
|
58 |
+
"46": "Package type",
|
59 |
+
"47": "Certified grade",
|
60 |
+
"48": "Container",
|
61 |
+
"49": "Sub brand",
|
62 |
+
"50": "Cereal type"
|
63 |
+
},
|
64 |
+
"initializer_range": 0.02,
|
65 |
+
"label2id": {
|
66 |
+
"Administration type": 35,
|
67 |
+
"Age": 19,
|
68 |
+
"Age range": 42,
|
69 |
+
"Animal": 25,
|
70 |
+
"Benefit": 28,
|
71 |
+
"Brand": 0,
|
72 |
+
"Caffeine content": 7,
|
73 |
+
"Cap": 22,
|
74 |
+
"Cereal type": 50,
|
75 |
+
"Certified grade": 47,
|
76 |
+
"Closure": 17,
|
77 |
+
"Closure type": 45,
|
78 |
+
"Color": 14,
|
79 |
+
"Container": 48,
|
80 |
+
"Container type": 9,
|
81 |
+
"Country": 10,
|
82 |
+
"Diet": 33,
|
83 |
+
"Dosage": 32,
|
84 |
+
"Firmness": 24,
|
85 |
+
"Flavor": 3,
|
86 |
+
"Gender": 11,
|
87 |
+
"Hair type": 29,
|
88 |
+
"Health benefit": 31,
|
89 |
+
"Item form": 1,
|
90 |
+
"Layer": 44,
|
91 |
+
"Load size": 36,
|
92 |
+
"Machine type": 8,
|
93 |
+
"Mask type": 41,
|
94 |
+
"Material": 16,
|
95 |
+
"Model name": 12,
|
96 |
+
"Net content": 4,
|
97 |
+
"Operation mode": 23,
|
98 |
+
"Pack size": 5,
|
99 |
+
"Package type": 46,
|
100 |
+
"Power source": 21,
|
101 |
+
"Protection level": 40,
|
102 |
+
"Reusability": 43,
|
103 |
+
"Roast type": 6,
|
104 |
+
"Scent": 27,
|
105 |
+
"Shoe type": 13,
|
106 |
+
"Size": 15,
|
107 |
+
"Skin type": 38,
|
108 |
+
"Specialty": 2,
|
109 |
+
"Specific uses": 37,
|
110 |
+
"Sport": 18,
|
111 |
+
"Sub brand": 49,
|
112 |
+
"Supplement type": 30,
|
113 |
+
"Supply size": 34,
|
114 |
+
"Tea variety": 39,
|
115 |
+
"Volume": 26,
|
116 |
+
"Waterproof": 20
|
117 |
+
},
|
118 |
+
"max_position_embeddings": 512,
|
119 |
+
"model_type": "distilbert",
|
120 |
+
"n_heads": 12,
|
121 |
+
"n_layers": 6,
|
122 |
+
"pad_token_id": 0,
|
123 |
+
"qa_dropout": 0.1,
|
124 |
+
"seq_classif_dropout": 0.2,
|
125 |
+
"sinusoidal_pos_embds": false,
|
126 |
+
"tie_weights_": true,
|
127 |
+
"torch_dtype": "float32",
|
128 |
+
"transformers_version": "4.41.2",
|
129 |
+
"vocab_size": 30522
|
130 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb7bbb00792e6f5d7827b1d0ed9e788e5be03e6d3127ab695656240f12402442
|
3 |
+
size 265620748
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:446eab74a72ac8b3468b3937c6538088c54463a89de054c90a8ed4de037412c3
|
3 |
+
size 265649442
|
runs/Jun04_02-55-04_c7cfbdc033d7/events.out.tfevents.1717469708.c7cfbdc033d7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e06b292488328ff27560d92b2a5e125840cd7448d998e27ecc5724b4d700a50
|
3 |
+
size 16358
|
runs/Jun04_02-56-39_c7cfbdc033d7/events.out.tfevents.1717469803.c7cfbdc033d7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47c5d7b8eeb49668b49488bbd4f90c47eb6a5924a81ba823976353200e240011
|
3 |
+
size 12966
|
runs/Jun04_02-56-39_c7cfbdc033d7/events.out.tfevents.1717471313.c7cfbdc033d7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45432b251acb2d68074c1c6f63b838c84d16e0c909ba2d2273acf235da0abad4
|
3 |
+
size 503
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0367ac454c92d5b2220f6515aaadcf8eabdad96e83eddca3cb1d02fe6b531542
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|