End of training
Browse files- README.md +75 -0
- config.json +146 -0
- model.safetensors +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 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: uniBERT.distilBERT.2
|
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 |
+
# uniBERT.distilBERT.2
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.6169
|
24 |
+
- Accuracy: (0.5361930294906166,)
|
25 |
+
- F1: (0.5387444240059887,)
|
26 |
+
- Precision: (0.5567514462203529,)
|
27 |
+
- Recall: 0.5362
|
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: 16
|
48 |
+
- eval_batch_size: 64
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 10
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:----------------------:|:----------------------:|:------:|
|
58 |
+
| 3.0538 | 1.0 | 187 | 2.7787 | (0.225201072386059,) | (0.18836848263830908,) | (0.3149708790620786,) | 0.2252 |
|
59 |
+
| 2.198 | 2.0 | 374 | 2.2031 | (0.3753351206434316,) | (0.3631236683415291,) | (0.42784864295242175,) | 0.3753 |
|
60 |
+
| 1.7009 | 3.0 | 561 | 1.9210 | (0.4410187667560322,) | (0.4323447164030645,) | (0.46798465231264463,) | 0.4410 |
|
61 |
+
| 1.3871 | 4.0 | 748 | 1.7879 | (0.47050938337801607,) | (0.46788445138156415,) | (0.4993274459424259,) | 0.4705 |
|
62 |
+
| 1.0832 | 5.0 | 935 | 1.7004 | (0.5067024128686327,) | (0.5103273615495704,) | (0.5379322201073571,) | 0.5067 |
|
63 |
+
| 0.8772 | 6.0 | 1122 | 1.6449 | (0.5120643431635389,) | (0.5113608061573298,) | (0.534501997594668,) | 0.5121 |
|
64 |
+
| 0.695 | 7.0 | 1309 | 1.6427 | (0.5254691689008043,) | (0.5284135185976587,) | (0.5461241615837267,) | 0.5255 |
|
65 |
+
| 0.5712 | 8.0 | 1496 | 1.6336 | (0.5241286863270778,) | (0.5266745245913999,) | (0.5544118981578735,) | 0.5241 |
|
66 |
+
| 0.5588 | 9.0 | 1683 | 1.6163 | (0.5348525469168901,) | (0.5375963439943585,) | (0.5584699977736378,) | 0.5349 |
|
67 |
+
| 0.4567 | 10.0 | 1870 | 1.6169 | (0.5361930294906166,) | (0.5387444240059887,) | (0.5567514462203529,) | 0.5362 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.39.3
|
73 |
+
- Pytorch 2.2.1+cu121
|
74 |
+
- Datasets 2.18.0
|
75 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "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": "O",
|
13 |
+
"1": "B-1",
|
14 |
+
"2": "I-1",
|
15 |
+
"3": "B-2",
|
16 |
+
"4": "I-2",
|
17 |
+
"5": "B-3",
|
18 |
+
"6": "I-3",
|
19 |
+
"7": "B-4",
|
20 |
+
"8": "I-4",
|
21 |
+
"9": "B-5",
|
22 |
+
"10": "I-5",
|
23 |
+
"11": "B-6",
|
24 |
+
"12": "I-6",
|
25 |
+
"13": "B-7",
|
26 |
+
"14": "I-7",
|
27 |
+
"15": "B-8",
|
28 |
+
"16": "I-8",
|
29 |
+
"17": "B-9",
|
30 |
+
"18": "I-9",
|
31 |
+
"19": "B-10",
|
32 |
+
"20": "I-10",
|
33 |
+
"21": "B-11",
|
34 |
+
"22": "I-11",
|
35 |
+
"23": "B-12",
|
36 |
+
"24": "I-12",
|
37 |
+
"25": "B-13",
|
38 |
+
"26": "I-13",
|
39 |
+
"27": "B-14",
|
40 |
+
"28": "I-14",
|
41 |
+
"29": "B-15",
|
42 |
+
"30": "I-15",
|
43 |
+
"31": "B-16",
|
44 |
+
"32": "I-16",
|
45 |
+
"33": "B-17",
|
46 |
+
"34": "I-17",
|
47 |
+
"35": "B-18",
|
48 |
+
"36": "I-18",
|
49 |
+
"37": "B-19",
|
50 |
+
"38": "I-19",
|
51 |
+
"39": "B-20",
|
52 |
+
"40": "I-20",
|
53 |
+
"41": "B-21",
|
54 |
+
"42": "I-21",
|
55 |
+
"43": "B-22",
|
56 |
+
"44": "I-22",
|
57 |
+
"45": "B-23",
|
58 |
+
"46": "I-23",
|
59 |
+
"47": "B-24",
|
60 |
+
"48": "I-24",
|
61 |
+
"49": "B-25",
|
62 |
+
"50": "I-25",
|
63 |
+
"51": "B-26",
|
64 |
+
"52": "I-26",
|
65 |
+
"53": "B-27",
|
66 |
+
"54": "I-27",
|
67 |
+
"55": "B-28",
|
68 |
+
"56": "I-28",
|
69 |
+
"57": "B-29",
|
70 |
+
"58": "I-29"
|
71 |
+
},
|
72 |
+
"initializer_range": 0.02,
|
73 |
+
"label2id": {
|
74 |
+
"B-1": 1,
|
75 |
+
"B-10": 19,
|
76 |
+
"B-11": 21,
|
77 |
+
"B-12": 23,
|
78 |
+
"B-13": 25,
|
79 |
+
"B-14": 27,
|
80 |
+
"B-15": 29,
|
81 |
+
"B-16": 31,
|
82 |
+
"B-17": 33,
|
83 |
+
"B-18": 35,
|
84 |
+
"B-19": 37,
|
85 |
+
"B-2": 3,
|
86 |
+
"B-20": 39,
|
87 |
+
"B-21": 41,
|
88 |
+
"B-22": 43,
|
89 |
+
"B-23": 45,
|
90 |
+
"B-24": 47,
|
91 |
+
"B-25": 49,
|
92 |
+
"B-26": 51,
|
93 |
+
"B-27": 53,
|
94 |
+
"B-28": 55,
|
95 |
+
"B-29": 57,
|
96 |
+
"B-3": 5,
|
97 |
+
"B-4": 7,
|
98 |
+
"B-5": 9,
|
99 |
+
"B-6": 11,
|
100 |
+
"B-7": 13,
|
101 |
+
"B-8": 15,
|
102 |
+
"B-9": 17,
|
103 |
+
"I-1": 2,
|
104 |
+
"I-10": 20,
|
105 |
+
"I-11": 22,
|
106 |
+
"I-12": 24,
|
107 |
+
"I-13": 26,
|
108 |
+
"I-14": 28,
|
109 |
+
"I-15": 30,
|
110 |
+
"I-16": 32,
|
111 |
+
"I-17": 34,
|
112 |
+
"I-18": 36,
|
113 |
+
"I-19": 38,
|
114 |
+
"I-2": 4,
|
115 |
+
"I-20": 40,
|
116 |
+
"I-21": 42,
|
117 |
+
"I-22": 44,
|
118 |
+
"I-23": 46,
|
119 |
+
"I-24": 48,
|
120 |
+
"I-25": 50,
|
121 |
+
"I-26": 52,
|
122 |
+
"I-27": 54,
|
123 |
+
"I-28": 56,
|
124 |
+
"I-29": 58,
|
125 |
+
"I-3": 6,
|
126 |
+
"I-4": 8,
|
127 |
+
"I-5": 10,
|
128 |
+
"I-6": 12,
|
129 |
+
"I-7": 14,
|
130 |
+
"I-8": 16,
|
131 |
+
"I-9": 18,
|
132 |
+
"O": 0
|
133 |
+
},
|
134 |
+
"max_position_embeddings": 512,
|
135 |
+
"model_type": "distilbert",
|
136 |
+
"n_heads": 12,
|
137 |
+
"n_layers": 6,
|
138 |
+
"pad_token_id": 0,
|
139 |
+
"qa_dropout": 0.1,
|
140 |
+
"seq_classif_dropout": 0.2,
|
141 |
+
"sinusoidal_pos_embds": false,
|
142 |
+
"tie_weights_": true,
|
143 |
+
"torch_dtype": "float32",
|
144 |
+
"transformers_version": "4.39.3",
|
145 |
+
"vocab_size": 30522
|
146 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caf84f445fb94f603a532ce86ffbccd96b6ec09d9a6dd5df3bb0f928228fbd20
|
3 |
+
size 265645356
|
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 sha256:7be90e835b7b73e6be9bac73b5c8302dfdeccdfdeebf191313cdb795406e7c21
|
3 |
+
size 4856
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|