End of training
Browse files- README.md +68 -0
- config.json +119 -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 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: my_model
|
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 |
+
# my_model
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1133
|
24 |
+
- Precision: 0.8967
|
25 |
+
- Recall: 0.9086
|
26 |
+
- F1: 0.9026
|
27 |
+
- Accuracy: 0.9308
|
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: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 3
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.1943 | 1.0 | 2241 | 0.1610 | 0.8577 | 0.8640 | 0.8608 | 0.9014 |
|
59 |
+
| 0.1341 | 2.0 | 4482 | 0.1204 | 0.8890 | 0.9014 | 0.8951 | 0.9259 |
|
60 |
+
| 0.1095 | 3.0 | 6723 | 0.1133 | 0.8967 | 0.9086 | 0.9026 | 0.9308 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.35.0
|
66 |
+
- Pytorch 2.1.0
|
67 |
+
- Datasets 2.14.6
|
68 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7",
|
20 |
+
"8": "LABEL_8",
|
21 |
+
"9": "LABEL_9",
|
22 |
+
"10": "LABEL_10",
|
23 |
+
"11": "LABEL_11",
|
24 |
+
"12": "LABEL_12",
|
25 |
+
"13": "LABEL_13",
|
26 |
+
"14": "LABEL_14",
|
27 |
+
"15": "LABEL_15",
|
28 |
+
"16": "LABEL_16",
|
29 |
+
"17": "LABEL_17",
|
30 |
+
"18": "LABEL_18",
|
31 |
+
"19": "LABEL_19",
|
32 |
+
"20": "LABEL_20",
|
33 |
+
"21": "LABEL_21",
|
34 |
+
"22": "LABEL_22",
|
35 |
+
"23": "LABEL_23",
|
36 |
+
"24": "LABEL_24",
|
37 |
+
"25": "LABEL_25",
|
38 |
+
"26": "LABEL_26",
|
39 |
+
"27": "LABEL_27",
|
40 |
+
"28": "LABEL_28",
|
41 |
+
"29": "LABEL_29",
|
42 |
+
"30": "LABEL_30",
|
43 |
+
"31": "LABEL_31",
|
44 |
+
"32": "LABEL_32",
|
45 |
+
"33": "LABEL_33",
|
46 |
+
"34": "LABEL_34",
|
47 |
+
"35": "LABEL_35",
|
48 |
+
"36": "LABEL_36",
|
49 |
+
"37": "LABEL_37",
|
50 |
+
"38": "LABEL_38",
|
51 |
+
"39": "LABEL_39",
|
52 |
+
"40": "LABEL_40",
|
53 |
+
"41": "LABEL_41",
|
54 |
+
"42": "LABEL_42",
|
55 |
+
"43": "LABEL_43",
|
56 |
+
"44": "LABEL_44"
|
57 |
+
},
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"label2id": {
|
60 |
+
"LABEL_0": 0,
|
61 |
+
"LABEL_1": 1,
|
62 |
+
"LABEL_10": 10,
|
63 |
+
"LABEL_11": 11,
|
64 |
+
"LABEL_12": 12,
|
65 |
+
"LABEL_13": 13,
|
66 |
+
"LABEL_14": 14,
|
67 |
+
"LABEL_15": 15,
|
68 |
+
"LABEL_16": 16,
|
69 |
+
"LABEL_17": 17,
|
70 |
+
"LABEL_18": 18,
|
71 |
+
"LABEL_19": 19,
|
72 |
+
"LABEL_2": 2,
|
73 |
+
"LABEL_20": 20,
|
74 |
+
"LABEL_21": 21,
|
75 |
+
"LABEL_22": 22,
|
76 |
+
"LABEL_23": 23,
|
77 |
+
"LABEL_24": 24,
|
78 |
+
"LABEL_25": 25,
|
79 |
+
"LABEL_26": 26,
|
80 |
+
"LABEL_27": 27,
|
81 |
+
"LABEL_28": 28,
|
82 |
+
"LABEL_29": 29,
|
83 |
+
"LABEL_3": 3,
|
84 |
+
"LABEL_30": 30,
|
85 |
+
"LABEL_31": 31,
|
86 |
+
"LABEL_32": 32,
|
87 |
+
"LABEL_33": 33,
|
88 |
+
"LABEL_34": 34,
|
89 |
+
"LABEL_35": 35,
|
90 |
+
"LABEL_36": 36,
|
91 |
+
"LABEL_37": 37,
|
92 |
+
"LABEL_38": 38,
|
93 |
+
"LABEL_39": 39,
|
94 |
+
"LABEL_4": 4,
|
95 |
+
"LABEL_40": 40,
|
96 |
+
"LABEL_41": 41,
|
97 |
+
"LABEL_42": 42,
|
98 |
+
"LABEL_43": 43,
|
99 |
+
"LABEL_44": 44,
|
100 |
+
"LABEL_5": 5,
|
101 |
+
"LABEL_6": 6,
|
102 |
+
"LABEL_7": 7,
|
103 |
+
"LABEL_8": 8,
|
104 |
+
"LABEL_9": 9
|
105 |
+
},
|
106 |
+
"max_position_embeddings": 512,
|
107 |
+
"model_type": "distilbert",
|
108 |
+
"n_heads": 12,
|
109 |
+
"n_layers": 6,
|
110 |
+
"output_past": true,
|
111 |
+
"pad_token_id": 0,
|
112 |
+
"qa_dropout": 0.1,
|
113 |
+
"seq_classif_dropout": 0.2,
|
114 |
+
"sinusoidal_pos_embds": false,
|
115 |
+
"tie_weights_": true,
|
116 |
+
"torch_dtype": "float32",
|
117 |
+
"transformers_version": "4.35.0",
|
118 |
+
"vocab_size": 28996
|
119 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4741ceb62886018a138b1d435bcc2ecc0980ed7c008c451f153b0fb7da3eaba3
|
3 |
+
size 260914412
|
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:cb2be85793abcc806e9074b66eda5581cda316d963b17b4aa87faf2c71d55990
|
3 |
+
size 4536
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|