Lifehouse commited on
Commit
605783e
·
verified ·
1 Parent(s): c49c5be

Training in progress, epoch 1

Browse files
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - generator
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: distilbert-sql-timeout-classifier-with-features-4096
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: generator
18
+ type: generator
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.844167610419026
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # distilbert-sql-timeout-classifier-with-features-4096
32
+
33
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the generator dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.9918
36
+ - Accuracy: 0.8442
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 2e-05
56
+ - train_batch_size: 2
57
+ - eval_batch_size: 2
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 3
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 0.5456 | 1.0 | 3255 | 0.7278 | 0.8310 |
68
+ | 0.3173 | 2.0 | 6510 | 0.7899 | 0.8519 |
69
+ | 0.2159 | 3.0 | 9765 | 0.9918 | 0.8442 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.38.1
75
+ - Pytorch 2.2.1+cu121
76
+ - Datasets 2.17.1
77
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ClusterLoad": 30529,
3
+ "DDLIndicator": 30528,
4
+ "DMLIndicator": 30523,
5
+ "DQLIndicator": 30537,
6
+ "GroupByIndicator": 30538,
7
+ "InputBytesSize": 30531,
8
+ "InputPartitionsNum": 30539,
9
+ "InputRowCount": 30530,
10
+ "InputTablesNum": 30533,
11
+ "IsPureDQL": 30532,
12
+ "JoinsNum": 30534,
13
+ "LateralViewIndicator": 30522,
14
+ "LimitSize": 30526,
15
+ "OrderByIndicator": 30535,
16
+ "OutPutRowCount": 30536,
17
+ "inputProjectRowSize": 30525,
18
+ "inputScanRowSize": 30524,
19
+ "outputRowSize": 30527
20
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "runtime_timeout",
13
+ "1": "not_timeout"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "not_timeout": 1,
18
+ "runtime_timeout": 0
19
+ },
20
+ "max_position_embeddings": 4096,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
25
+ "problem_type": "single_label_classification",
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.38.1",
31
+ "vocab_size": 30540
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b773b42b6b99431700b1373da134a7db0be461fd1c346f1d6c09ecbaa17c663
3
+ size 278897920
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 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "30522": {
44
+ "content": "LateralViewIndicator",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "30523": {
52
+ "content": "DMLIndicator",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "30524": {
60
+ "content": "inputScanRowSize",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "30525": {
68
+ "content": "inputProjectRowSize",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "30526": {
76
+ "content": "LimitSize",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "30527": {
84
+ "content": "outputRowSize",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "30528": {
92
+ "content": "DDLIndicator",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "30529": {
100
+ "content": "ClusterLoad",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "30530": {
108
+ "content": "InputRowCount",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "30531": {
116
+ "content": "InputBytesSize",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "30532": {
124
+ "content": "IsPureDQL",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "30533": {
132
+ "content": "InputTablesNum",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "30534": {
140
+ "content": "JoinsNum",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "30535": {
148
+ "content": "OrderByIndicator",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "30536": {
156
+ "content": "OutPutRowCount",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "30537": {
164
+ "content": "DQLIndicator",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "30538": {
172
+ "content": "GroupByIndicator",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "30539": {
180
+ "content": "InputPartitionsNum",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ }
187
+ },
188
+ "clean_up_tokenization_spaces": true,
189
+ "cls_token": "[CLS]",
190
+ "do_lower_case": true,
191
+ "mask_token": "[MASK]",
192
+ "model_max_length": 512,
193
+ "pad_token": "[PAD]",
194
+ "sep_token": "[SEP]",
195
+ "strip_accents": null,
196
+ "tokenize_chinese_chars": true,
197
+ "tokenizer_class": "DistilBertTokenizer",
198
+ "unk_token": "[UNK]"
199
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ae9e900b94e9a3c612f09607a7aaa481e6d036fa3da93e697b9e3e65b18ad8
3
+ size 5048
vocab.txt ADDED
The diff for this file is too large to render. See raw diff