Hugging Face's logo

HuggingFaceTB
/
stack-edu-classifier-sql

Text Classification
Transformers
Safetensors
code
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
loubnabnl HF staff commited on
Commit
5ebf0e7
·
verified ·
1 Parent(s): 09318ae

Model save

Browse files
Files changed (10) hide show
  1. README.md +94 -0
  2. final/config.json +32 -0
  3. final/merges.txt +0 -0
  4. final/model.safetensors +3 -0
  5. final/special_tokens_map.json +45 -0
  6. final/tokenizer.json +0 -0
  7. final/tokenizer_config.json +186 -0
  8. final/training_args.bin +3 -0
  9. final/vocab.json +0 -0
  10. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: bigcode/starencoder
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - precision
7
+ - recall
8
+ - accuracy
9
+ model-index:
10
+ - name: classifier-llama3-sql-500k
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # classifier-llama3-sql-500k
18
+
19
+ This model is a fine-tuned version of [bigcode/starencoder](https://huggingface.co/bigcode/starencoder) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4719
22
+ - Precision: 0.6074
23
+ - Recall: 0.4618
24
+ - F1 Macro: 0.4864
25
+ - Accuracy: 0.5478
26
+ - F1 Binary Minimum3: 0.8854
27
+ - F1 Binary Minimum2: 0.9418
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: 0.0001
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 256
49
+ - seed: 0
50
+ - distributed_type: multi-GPU
51
+ - num_devices: 8
52
+ - total_train_batch_size: 128
53
+ - total_eval_batch_size: 2048
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: linear
56
+ - lr_scheduler_warmup_steps: 200
57
+ - num_epochs: 30
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy | F1 Binary Minimum3 | F1 Binary Minimum2 |
62
+ |:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:--------:|:--------:|:------------------:|:------------------:|
63
+ | No log | 0 | 0 | 8.5378 | 0.0326 | 0.2 | 0.0561 | 0.1632 | 0 | 0 |
64
+ | 0.5231 | 1.2837 | 1000 | 0.5326 | 0.5973 | 0.4176 | 0.4388 | 0.5192 | 0.8777 | 0.9339 |
65
+ | 0.5041 | 2.5674 | 2000 | 0.5038 | 0.6039 | 0.4350 | 0.4533 | 0.5348 | 0.8824 | 0.9392 |
66
+ | 0.5062 | 3.8511 | 3000 | 0.4965 | 0.6035 | 0.4452 | 0.4652 | 0.5402 | 0.8829 | 0.9411 |
67
+ | 0.498 | 5.1348 | 4000 | 0.4916 | 0.6036 | 0.4445 | 0.4634 | 0.5398 | 0.8848 | 0.9404 |
68
+ | 0.5036 | 6.4185 | 5000 | 0.4894 | 0.5963 | 0.4531 | 0.4789 | 0.5397 | 0.8842 | 0.9396 |
69
+ | 0.4968 | 7.7022 | 6000 | 0.4880 | 0.6082 | 0.4402 | 0.4595 | 0.5347 | 0.8826 | 0.9396 |
70
+ | 0.498 | 8.9859 | 7000 | 0.4835 | 0.6032 | 0.4592 | 0.4843 | 0.5440 | 0.8837 | 0.9413 |
71
+ | 0.4849 | 10.2696 | 8000 | 0.4816 | 0.6168 | 0.4555 | 0.4799 | 0.5442 | 0.8844 | 0.9412 |
72
+ | 0.4925 | 11.5533 | 9000 | 0.4821 | 0.5868 | 0.4595 | 0.4861 | 0.5422 | 0.8843 | 0.9405 |
73
+ | 0.477 | 12.8370 | 10000 | 0.4800 | 0.6117 | 0.4472 | 0.4688 | 0.5404 | 0.8849 | 0.9403 |
74
+ | 0.4753 | 14.1207 | 11000 | 0.4790 | 0.6111 | 0.4533 | 0.4737 | 0.5444 | 0.8842 | 0.9420 |
75
+ | 0.4863 | 15.4044 | 12000 | 0.4809 | 0.5849 | 0.4593 | 0.4858 | 0.5426 | 0.8847 | 0.9402 |
76
+ | 0.4794 | 16.6881 | 13000 | 0.4761 | 0.6116 | 0.4565 | 0.4820 | 0.5442 | 0.8844 | 0.9410 |
77
+ | 0.4684 | 17.9718 | 14000 | 0.4766 | 0.6044 | 0.4533 | 0.4756 | 0.5444 | 0.8852 | 0.9412 |
78
+ | 0.4814 | 19.2555 | 15000 | 0.4748 | 0.6093 | 0.4614 | 0.4842 | 0.5496 | 0.8844 | 0.9427 |
79
+ | 0.4993 | 20.5392 | 16000 | 0.4746 | 0.5977 | 0.4620 | 0.4879 | 0.5464 | 0.8849 | 0.9415 |
80
+ | 0.4788 | 21.8228 | 17000 | 0.4739 | 0.6125 | 0.4592 | 0.4809 | 0.5482 | 0.8860 | 0.9426 |
81
+ | 0.4857 | 23.1065 | 18000 | 0.4747 | 0.6190 | 0.4546 | 0.4771 | 0.5457 | 0.8858 | 0.9414 |
82
+ | 0.4709 | 24.3902 | 19000 | 0.4728 | 0.6132 | 0.4566 | 0.4800 | 0.5462 | 0.8850 | 0.9417 |
83
+ | 0.4803 | 25.6739 | 20000 | 0.4754 | 0.5999 | 0.4585 | 0.4858 | 0.5435 | 0.8856 | 0.9397 |
84
+ | 0.4731 | 26.9576 | 21000 | 0.4725 | 0.6100 | 0.4575 | 0.4805 | 0.5470 | 0.8859 | 0.9415 |
85
+ | 0.4788 | 28.2413 | 22000 | 0.4725 | 0.6087 | 0.4609 | 0.4861 | 0.5478 | 0.8861 | 0.9415 |
86
+ | 0.4594 | 29.5250 | 23000 | 0.4719 | 0.6074 | 0.4618 | 0.4864 | 0.5478 | 0.8854 | 0.9418 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.43.4
92
+ - Pytorch 2.4.0+cu121
93
+ - Datasets 2.21.0
94
+ - Tokenizers 0.19.1
final/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigcode/starencoder",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": 0.0,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 1024,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 49152,
25
+ "position_embedding_type": "absolute",
26
+ "problem_type": "regression",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.43.4",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 49156
32
+ }
final/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
final/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed65d15e563cc53c8b6d086e261febdb4c87bacaeefa47dfd3daa906088822a
3
+ size 496772092
final/special_tokens_map.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": "<|endoftext|>",
38
+ "unk_token": {
39
+ "content": "<|endoftext|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ }
final/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
final/tokenizer_config.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<filename>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<gh_stars>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|endoftext|>",
159
+ "<fim_prefix>",
160
+ "<fim_middle>",
161
+ "<fim_suffix>",
162
+ "<fim_pad>",
163
+ "<filename>",
164
+ "<gh_stars>",
165
+ "<issue_start>",
166
+ "<issue_comment>",
167
+ "<issue_closed>",
168
+ "<jupyter_start>",
169
+ "<jupyter_text>",
170
+ "<jupyter_code>",
171
+ "<jupyter_output>",
172
+ "<empty_output>",
173
+ "<commit_before>",
174
+ "<commit_msg>",
175
+ "<commit_after>",
176
+ "<reponame>"
177
+ ],
178
+ "bos_token": "<|endoftext|>",
179
+ "clean_up_tokenization_spaces": true,
180
+ "eos_token": "<|endoftext|>",
181
+ "model_max_length": 1024,
182
+ "pad_token": "<|endoftext|>",
183
+ "tokenizer_class": "GPT2Tokenizer",
184
+ "unk_token": "<|endoftext|>",
185
+ "vocab_size": 49152
186
+ }
final/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92fd8cae19a8366b8ceffb78915d5c4c7e0150cc8c2b468350f9dcc5f8be91f9
3
+ size 5304
final/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26158624d54cf67e3df931ecede5100f59979a9f8427a0dc3cc8b9fa9fdfe820
3
  size 496772092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed65d15e563cc53c8b6d086e261febdb4c87bacaeefa47dfd3daa906088822a
3
  size 496772092