davidliu0716 commited on
Commit
2f175a5
1 Parent(s): 6c1cf55

Training completed!

Browse files
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ model-index:
10
+ - name: distilbert-base-uncased-finetuned-language
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
+ # distilbert-base-uncased-finetuned-language
18
+
19
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0408
22
+ - Accuracy: 0.9932
23
+ - F1: 0.9932
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 32
45
+ - seed: 42
46
+ - distributed_type: tpu
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 2
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 0.2088 | 1.0 | 2188 | 0.0386 | 0.9927 | 0.9927 |
56
+ | 0.0105 | 2.0 | 4376 | 0.0408 | 0.9932 | 0.9932 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.34.0
62
+ - Pytorch 2.0.1+cu118
63
+ - Datasets 2.14.5
64
+ - Tokenizers 0.14.0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
config.json ADDED
@@ -0,0 +1,229 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "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
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48",
61
+ "49": "LABEL_49",
62
+ "50": "LABEL_50",
63
+ "51": "LABEL_51",
64
+ "52": "LABEL_52",
65
+ "53": "LABEL_53",
66
+ "54": "LABEL_54",
67
+ "55": "LABEL_55",
68
+ "56": "LABEL_56",
69
+ "57": "LABEL_57",
70
+ "58": "LABEL_58",
71
+ "59": "LABEL_59",
72
+ "60": "LABEL_60",
73
+ "61": "LABEL_61",
74
+ "62": "LABEL_62",
75
+ "63": "LABEL_63",
76
+ "64": "LABEL_64",
77
+ "65": "LABEL_65",
78
+ "66": "LABEL_66",
79
+ "67": "LABEL_67",
80
+ "68": "LABEL_68",
81
+ "69": "LABEL_69",
82
+ "70": "LABEL_70",
83
+ "71": "LABEL_71",
84
+ "72": "LABEL_72",
85
+ "73": "LABEL_73",
86
+ "74": "LABEL_74",
87
+ "75": "LABEL_75",
88
+ "76": "LABEL_76",
89
+ "77": "LABEL_77",
90
+ "78": "LABEL_78",
91
+ "79": "LABEL_79",
92
+ "80": "LABEL_80",
93
+ "81": "LABEL_81",
94
+ "82": "LABEL_82",
95
+ "83": "LABEL_83",
96
+ "84": "LABEL_84",
97
+ "85": "LABEL_85",
98
+ "86": "LABEL_86",
99
+ "87": "LABEL_87",
100
+ "88": "LABEL_88",
101
+ "89": "LABEL_89",
102
+ "90": "LABEL_90",
103
+ "91": "LABEL_91",
104
+ "92": "LABEL_92",
105
+ "93": "LABEL_93",
106
+ "94": "LABEL_94",
107
+ "95": "LABEL_95",
108
+ "96": "LABEL_96",
109
+ "97": "LABEL_97",
110
+ "98": "LABEL_98",
111
+ "99": "LABEL_99"
112
+ },
113
+ "initializer_range": 0.02,
114
+ "label2id": {
115
+ "LABEL_0": 0,
116
+ "LABEL_1": 1,
117
+ "LABEL_10": 10,
118
+ "LABEL_11": 11,
119
+ "LABEL_12": 12,
120
+ "LABEL_13": 13,
121
+ "LABEL_14": 14,
122
+ "LABEL_15": 15,
123
+ "LABEL_16": 16,
124
+ "LABEL_17": 17,
125
+ "LABEL_18": 18,
126
+ "LABEL_19": 19,
127
+ "LABEL_2": 2,
128
+ "LABEL_20": 20,
129
+ "LABEL_21": 21,
130
+ "LABEL_22": 22,
131
+ "LABEL_23": 23,
132
+ "LABEL_24": 24,
133
+ "LABEL_25": 25,
134
+ "LABEL_26": 26,
135
+ "LABEL_27": 27,
136
+ "LABEL_28": 28,
137
+ "LABEL_29": 29,
138
+ "LABEL_3": 3,
139
+ "LABEL_30": 30,
140
+ "LABEL_31": 31,
141
+ "LABEL_32": 32,
142
+ "LABEL_33": 33,
143
+ "LABEL_34": 34,
144
+ "LABEL_35": 35,
145
+ "LABEL_36": 36,
146
+ "LABEL_37": 37,
147
+ "LABEL_38": 38,
148
+ "LABEL_39": 39,
149
+ "LABEL_4": 4,
150
+ "LABEL_40": 40,
151
+ "LABEL_41": 41,
152
+ "LABEL_42": 42,
153
+ "LABEL_43": 43,
154
+ "LABEL_44": 44,
155
+ "LABEL_45": 45,
156
+ "LABEL_46": 46,
157
+ "LABEL_47": 47,
158
+ "LABEL_48": 48,
159
+ "LABEL_49": 49,
160
+ "LABEL_5": 5,
161
+ "LABEL_50": 50,
162
+ "LABEL_51": 51,
163
+ "LABEL_52": 52,
164
+ "LABEL_53": 53,
165
+ "LABEL_54": 54,
166
+ "LABEL_55": 55,
167
+ "LABEL_56": 56,
168
+ "LABEL_57": 57,
169
+ "LABEL_58": 58,
170
+ "LABEL_59": 59,
171
+ "LABEL_6": 6,
172
+ "LABEL_60": 60,
173
+ "LABEL_61": 61,
174
+ "LABEL_62": 62,
175
+ "LABEL_63": 63,
176
+ "LABEL_64": 64,
177
+ "LABEL_65": 65,
178
+ "LABEL_66": 66,
179
+ "LABEL_67": 67,
180
+ "LABEL_68": 68,
181
+ "LABEL_69": 69,
182
+ "LABEL_7": 7,
183
+ "LABEL_70": 70,
184
+ "LABEL_71": 71,
185
+ "LABEL_72": 72,
186
+ "LABEL_73": 73,
187
+ "LABEL_74": 74,
188
+ "LABEL_75": 75,
189
+ "LABEL_76": 76,
190
+ "LABEL_77": 77,
191
+ "LABEL_78": 78,
192
+ "LABEL_79": 79,
193
+ "LABEL_8": 8,
194
+ "LABEL_80": 80,
195
+ "LABEL_81": 81,
196
+ "LABEL_82": 82,
197
+ "LABEL_83": 83,
198
+ "LABEL_84": 84,
199
+ "LABEL_85": 85,
200
+ "LABEL_86": 86,
201
+ "LABEL_87": 87,
202
+ "LABEL_88": 88,
203
+ "LABEL_89": 89,
204
+ "LABEL_9": 9,
205
+ "LABEL_90": 90,
206
+ "LABEL_91": 91,
207
+ "LABEL_92": 92,
208
+ "LABEL_93": 93,
209
+ "LABEL_94": 94,
210
+ "LABEL_95": 95,
211
+ "LABEL_96": 96,
212
+ "LABEL_97": 97,
213
+ "LABEL_98": 98,
214
+ "LABEL_99": 99
215
+ },
216
+ "max_position_embeddings": 512,
217
+ "model_type": "distilbert",
218
+ "n_heads": 12,
219
+ "n_layers": 6,
220
+ "pad_token_id": 0,
221
+ "problem_type": "single_label_classification",
222
+ "qa_dropout": 0.1,
223
+ "seq_classif_dropout": 0.2,
224
+ "sinusoidal_pos_embds": false,
225
+ "tie_weights_": true,
226
+ "torch_dtype": "float32",
227
+ "transformers_version": "4.34.0",
228
+ "vocab_size": 30522
229
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a907d28a3fb965354cd88928199dd0e40fb45f0dafd9835e9431d5ff3cb2e7
3
+ size 268156973
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630e00b46d6b08aa173bd734f0e77dd6ffb7113afae3b2893e596504585dc5ea
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff