Afreen commited on
Commit
38e43e3
1 Parent(s): 0f1c29e
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-Clean-up_Standards",
14
+ "2": "B-Impacted_Media",
15
+ "3": "B-Regulatory_Program",
16
+ "4": "B-Remedial_Components",
17
+ "5": "B-Types_of_Contaminants",
18
+ "6": "I-Clean-up_Standards",
19
+ "7": "I-Impacted_Media",
20
+ "8": "I-Regulatory_Program",
21
+ "9": "I-Remedial_Components",
22
+ "10": "I-Types_of_Contaminants"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "label2id": {
26
+ "B-Clean-up_Standards": 1,
27
+ "B-Impacted_Media": 2,
28
+ "B-Regulatory_Program": 3,
29
+ "B-Remedial_Components": 4,
30
+ "B-Types_of_Contaminants": 5,
31
+ "I-Clean-up_Standards": 6,
32
+ "I-Impacted_Media": 7,
33
+ "I-Regulatory_Program": 8,
34
+ "I-Remedial_Components": 9,
35
+ "I-Types_of_Contaminants": 10,
36
+ "O": 0
37
+ },
38
+ "max_position_embeddings": 512,
39
+ "model_type": "distilbert",
40
+ "n_heads": 12,
41
+ "n_layers": 6,
42
+ "pad_token_id": 0,
43
+ "qa_dropout": 0.1,
44
+ "seq_classif_dropout": 0.2,
45
+ "sinusoidal_pos_embds": false,
46
+ "tie_weights_": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.32.1",
49
+ "vocab_size": 30522
50
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f024224d860ad973809d56a2a2858ffbaa200be625bb8405d34a3458797ca77
3
+ size 531053370
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8328807e1aa2b39f534edc43a7f73503046ecaf901f49f06a477ac1519cbb170
3
+ size 265519202
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a22f491fbc0d88c20da41fe3eec83a3e23a1aad62e52e4a43649fcfd68220d8
3
+ size 13990
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b40f9793686376d734c9061f93e730570d8c850d986b48ac3127b9a7cbd3b1
3
+ size 1064
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
trainer_state.json ADDED
@@ -0,0 +1,271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 30.303030303030305,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.6655681133270264,
14
+ "eval_runtime": 31.9535,
15
+ "eval_samples_per_second": 16.242,
16
+ "eval_steps_per_second": 1.033,
17
+ "step": 33
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_loss": 0.34202826023101807,
22
+ "eval_runtime": 32.6272,
23
+ "eval_samples_per_second": 15.907,
24
+ "eval_steps_per_second": 1.011,
25
+ "step": 66
26
+ },
27
+ {
28
+ "epoch": 3.0,
29
+ "eval_loss": 0.1993253082036972,
30
+ "eval_runtime": 34.1947,
31
+ "eval_samples_per_second": 15.178,
32
+ "eval_steps_per_second": 0.965,
33
+ "step": 99
34
+ },
35
+ {
36
+ "epoch": 4.0,
37
+ "eval_loss": 0.12108779698610306,
38
+ "eval_runtime": 33.5003,
39
+ "eval_samples_per_second": 15.492,
40
+ "eval_steps_per_second": 0.985,
41
+ "step": 132
42
+ },
43
+ {
44
+ "epoch": 5.0,
45
+ "eval_loss": 0.08059267699718475,
46
+ "eval_runtime": 33.0363,
47
+ "eval_samples_per_second": 15.71,
48
+ "eval_steps_per_second": 0.999,
49
+ "step": 165
50
+ },
51
+ {
52
+ "epoch": 6.0,
53
+ "eval_loss": 0.0539543516933918,
54
+ "eval_runtime": 33.3191,
55
+ "eval_samples_per_second": 15.577,
56
+ "eval_steps_per_second": 0.99,
57
+ "step": 198
58
+ },
59
+ {
60
+ "epoch": 7.0,
61
+ "eval_loss": 0.033514220267534256,
62
+ "eval_runtime": 33.9315,
63
+ "eval_samples_per_second": 15.296,
64
+ "eval_steps_per_second": 0.973,
65
+ "step": 231
66
+ },
67
+ {
68
+ "epoch": 8.0,
69
+ "eval_loss": 0.02793893776834011,
70
+ "eval_runtime": 33.1021,
71
+ "eval_samples_per_second": 15.679,
72
+ "eval_steps_per_second": 0.997,
73
+ "step": 264
74
+ },
75
+ {
76
+ "epoch": 9.0,
77
+ "eval_loss": 0.017579322680830956,
78
+ "eval_runtime": 33.1929,
79
+ "eval_samples_per_second": 15.636,
80
+ "eval_steps_per_second": 0.994,
81
+ "step": 297
82
+ },
83
+ {
84
+ "epoch": 10.0,
85
+ "eval_loss": 0.017992401495575905,
86
+ "eval_runtime": 33.5989,
87
+ "eval_samples_per_second": 15.447,
88
+ "eval_steps_per_second": 0.982,
89
+ "step": 330
90
+ },
91
+ {
92
+ "epoch": 11.0,
93
+ "eval_loss": 0.011186002753674984,
94
+ "eval_runtime": 33.2114,
95
+ "eval_samples_per_second": 15.627,
96
+ "eval_steps_per_second": 0.994,
97
+ "step": 363
98
+ },
99
+ {
100
+ "epoch": 12.0,
101
+ "eval_loss": 0.009413644671440125,
102
+ "eval_runtime": 33.6973,
103
+ "eval_samples_per_second": 15.402,
104
+ "eval_steps_per_second": 0.979,
105
+ "step": 396
106
+ },
107
+ {
108
+ "epoch": 13.0,
109
+ "eval_loss": 0.008357277140021324,
110
+ "eval_runtime": 34.2116,
111
+ "eval_samples_per_second": 15.17,
112
+ "eval_steps_per_second": 0.965,
113
+ "step": 429
114
+ },
115
+ {
116
+ "epoch": 14.0,
117
+ "eval_loss": 0.006698057986795902,
118
+ "eval_runtime": 32.3567,
119
+ "eval_samples_per_second": 16.04,
120
+ "eval_steps_per_second": 1.02,
121
+ "step": 462
122
+ },
123
+ {
124
+ "epoch": 15.0,
125
+ "eval_loss": 0.005631112959235907,
126
+ "eval_runtime": 30.3383,
127
+ "eval_samples_per_second": 17.107,
128
+ "eval_steps_per_second": 1.088,
129
+ "step": 495
130
+ },
131
+ {
132
+ "epoch": 15.15,
133
+ "learning_rate": 1.2424242424242425e-05,
134
+ "loss": 0.1575,
135
+ "step": 500
136
+ },
137
+ {
138
+ "epoch": 16.0,
139
+ "eval_loss": 0.00457022013142705,
140
+ "eval_runtime": 30.6053,
141
+ "eval_samples_per_second": 16.958,
142
+ "eval_steps_per_second": 1.078,
143
+ "step": 528
144
+ },
145
+ {
146
+ "epoch": 17.0,
147
+ "eval_loss": 0.005157523322850466,
148
+ "eval_runtime": 30.0767,
149
+ "eval_samples_per_second": 17.256,
150
+ "eval_steps_per_second": 1.097,
151
+ "step": 561
152
+ },
153
+ {
154
+ "epoch": 18.0,
155
+ "eval_loss": 0.0044335490092635155,
156
+ "eval_runtime": 29.0299,
157
+ "eval_samples_per_second": 17.878,
158
+ "eval_steps_per_second": 1.137,
159
+ "step": 594
160
+ },
161
+ {
162
+ "epoch": 19.0,
163
+ "eval_loss": 0.003722449066117406,
164
+ "eval_runtime": 28.4937,
165
+ "eval_samples_per_second": 18.215,
166
+ "eval_steps_per_second": 1.158,
167
+ "step": 627
168
+ },
169
+ {
170
+ "epoch": 20.0,
171
+ "eval_loss": 0.004425578285008669,
172
+ "eval_runtime": 32.1425,
173
+ "eval_samples_per_second": 16.147,
174
+ "eval_steps_per_second": 1.027,
175
+ "step": 660
176
+ },
177
+ {
178
+ "epoch": 21.0,
179
+ "eval_loss": 0.0040681445971131325,
180
+ "eval_runtime": 28.8069,
181
+ "eval_samples_per_second": 18.017,
182
+ "eval_steps_per_second": 1.146,
183
+ "step": 693
184
+ },
185
+ {
186
+ "epoch": 22.0,
187
+ "eval_loss": 0.003019771073013544,
188
+ "eval_runtime": 28.6404,
189
+ "eval_samples_per_second": 18.121,
190
+ "eval_steps_per_second": 1.152,
191
+ "step": 726
192
+ },
193
+ {
194
+ "epoch": 23.0,
195
+ "eval_loss": 0.002829624805599451,
196
+ "eval_runtime": 29.787,
197
+ "eval_samples_per_second": 17.424,
198
+ "eval_steps_per_second": 1.108,
199
+ "step": 759
200
+ },
201
+ {
202
+ "epoch": 24.0,
203
+ "eval_loss": 0.002751641208305955,
204
+ "eval_runtime": 28.377,
205
+ "eval_samples_per_second": 18.289,
206
+ "eval_steps_per_second": 1.163,
207
+ "step": 792
208
+ },
209
+ {
210
+ "epoch": 25.0,
211
+ "eval_loss": 0.002945221494883299,
212
+ "eval_runtime": 29.5958,
213
+ "eval_samples_per_second": 17.536,
214
+ "eval_steps_per_second": 1.115,
215
+ "step": 825
216
+ },
217
+ {
218
+ "epoch": 26.0,
219
+ "eval_loss": 0.0026160639245063066,
220
+ "eval_runtime": 29.0161,
221
+ "eval_samples_per_second": 17.887,
222
+ "eval_steps_per_second": 1.137,
223
+ "step": 858
224
+ },
225
+ {
226
+ "epoch": 27.0,
227
+ "eval_loss": 0.002537393243983388,
228
+ "eval_runtime": 28.4904,
229
+ "eval_samples_per_second": 18.217,
230
+ "eval_steps_per_second": 1.158,
231
+ "step": 891
232
+ },
233
+ {
234
+ "epoch": 28.0,
235
+ "eval_loss": 0.00242584478110075,
236
+ "eval_runtime": 29.437,
237
+ "eval_samples_per_second": 17.631,
238
+ "eval_steps_per_second": 1.121,
239
+ "step": 924
240
+ },
241
+ {
242
+ "epoch": 29.0,
243
+ "eval_loss": 0.0026495754718780518,
244
+ "eval_runtime": 28.3889,
245
+ "eval_samples_per_second": 18.282,
246
+ "eval_steps_per_second": 1.162,
247
+ "step": 957
248
+ },
249
+ {
250
+ "epoch": 30.0,
251
+ "eval_loss": 0.0023259243462234735,
252
+ "eval_runtime": 28.1977,
253
+ "eval_samples_per_second": 18.406,
254
+ "eval_steps_per_second": 1.17,
255
+ "step": 990
256
+ },
257
+ {
258
+ "epoch": 30.3,
259
+ "learning_rate": 4.848484848484849e-06,
260
+ "loss": 0.0065,
261
+ "step": 1000
262
+ }
263
+ ],
264
+ "logging_steps": 500,
265
+ "max_steps": 1320,
266
+ "num_train_epochs": 40,
267
+ "save_steps": 500,
268
+ "total_flos": 278856790097838.0,
269
+ "trial_name": null,
270
+ "trial_params": null
271
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7055907b6d27e74601fff328ea1fadd2feac1546e616919fc601fadf9570622d
3
+ size 4472
vocab.txt ADDED
The diff for this file is too large to render. See raw diff