Hugging Face's logo

hallisky
/
cds_style_classifier

Text Classification
Transformers
PyTorch
roberta
Model card Files
xet
Community
1
hallisky commited on
Commit
2f64d1c
·
verified ·
1 Parent(s): 1a2df28

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +54 -0
  2. merges.txt +0 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +51 -0
  8. tokenizer_config.json +64 -0
  9. trainer_state.json +256 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 4096,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "max_position_embeddings": 514,
43
+ "model_type": "roberta",
44
+ "num_attention_heads": 16,
45
+ "num_hidden_layers": 24,
46
+ "pad_token_id": 1,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "multi_label_classification",
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.24.0",
51
+ "type_vocab_size": 1,
52
+ "use_cache": true,
53
+ "vocab_size": 50265
54
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:935b949ee06fc90132b7284b4a194739d8ef4abaa392923a5134fd1d348d46a3
3
+ size 2843198981
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9ce03623ff256e54923076c77b874ee080d1bfecdb29484a424d9bc62c6fd0b
3
+ size 1421624053
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3745c235f9e8a7dde4b0e06d81ef4505f592cfabbafb88320cc8de450b10e6cc
3
+ size 17641
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30a94d8043e747970b07529768476c771a86daaa1c81ae2dbff2fd78d898b67
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 512,
37
+ "name_or_path": "roberta-large",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": null,
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8444921415218445,
3
+ "best_model_checkpoint": "/gscratch/xlab/hallisky/style/models/multilabel/03-21-2023_21:54:15/checkpoint-4272",
4
+ "epoch": 4.0,
5
+ "global_step": 4272,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.25,
12
+ "learning_rate": 5e-06,
13
+ "loss": 0.3538,
14
+ "step": 267
15
+ },
16
+ {
17
+ "epoch": 0.25,
18
+ "eval_acc": 0.6889150453506889,
19
+ "eval_loss": 0.15054994821548462,
20
+ "eval_runtime": 41.4893,
21
+ "eval_samples_per_second": 348.114,
22
+ "eval_steps_per_second": 1.374,
23
+ "step": 267
24
+ },
25
+ {
26
+ "epoch": 0.5,
27
+ "learning_rate": 1e-05,
28
+ "loss": 0.1314,
29
+ "step": 534
30
+ },
31
+ {
32
+ "epoch": 0.5,
33
+ "eval_acc": 0.7778162431627779,
34
+ "eval_loss": 0.10427295416593552,
35
+ "eval_runtime": 41.0952,
36
+ "eval_samples_per_second": 351.453,
37
+ "eval_steps_per_second": 1.387,
38
+ "step": 534
39
+ },
40
+ {
41
+ "epoch": 0.75,
42
+ "learning_rate": 9.444444444444445e-06,
43
+ "loss": 0.1031,
44
+ "step": 801
45
+ },
46
+ {
47
+ "epoch": 0.75,
48
+ "eval_acc": 0.8037803780378038,
49
+ "eval_loss": 0.0903468206524849,
50
+ "eval_runtime": 41.1937,
51
+ "eval_samples_per_second": 350.612,
52
+ "eval_steps_per_second": 1.384,
53
+ "step": 801
54
+ },
55
+ {
56
+ "epoch": 1.0,
57
+ "learning_rate": 8.888888888888888e-06,
58
+ "loss": 0.0916,
59
+ "step": 1068
60
+ },
61
+ {
62
+ "epoch": 1.0,
63
+ "eval_acc": 0.8165893512428166,
64
+ "eval_loss": 0.08489712327718735,
65
+ "eval_runtime": 41.1826,
66
+ "eval_samples_per_second": 350.706,
67
+ "eval_steps_per_second": 1.384,
68
+ "step": 1068
69
+ },
70
+ {
71
+ "epoch": 1.25,
72
+ "learning_rate": 8.333333333333334e-06,
73
+ "loss": 0.0807,
74
+ "step": 1335
75
+ },
76
+ {
77
+ "epoch": 1.25,
78
+ "eval_acc": 0.8217821782178217,
79
+ "eval_loss": 0.0828377977013588,
80
+ "eval_runtime": 41.1771,
81
+ "eval_samples_per_second": 350.754,
82
+ "eval_steps_per_second": 1.384,
83
+ "step": 1335
84
+ },
85
+ {
86
+ "epoch": 1.5,
87
+ "learning_rate": 7.77777777777778e-06,
88
+ "loss": 0.0777,
89
+ "step": 1602
90
+ },
91
+ {
92
+ "epoch": 1.5,
93
+ "eval_acc": 0.8273904313508273,
94
+ "eval_loss": 0.07905308157205582,
95
+ "eval_runtime": 41.1692,
96
+ "eval_samples_per_second": 350.821,
97
+ "eval_steps_per_second": 1.385,
98
+ "step": 1602
99
+ },
100
+ {
101
+ "epoch": 1.75,
102
+ "learning_rate": 7.222222222222223e-06,
103
+ "loss": 0.0748,
104
+ "step": 1869
105
+ },
106
+ {
107
+ "epoch": 1.75,
108
+ "eval_acc": 0.8333448729488333,
109
+ "eval_loss": 0.07718278467655182,
110
+ "eval_runtime": 41.1712,
111
+ "eval_samples_per_second": 350.804,
112
+ "eval_steps_per_second": 1.384,
113
+ "step": 1869
114
+ },
115
+ {
116
+ "epoch": 2.0,
117
+ "learning_rate": 6.666666666666667e-06,
118
+ "loss": 0.0732,
119
+ "step": 2136
120
+ },
121
+ {
122
+ "epoch": 2.0,
123
+ "eval_acc": 0.8379145606868379,
124
+ "eval_loss": 0.07422468066215515,
125
+ "eval_runtime": 41.1823,
126
+ "eval_samples_per_second": 350.709,
127
+ "eval_steps_per_second": 1.384,
128
+ "step": 2136
129
+ },
130
+ {
131
+ "epoch": 2.25,
132
+ "learning_rate": 6.111111111111112e-06,
133
+ "loss": 0.0635,
134
+ "step": 2403
135
+ },
136
+ {
137
+ "epoch": 2.25,
138
+ "eval_acc": 0.8334141106418335,
139
+ "eval_loss": 0.07540296018123627,
140
+ "eval_runtime": 41.1954,
141
+ "eval_samples_per_second": 350.597,
142
+ "eval_steps_per_second": 1.384,
143
+ "step": 2403
144
+ },
145
+ {
146
+ "epoch": 2.5,
147
+ "learning_rate": 5.555555555555557e-06,
148
+ "loss": 0.0627,
149
+ "step": 2670
150
+ },
151
+ {
152
+ "epoch": 2.5,
153
+ "eval_acc": 0.8368759952918369,
154
+ "eval_loss": 0.07453104108572006,
155
+ "eval_runtime": 41.204,
156
+ "eval_samples_per_second": 350.524,
157
+ "eval_steps_per_second": 1.383,
158
+ "step": 2670
159
+ },
160
+ {
161
+ "epoch": 2.75,
162
+ "learning_rate": 5e-06,
163
+ "loss": 0.0621,
164
+ "step": 2937
165
+ },
166
+ {
167
+ "epoch": 2.75,
168
+ "eval_acc": 0.8378453229938378,
169
+ "eval_loss": 0.07528460025787354,
170
+ "eval_runtime": 41.1464,
171
+ "eval_samples_per_second": 351.015,
172
+ "eval_steps_per_second": 1.385,
173
+ "step": 2937
174
+ },
175
+ {
176
+ "epoch": 3.0,
177
+ "learning_rate": 4.444444444444444e-06,
178
+ "loss": 0.0616,
179
+ "step": 3204
180
+ },
181
+ {
182
+ "epoch": 3.0,
183
+ "eval_acc": 0.8421380599598421,
184
+ "eval_loss": 0.07257214188575745,
185
+ "eval_runtime": 41.1192,
186
+ "eval_samples_per_second": 351.247,
187
+ "eval_steps_per_second": 1.386,
188
+ "step": 3204
189
+ },
190
+ {
191
+ "epoch": 3.25,
192
+ "learning_rate": 3.88888888888889e-06,
193
+ "loss": 0.0544,
194
+ "step": 3471
195
+ },
196
+ {
197
+ "epoch": 3.25,
198
+ "eval_acc": 0.844007477670844,
199
+ "eval_loss": 0.07361570745706558,
200
+ "eval_runtime": 41.4565,
201
+ "eval_samples_per_second": 348.389,
202
+ "eval_steps_per_second": 1.375,
203
+ "step": 3471
204
+ },
205
+ {
206
+ "epoch": 3.5,
207
+ "learning_rate": 3.3333333333333333e-06,
208
+ "loss": 0.0539,
209
+ "step": 3738
210
+ },
211
+ {
212
+ "epoch": 3.5,
213
+ "eval_acc": 0.8441459530568441,
214
+ "eval_loss": 0.07325488328933716,
215
+ "eval_runtime": 41.1118,
216
+ "eval_samples_per_second": 351.311,
217
+ "eval_steps_per_second": 1.386,
218
+ "step": 3738
219
+ },
220
+ {
221
+ "epoch": 3.75,
222
+ "learning_rate": 2.7777777777777783e-06,
223
+ "loss": 0.0538,
224
+ "step": 4005
225
+ },
226
+ {
227
+ "epoch": 3.75,
228
+ "eval_acc": 0.8426227238108426,
229
+ "eval_loss": 0.07311566174030304,
230
+ "eval_runtime": 41.1396,
231
+ "eval_samples_per_second": 351.073,
232
+ "eval_steps_per_second": 1.386,
233
+ "step": 4005
234
+ },
235
+ {
236
+ "epoch": 4.0,
237
+ "learning_rate": 2.222222222222222e-06,
238
+ "loss": 0.0528,
239
+ "step": 4272
240
+ },
241
+ {
242
+ "epoch": 4.0,
243
+ "eval_acc": 0.8444921415218445,
244
+ "eval_loss": 0.0724639743566513,
245
+ "eval_runtime": 41.153,
246
+ "eval_samples_per_second": 350.959,
247
+ "eval_steps_per_second": 1.385,
248
+ "step": 4272
249
+ }
250
+ ],
251
+ "max_steps": 5340,
252
+ "num_train_epochs": 5,
253
+ "total_flos": 1.758532164135154e+17,
254
+ "trial_name": null,
255
+ "trial_params": null
256
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52258e49e25773b1528732196fca22b87f2b2aa84f802d41064bd8581323662
3
+ size 3451
vocab.json ADDED
The diff for this file is too large to render. See raw diff