sekarmulyani commited on
Commit
7a6c098
·
1 Parent(s): 76ef5c5

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "indolem/indobertweet-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_ids": 0,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "Bintang 1",
16
+ "1": "Bintang 2",
17
+ "2": "Bintang 3",
18
+ "3": "Bintang 4",
19
+ "4": "Bintang 5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "Bintang 1": 0,
25
+ "Bintang 2": 1,
26
+ "Bintang 3": 2,
27
+ "Bintang 4": 3,
28
+ "Bintang 5": 4
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "output_past": true,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "multi_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.32.0",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 31923
44
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de100b94103b3b736afd89bbf3310d0b6d5830da9b6f5f6ef897dd28a534d2c1
3
+ size 884664069
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ee5be0995e46fabb916878464e6f725fee3c9fb8a141e6237e7eb44e79d504
3
+ size 442316593
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:366a8a36ac9c0df2320a13b88803aed07a3b46b0b1d9940a9a0c48288d2d9833
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde9a44c7ee081dec533ca17591fe9631bd23540ae68ab6e78cf56d71e61b9f5
3
+ size 627
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_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
trainer_state.json ADDED
@@ -0,0 +1,1201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5357989568515884,
3
+ "best_model_checkpoint": "./indobertweet-review-rating/checkpoint-93240",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 93240,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 1.996782496782497e-05,
14
+ "loss": 0.4164,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "learning_rate": 1.9935649935649937e-05,
20
+ "loss": 0.3806,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.1,
25
+ "learning_rate": 1.9903474903474905e-05,
26
+ "loss": 0.3775,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.13,
31
+ "learning_rate": 1.9871299871299873e-05,
32
+ "loss": 0.373,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.16,
37
+ "learning_rate": 1.983912483912484e-05,
38
+ "loss": 0.3697,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.19,
43
+ "learning_rate": 1.980694980694981e-05,
44
+ "loss": 0.3687,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.23,
49
+ "learning_rate": 1.9774774774774777e-05,
50
+ "loss": 0.3683,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.26,
55
+ "learning_rate": 1.9742599742599745e-05,
56
+ "loss": 0.3591,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.29,
61
+ "learning_rate": 1.9710424710424713e-05,
62
+ "loss": 0.37,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.32,
67
+ "learning_rate": 1.967824967824968e-05,
68
+ "loss": 0.3643,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.35,
73
+ "learning_rate": 1.964607464607465e-05,
74
+ "loss": 0.3664,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.39,
79
+ "learning_rate": 1.9613899613899616e-05,
80
+ "loss": 0.3644,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.42,
85
+ "learning_rate": 1.9581724581724584e-05,
86
+ "loss": 0.3633,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.45,
91
+ "learning_rate": 1.9549549549549552e-05,
92
+ "loss": 0.3616,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.48,
97
+ "learning_rate": 1.951737451737452e-05,
98
+ "loss": 0.3659,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.51,
103
+ "learning_rate": 1.9485199485199485e-05,
104
+ "loss": 0.3613,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.55,
109
+ "learning_rate": 1.9453024453024453e-05,
110
+ "loss": 0.3661,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.58,
115
+ "learning_rate": 1.942084942084942e-05,
116
+ "loss": 0.3605,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.61,
121
+ "learning_rate": 1.9388674388674392e-05,
122
+ "loss": 0.3544,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.64,
127
+ "learning_rate": 1.935649935649936e-05,
128
+ "loss": 0.3599,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.68,
133
+ "learning_rate": 1.9324324324324328e-05,
134
+ "loss": 0.3583,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.71,
139
+ "learning_rate": 1.9292149292149292e-05,
140
+ "loss": 0.3571,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.74,
145
+ "learning_rate": 1.925997425997426e-05,
146
+ "loss": 0.3598,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 0.77,
151
+ "learning_rate": 1.9227799227799228e-05,
152
+ "loss": 0.3567,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 0.8,
157
+ "learning_rate": 1.9195624195624196e-05,
158
+ "loss": 0.3572,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 0.84,
163
+ "learning_rate": 1.9163449163449167e-05,
164
+ "loss": 0.3512,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 0.87,
169
+ "learning_rate": 1.9131274131274135e-05,
170
+ "loss": 0.3565,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 0.9,
175
+ "learning_rate": 1.90990990990991e-05,
176
+ "loss": 0.3452,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 0.93,
181
+ "learning_rate": 1.9066924066924067e-05,
182
+ "loss": 0.3531,
183
+ "step": 14500
184
+ },
185
+ {
186
+ "epoch": 0.97,
187
+ "learning_rate": 1.9034749034749035e-05,
188
+ "loss": 0.3475,
189
+ "step": 15000
190
+ },
191
+ {
192
+ "epoch": 1.0,
193
+ "learning_rate": 1.9002574002574003e-05,
194
+ "loss": 0.3579,
195
+ "step": 15500
196
+ },
197
+ {
198
+ "epoch": 1.0,
199
+ "eval_akurasi": 0.38799603174603176,
200
+ "eval_f1": 0.4929409550103533,
201
+ "eval_loss": 0.3472347557544708,
202
+ "eval_roc_auc": 0.6709201388888889,
203
+ "eval_runtime": 170.7708,
204
+ "eval_samples_per_second": 59.026,
205
+ "eval_steps_per_second": 7.378,
206
+ "step": 15540
207
+ },
208
+ {
209
+ "epoch": 1.03,
210
+ "learning_rate": 1.897039897039897e-05,
211
+ "loss": 0.3402,
212
+ "step": 16000
213
+ },
214
+ {
215
+ "epoch": 1.06,
216
+ "learning_rate": 1.8938223938223942e-05,
217
+ "loss": 0.3325,
218
+ "step": 16500
219
+ },
220
+ {
221
+ "epoch": 1.09,
222
+ "learning_rate": 1.8906048906048907e-05,
223
+ "loss": 0.3306,
224
+ "step": 17000
225
+ },
226
+ {
227
+ "epoch": 1.13,
228
+ "learning_rate": 1.8873873873873875e-05,
229
+ "loss": 0.3326,
230
+ "step": 17500
231
+ },
232
+ {
233
+ "epoch": 1.16,
234
+ "learning_rate": 1.8841698841698843e-05,
235
+ "loss": 0.3387,
236
+ "step": 18000
237
+ },
238
+ {
239
+ "epoch": 1.19,
240
+ "learning_rate": 1.880952380952381e-05,
241
+ "loss": 0.3336,
242
+ "step": 18500
243
+ },
244
+ {
245
+ "epoch": 1.22,
246
+ "learning_rate": 1.877734877734878e-05,
247
+ "loss": 0.3367,
248
+ "step": 19000
249
+ },
250
+ {
251
+ "epoch": 1.25,
252
+ "learning_rate": 1.8745173745173746e-05,
253
+ "loss": 0.3332,
254
+ "step": 19500
255
+ },
256
+ {
257
+ "epoch": 1.29,
258
+ "learning_rate": 1.8712998712998714e-05,
259
+ "loss": 0.3305,
260
+ "step": 20000
261
+ },
262
+ {
263
+ "epoch": 1.32,
264
+ "learning_rate": 1.8680823680823682e-05,
265
+ "loss": 0.3335,
266
+ "step": 20500
267
+ },
268
+ {
269
+ "epoch": 1.35,
270
+ "learning_rate": 1.864864864864865e-05,
271
+ "loss": 0.3349,
272
+ "step": 21000
273
+ },
274
+ {
275
+ "epoch": 1.38,
276
+ "learning_rate": 1.8616473616473618e-05,
277
+ "loss": 0.3327,
278
+ "step": 21500
279
+ },
280
+ {
281
+ "epoch": 1.42,
282
+ "learning_rate": 1.8584298584298586e-05,
283
+ "loss": 0.3268,
284
+ "step": 22000
285
+ },
286
+ {
287
+ "epoch": 1.45,
288
+ "learning_rate": 1.8552123552123554e-05,
289
+ "loss": 0.3264,
290
+ "step": 22500
291
+ },
292
+ {
293
+ "epoch": 1.48,
294
+ "learning_rate": 1.8519948519948522e-05,
295
+ "loss": 0.3375,
296
+ "step": 23000
297
+ },
298
+ {
299
+ "epoch": 1.51,
300
+ "learning_rate": 1.848777348777349e-05,
301
+ "loss": 0.333,
302
+ "step": 23500
303
+ },
304
+ {
305
+ "epoch": 1.54,
306
+ "learning_rate": 1.8455598455598458e-05,
307
+ "loss": 0.3373,
308
+ "step": 24000
309
+ },
310
+ {
311
+ "epoch": 1.58,
312
+ "learning_rate": 1.8423423423423425e-05,
313
+ "loss": 0.3327,
314
+ "step": 24500
315
+ },
316
+ {
317
+ "epoch": 1.61,
318
+ "learning_rate": 1.8391248391248393e-05,
319
+ "loss": 0.3297,
320
+ "step": 25000
321
+ },
322
+ {
323
+ "epoch": 1.64,
324
+ "learning_rate": 1.835907335907336e-05,
325
+ "loss": 0.3413,
326
+ "step": 25500
327
+ },
328
+ {
329
+ "epoch": 1.67,
330
+ "learning_rate": 1.832689832689833e-05,
331
+ "loss": 0.3303,
332
+ "step": 26000
333
+ },
334
+ {
335
+ "epoch": 1.71,
336
+ "learning_rate": 1.8294723294723297e-05,
337
+ "loss": 0.3305,
338
+ "step": 26500
339
+ },
340
+ {
341
+ "epoch": 1.74,
342
+ "learning_rate": 1.826254826254826e-05,
343
+ "loss": 0.3334,
344
+ "step": 27000
345
+ },
346
+ {
347
+ "epoch": 1.77,
348
+ "learning_rate": 1.8230373230373233e-05,
349
+ "loss": 0.331,
350
+ "step": 27500
351
+ },
352
+ {
353
+ "epoch": 1.8,
354
+ "learning_rate": 1.81981981981982e-05,
355
+ "loss": 0.3382,
356
+ "step": 28000
357
+ },
358
+ {
359
+ "epoch": 1.83,
360
+ "learning_rate": 1.816602316602317e-05,
361
+ "loss": 0.3361,
362
+ "step": 28500
363
+ },
364
+ {
365
+ "epoch": 1.87,
366
+ "learning_rate": 1.8133848133848137e-05,
367
+ "loss": 0.34,
368
+ "step": 29000
369
+ },
370
+ {
371
+ "epoch": 1.9,
372
+ "learning_rate": 1.8101673101673104e-05,
373
+ "loss": 0.3382,
374
+ "step": 29500
375
+ },
376
+ {
377
+ "epoch": 1.93,
378
+ "learning_rate": 1.806949806949807e-05,
379
+ "loss": 0.3293,
380
+ "step": 30000
381
+ },
382
+ {
383
+ "epoch": 1.96,
384
+ "learning_rate": 1.8037323037323037e-05,
385
+ "loss": 0.3291,
386
+ "step": 30500
387
+ },
388
+ {
389
+ "epoch": 1.99,
390
+ "learning_rate": 1.8005148005148008e-05,
391
+ "loss": 0.3286,
392
+ "step": 31000
393
+ },
394
+ {
395
+ "epoch": 2.0,
396
+ "eval_akurasi": 0.43134920634920637,
397
+ "eval_f1": 0.5178539599548453,
398
+ "eval_loss": 0.34680771827697754,
399
+ "eval_roc_auc": 0.6864955357142858,
400
+ "eval_runtime": 170.8274,
401
+ "eval_samples_per_second": 59.007,
402
+ "eval_steps_per_second": 7.376,
403
+ "step": 31080
404
+ },
405
+ {
406
+ "epoch": 2.03,
407
+ "learning_rate": 1.7972972972972976e-05,
408
+ "loss": 0.3128,
409
+ "step": 31500
410
+ },
411
+ {
412
+ "epoch": 2.06,
413
+ "learning_rate": 1.7940797940797944e-05,
414
+ "loss": 0.301,
415
+ "step": 32000
416
+ },
417
+ {
418
+ "epoch": 2.09,
419
+ "learning_rate": 1.7908622908622912e-05,
420
+ "loss": 0.3053,
421
+ "step": 32500
422
+ },
423
+ {
424
+ "epoch": 2.12,
425
+ "learning_rate": 1.7876447876447876e-05,
426
+ "loss": 0.3079,
427
+ "step": 33000
428
+ },
429
+ {
430
+ "epoch": 2.16,
431
+ "learning_rate": 1.7844272844272844e-05,
432
+ "loss": 0.3001,
433
+ "step": 33500
434
+ },
435
+ {
436
+ "epoch": 2.19,
437
+ "learning_rate": 1.7812097812097812e-05,
438
+ "loss": 0.3017,
439
+ "step": 34000
440
+ },
441
+ {
442
+ "epoch": 2.22,
443
+ "learning_rate": 1.7779922779922783e-05,
444
+ "loss": 0.2996,
445
+ "step": 34500
446
+ },
447
+ {
448
+ "epoch": 2.25,
449
+ "learning_rate": 1.774774774774775e-05,
450
+ "loss": 0.306,
451
+ "step": 35000
452
+ },
453
+ {
454
+ "epoch": 2.28,
455
+ "learning_rate": 1.7715572715572716e-05,
456
+ "loss": 0.3084,
457
+ "step": 35500
458
+ },
459
+ {
460
+ "epoch": 2.32,
461
+ "learning_rate": 1.7683397683397684e-05,
462
+ "loss": 0.3139,
463
+ "step": 36000
464
+ },
465
+ {
466
+ "epoch": 2.35,
467
+ "learning_rate": 1.7651222651222652e-05,
468
+ "loss": 0.3106,
469
+ "step": 36500
470
+ },
471
+ {
472
+ "epoch": 2.38,
473
+ "learning_rate": 1.761904761904762e-05,
474
+ "loss": 0.306,
475
+ "step": 37000
476
+ },
477
+ {
478
+ "epoch": 2.41,
479
+ "learning_rate": 1.7586872586872588e-05,
480
+ "loss": 0.3108,
481
+ "step": 37500
482
+ },
483
+ {
484
+ "epoch": 2.45,
485
+ "learning_rate": 1.7554697554697555e-05,
486
+ "loss": 0.3155,
487
+ "step": 38000
488
+ },
489
+ {
490
+ "epoch": 2.48,
491
+ "learning_rate": 1.7522522522522523e-05,
492
+ "loss": 0.3021,
493
+ "step": 38500
494
+ },
495
+ {
496
+ "epoch": 2.51,
497
+ "learning_rate": 1.749034749034749e-05,
498
+ "loss": 0.31,
499
+ "step": 39000
500
+ },
501
+ {
502
+ "epoch": 2.54,
503
+ "learning_rate": 1.745817245817246e-05,
504
+ "loss": 0.3061,
505
+ "step": 39500
506
+ },
507
+ {
508
+ "epoch": 2.57,
509
+ "learning_rate": 1.7425997425997427e-05,
510
+ "loss": 0.3108,
511
+ "step": 40000
512
+ },
513
+ {
514
+ "epoch": 2.61,
515
+ "learning_rate": 1.7393822393822395e-05,
516
+ "loss": 0.3028,
517
+ "step": 40500
518
+ },
519
+ {
520
+ "epoch": 2.64,
521
+ "learning_rate": 1.7361647361647363e-05,
522
+ "loss": 0.3081,
523
+ "step": 41000
524
+ },
525
+ {
526
+ "epoch": 2.67,
527
+ "learning_rate": 1.732947232947233e-05,
528
+ "loss": 0.3091,
529
+ "step": 41500
530
+ },
531
+ {
532
+ "epoch": 2.7,
533
+ "learning_rate": 1.72972972972973e-05,
534
+ "loss": 0.3063,
535
+ "step": 42000
536
+ },
537
+ {
538
+ "epoch": 2.73,
539
+ "learning_rate": 1.7265122265122267e-05,
540
+ "loss": 0.3085,
541
+ "step": 42500
542
+ },
543
+ {
544
+ "epoch": 2.77,
545
+ "learning_rate": 1.7232947232947234e-05,
546
+ "loss": 0.3079,
547
+ "step": 43000
548
+ },
549
+ {
550
+ "epoch": 2.8,
551
+ "learning_rate": 1.7200772200772202e-05,
552
+ "loss": 0.3109,
553
+ "step": 43500
554
+ },
555
+ {
556
+ "epoch": 2.83,
557
+ "learning_rate": 1.716859716859717e-05,
558
+ "loss": 0.3135,
559
+ "step": 44000
560
+ },
561
+ {
562
+ "epoch": 2.86,
563
+ "learning_rate": 1.7136422136422138e-05,
564
+ "loss": 0.3063,
565
+ "step": 44500
566
+ },
567
+ {
568
+ "epoch": 2.9,
569
+ "learning_rate": 1.7104247104247106e-05,
570
+ "loss": 0.3173,
571
+ "step": 45000
572
+ },
573
+ {
574
+ "epoch": 2.93,
575
+ "learning_rate": 1.7072072072072074e-05,
576
+ "loss": 0.3082,
577
+ "step": 45500
578
+ },
579
+ {
580
+ "epoch": 2.96,
581
+ "learning_rate": 1.7039897039897042e-05,
582
+ "loss": 0.3047,
583
+ "step": 46000
584
+ },
585
+ {
586
+ "epoch": 2.99,
587
+ "learning_rate": 1.700772200772201e-05,
588
+ "loss": 0.3124,
589
+ "step": 46500
590
+ },
591
+ {
592
+ "epoch": 3.0,
593
+ "eval_akurasi": 0.4599206349206349,
594
+ "eval_f1": 0.5274112829845313,
595
+ "eval_loss": 0.3588548004627228,
596
+ "eval_roc_auc": 0.6944568452380953,
597
+ "eval_runtime": 171.0225,
598
+ "eval_samples_per_second": 58.94,
599
+ "eval_steps_per_second": 7.367,
600
+ "step": 46620
601
+ },
602
+ {
603
+ "epoch": 3.02,
604
+ "learning_rate": 1.6975546975546978e-05,
605
+ "loss": 0.2838,
606
+ "step": 47000
607
+ },
608
+ {
609
+ "epoch": 3.06,
610
+ "learning_rate": 1.6943371943371946e-05,
611
+ "loss": 0.2749,
612
+ "step": 47500
613
+ },
614
+ {
615
+ "epoch": 3.09,
616
+ "learning_rate": 1.6911196911196913e-05,
617
+ "loss": 0.2808,
618
+ "step": 48000
619
+ },
620
+ {
621
+ "epoch": 3.12,
622
+ "learning_rate": 1.6879021879021878e-05,
623
+ "loss": 0.2751,
624
+ "step": 48500
625
+ },
626
+ {
627
+ "epoch": 3.15,
628
+ "learning_rate": 1.6846846846846846e-05,
629
+ "loss": 0.279,
630
+ "step": 49000
631
+ },
632
+ {
633
+ "epoch": 3.19,
634
+ "learning_rate": 1.6814671814671817e-05,
635
+ "loss": 0.2743,
636
+ "step": 49500
637
+ },
638
+ {
639
+ "epoch": 3.22,
640
+ "learning_rate": 1.6782496782496785e-05,
641
+ "loss": 0.2787,
642
+ "step": 50000
643
+ },
644
+ {
645
+ "epoch": 3.25,
646
+ "learning_rate": 1.6750321750321753e-05,
647
+ "loss": 0.2796,
648
+ "step": 50500
649
+ },
650
+ {
651
+ "epoch": 3.28,
652
+ "learning_rate": 1.671814671814672e-05,
653
+ "loss": 0.2723,
654
+ "step": 51000
655
+ },
656
+ {
657
+ "epoch": 3.31,
658
+ "learning_rate": 1.6685971685971685e-05,
659
+ "loss": 0.2751,
660
+ "step": 51500
661
+ },
662
+ {
663
+ "epoch": 3.35,
664
+ "learning_rate": 1.6653796653796653e-05,
665
+ "loss": 0.2682,
666
+ "step": 52000
667
+ },
668
+ {
669
+ "epoch": 3.38,
670
+ "learning_rate": 1.662162162162162e-05,
671
+ "loss": 0.2722,
672
+ "step": 52500
673
+ },
674
+ {
675
+ "epoch": 3.41,
676
+ "learning_rate": 1.6589446589446592e-05,
677
+ "loss": 0.2841,
678
+ "step": 53000
679
+ },
680
+ {
681
+ "epoch": 3.44,
682
+ "learning_rate": 1.655727155727156e-05,
683
+ "loss": 0.2762,
684
+ "step": 53500
685
+ },
686
+ {
687
+ "epoch": 3.47,
688
+ "learning_rate": 1.6525096525096528e-05,
689
+ "loss": 0.2762,
690
+ "step": 54000
691
+ },
692
+ {
693
+ "epoch": 3.51,
694
+ "learning_rate": 1.6492921492921493e-05,
695
+ "loss": 0.2785,
696
+ "step": 54500
697
+ },
698
+ {
699
+ "epoch": 3.54,
700
+ "learning_rate": 1.646074646074646e-05,
701
+ "loss": 0.2753,
702
+ "step": 55000
703
+ },
704
+ {
705
+ "epoch": 3.57,
706
+ "learning_rate": 1.642857142857143e-05,
707
+ "loss": 0.2742,
708
+ "step": 55500
709
+ },
710
+ {
711
+ "epoch": 3.6,
712
+ "learning_rate": 1.6396396396396396e-05,
713
+ "loss": 0.282,
714
+ "step": 56000
715
+ },
716
+ {
717
+ "epoch": 3.64,
718
+ "learning_rate": 1.6364221364221368e-05,
719
+ "loss": 0.2767,
720
+ "step": 56500
721
+ },
722
+ {
723
+ "epoch": 3.67,
724
+ "learning_rate": 1.6332046332046336e-05,
725
+ "loss": 0.2851,
726
+ "step": 57000
727
+ },
728
+ {
729
+ "epoch": 3.7,
730
+ "learning_rate": 1.62998712998713e-05,
731
+ "loss": 0.2818,
732
+ "step": 57500
733
+ },
734
+ {
735
+ "epoch": 3.73,
736
+ "learning_rate": 1.6267696267696268e-05,
737
+ "loss": 0.278,
738
+ "step": 58000
739
+ },
740
+ {
741
+ "epoch": 3.76,
742
+ "learning_rate": 1.6235521235521236e-05,
743
+ "loss": 0.2695,
744
+ "step": 58500
745
+ },
746
+ {
747
+ "epoch": 3.8,
748
+ "learning_rate": 1.6203346203346204e-05,
749
+ "loss": 0.2758,
750
+ "step": 59000
751
+ },
752
+ {
753
+ "epoch": 3.83,
754
+ "learning_rate": 1.6171171171171172e-05,
755
+ "loss": 0.2805,
756
+ "step": 59500
757
+ },
758
+ {
759
+ "epoch": 3.86,
760
+ "learning_rate": 1.613899613899614e-05,
761
+ "loss": 0.2846,
762
+ "step": 60000
763
+ },
764
+ {
765
+ "epoch": 3.89,
766
+ "learning_rate": 1.6106821106821108e-05,
767
+ "loss": 0.2774,
768
+ "step": 60500
769
+ },
770
+ {
771
+ "epoch": 3.93,
772
+ "learning_rate": 1.6074646074646076e-05,
773
+ "loss": 0.2808,
774
+ "step": 61000
775
+ },
776
+ {
777
+ "epoch": 3.96,
778
+ "learning_rate": 1.6042471042471043e-05,
779
+ "loss": 0.2833,
780
+ "step": 61500
781
+ },
782
+ {
783
+ "epoch": 3.99,
784
+ "learning_rate": 1.601029601029601e-05,
785
+ "loss": 0.2709,
786
+ "step": 62000
787
+ },
788
+ {
789
+ "epoch": 4.0,
790
+ "eval_akurasi": 0.491765873015873,
791
+ "eval_f1": 0.5355716290618591,
792
+ "eval_loss": 0.37542611360549927,
793
+ "eval_roc_auc": 0.7028645833333333,
794
+ "eval_runtime": 171.2358,
795
+ "eval_samples_per_second": 58.866,
796
+ "eval_steps_per_second": 7.358,
797
+ "step": 62160
798
+ },
799
+ {
800
+ "epoch": 4.02,
801
+ "learning_rate": 1.597812097812098e-05,
802
+ "loss": 0.2595,
803
+ "step": 62500
804
+ },
805
+ {
806
+ "epoch": 4.05,
807
+ "learning_rate": 1.5945945945945947e-05,
808
+ "loss": 0.2407,
809
+ "step": 63000
810
+ },
811
+ {
812
+ "epoch": 4.09,
813
+ "learning_rate": 1.5913770913770915e-05,
814
+ "loss": 0.234,
815
+ "step": 63500
816
+ },
817
+ {
818
+ "epoch": 4.12,
819
+ "learning_rate": 1.5881595881595883e-05,
820
+ "loss": 0.2333,
821
+ "step": 64000
822
+ },
823
+ {
824
+ "epoch": 4.15,
825
+ "learning_rate": 1.584942084942085e-05,
826
+ "loss": 0.2502,
827
+ "step": 64500
828
+ },
829
+ {
830
+ "epoch": 4.18,
831
+ "learning_rate": 1.581724581724582e-05,
832
+ "loss": 0.2441,
833
+ "step": 65000
834
+ },
835
+ {
836
+ "epoch": 4.21,
837
+ "learning_rate": 1.5785070785070787e-05,
838
+ "loss": 0.2452,
839
+ "step": 65500
840
+ },
841
+ {
842
+ "epoch": 4.25,
843
+ "learning_rate": 1.5752895752895755e-05,
844
+ "loss": 0.2418,
845
+ "step": 66000
846
+ },
847
+ {
848
+ "epoch": 4.28,
849
+ "learning_rate": 1.5720720720720722e-05,
850
+ "loss": 0.2442,
851
+ "step": 66500
852
+ },
853
+ {
854
+ "epoch": 4.31,
855
+ "learning_rate": 1.568854568854569e-05,
856
+ "loss": 0.2421,
857
+ "step": 67000
858
+ },
859
+ {
860
+ "epoch": 4.34,
861
+ "learning_rate": 1.5656370656370658e-05,
862
+ "loss": 0.2406,
863
+ "step": 67500
864
+ },
865
+ {
866
+ "epoch": 4.38,
867
+ "learning_rate": 1.5624195624195626e-05,
868
+ "loss": 0.2551,
869
+ "step": 68000
870
+ },
871
+ {
872
+ "epoch": 4.41,
873
+ "learning_rate": 1.5592020592020594e-05,
874
+ "loss": 0.2465,
875
+ "step": 68500
876
+ },
877
+ {
878
+ "epoch": 4.44,
879
+ "learning_rate": 1.5559845559845562e-05,
880
+ "loss": 0.2489,
881
+ "step": 69000
882
+ },
883
+ {
884
+ "epoch": 4.47,
885
+ "learning_rate": 1.552767052767053e-05,
886
+ "loss": 0.2486,
887
+ "step": 69500
888
+ },
889
+ {
890
+ "epoch": 4.5,
891
+ "learning_rate": 1.5495495495495498e-05,
892
+ "loss": 0.2535,
893
+ "step": 70000
894
+ },
895
+ {
896
+ "epoch": 4.54,
897
+ "learning_rate": 1.5463320463320462e-05,
898
+ "loss": 0.2515,
899
+ "step": 70500
900
+ },
901
+ {
902
+ "epoch": 4.57,
903
+ "learning_rate": 1.5431145431145434e-05,
904
+ "loss": 0.2585,
905
+ "step": 71000
906
+ },
907
+ {
908
+ "epoch": 4.6,
909
+ "learning_rate": 1.53989703989704e-05,
910
+ "loss": 0.2451,
911
+ "step": 71500
912
+ },
913
+ {
914
+ "epoch": 4.63,
915
+ "learning_rate": 1.536679536679537e-05,
916
+ "loss": 0.2493,
917
+ "step": 72000
918
+ },
919
+ {
920
+ "epoch": 4.67,
921
+ "learning_rate": 1.5334620334620337e-05,
922
+ "loss": 0.2522,
923
+ "step": 72500
924
+ },
925
+ {
926
+ "epoch": 4.7,
927
+ "learning_rate": 1.5302445302445305e-05,
928
+ "loss": 0.2517,
929
+ "step": 73000
930
+ },
931
+ {
932
+ "epoch": 4.73,
933
+ "learning_rate": 1.527027027027027e-05,
934
+ "loss": 0.2511,
935
+ "step": 73500
936
+ },
937
+ {
938
+ "epoch": 4.76,
939
+ "learning_rate": 1.523809523809524e-05,
940
+ "loss": 0.2542,
941
+ "step": 74000
942
+ },
943
+ {
944
+ "epoch": 4.79,
945
+ "learning_rate": 1.5205920205920209e-05,
946
+ "loss": 0.2568,
947
+ "step": 74500
948
+ },
949
+ {
950
+ "epoch": 4.83,
951
+ "learning_rate": 1.5173745173745175e-05,
952
+ "loss": 0.2528,
953
+ "step": 75000
954
+ },
955
+ {
956
+ "epoch": 4.86,
957
+ "learning_rate": 1.5141570141570143e-05,
958
+ "loss": 0.2463,
959
+ "step": 75500
960
+ },
961
+ {
962
+ "epoch": 4.89,
963
+ "learning_rate": 1.5109395109395111e-05,
964
+ "loss": 0.2491,
965
+ "step": 76000
966
+ },
967
+ {
968
+ "epoch": 4.92,
969
+ "learning_rate": 1.5077220077220079e-05,
970
+ "loss": 0.2519,
971
+ "step": 76500
972
+ },
973
+ {
974
+ "epoch": 4.95,
975
+ "learning_rate": 1.5045045045045045e-05,
976
+ "loss": 0.2594,
977
+ "step": 77000
978
+ },
979
+ {
980
+ "epoch": 4.99,
981
+ "learning_rate": 1.5012870012870013e-05,
982
+ "loss": 0.2539,
983
+ "step": 77500
984
+ },
985
+ {
986
+ "epoch": 5.0,
987
+ "eval_akurasi": 0.489781746031746,
988
+ "eval_f1": 0.5299071938200739,
989
+ "eval_loss": 0.404236763715744,
990
+ "eval_roc_auc": 0.7000744047619047,
991
+ "eval_runtime": 171.3763,
992
+ "eval_samples_per_second": 58.818,
993
+ "eval_steps_per_second": 7.352,
994
+ "step": 77700
995
+ },
996
+ {
997
+ "epoch": 5.02,
998
+ "learning_rate": 1.498069498069498e-05,
999
+ "loss": 0.2286,
1000
+ "step": 78000
1001
+ },
1002
+ {
1003
+ "epoch": 5.05,
1004
+ "learning_rate": 1.494851994851995e-05,
1005
+ "loss": 0.2122,
1006
+ "step": 78500
1007
+ },
1008
+ {
1009
+ "epoch": 5.08,
1010
+ "learning_rate": 1.4916344916344918e-05,
1011
+ "loss": 0.2104,
1012
+ "step": 79000
1013
+ },
1014
+ {
1015
+ "epoch": 5.12,
1016
+ "learning_rate": 1.4884169884169886e-05,
1017
+ "loss": 0.218,
1018
+ "step": 79500
1019
+ },
1020
+ {
1021
+ "epoch": 5.15,
1022
+ "learning_rate": 1.4851994851994852e-05,
1023
+ "loss": 0.2155,
1024
+ "step": 80000
1025
+ },
1026
+ {
1027
+ "epoch": 5.18,
1028
+ "learning_rate": 1.481981981981982e-05,
1029
+ "loss": 0.2241,
1030
+ "step": 80500
1031
+ },
1032
+ {
1033
+ "epoch": 5.21,
1034
+ "learning_rate": 1.4787644787644788e-05,
1035
+ "loss": 0.2214,
1036
+ "step": 81000
1037
+ },
1038
+ {
1039
+ "epoch": 5.24,
1040
+ "learning_rate": 1.4755469755469756e-05,
1041
+ "loss": 0.217,
1042
+ "step": 81500
1043
+ },
1044
+ {
1045
+ "epoch": 5.28,
1046
+ "learning_rate": 1.4723294723294726e-05,
1047
+ "loss": 0.2222,
1048
+ "step": 82000
1049
+ },
1050
+ {
1051
+ "epoch": 5.31,
1052
+ "learning_rate": 1.4691119691119694e-05,
1053
+ "loss": 0.2207,
1054
+ "step": 82500
1055
+ },
1056
+ {
1057
+ "epoch": 5.34,
1058
+ "learning_rate": 1.465894465894466e-05,
1059
+ "loss": 0.2277,
1060
+ "step": 83000
1061
+ },
1062
+ {
1063
+ "epoch": 5.37,
1064
+ "learning_rate": 1.4626769626769628e-05,
1065
+ "loss": 0.2265,
1066
+ "step": 83500
1067
+ },
1068
+ {
1069
+ "epoch": 5.41,
1070
+ "learning_rate": 1.4594594594594596e-05,
1071
+ "loss": 0.224,
1072
+ "step": 84000
1073
+ },
1074
+ {
1075
+ "epoch": 5.44,
1076
+ "learning_rate": 1.4562419562419564e-05,
1077
+ "loss": 0.2177,
1078
+ "step": 84500
1079
+ },
1080
+ {
1081
+ "epoch": 5.47,
1082
+ "learning_rate": 1.453024453024453e-05,
1083
+ "loss": 0.2192,
1084
+ "step": 85000
1085
+ },
1086
+ {
1087
+ "epoch": 5.5,
1088
+ "learning_rate": 1.4498069498069501e-05,
1089
+ "loss": 0.2245,
1090
+ "step": 85500
1091
+ },
1092
+ {
1093
+ "epoch": 5.53,
1094
+ "learning_rate": 1.4465894465894467e-05,
1095
+ "loss": 0.2212,
1096
+ "step": 86000
1097
+ },
1098
+ {
1099
+ "epoch": 5.57,
1100
+ "learning_rate": 1.4433719433719435e-05,
1101
+ "loss": 0.2297,
1102
+ "step": 86500
1103
+ },
1104
+ {
1105
+ "epoch": 5.6,
1106
+ "learning_rate": 1.4401544401544403e-05,
1107
+ "loss": 0.2309,
1108
+ "step": 87000
1109
+ },
1110
+ {
1111
+ "epoch": 5.63,
1112
+ "learning_rate": 1.4369369369369371e-05,
1113
+ "loss": 0.2293,
1114
+ "step": 87500
1115
+ },
1116
+ {
1117
+ "epoch": 5.66,
1118
+ "learning_rate": 1.4337194337194337e-05,
1119
+ "loss": 0.2236,
1120
+ "step": 88000
1121
+ },
1122
+ {
1123
+ "epoch": 5.69,
1124
+ "learning_rate": 1.4305019305019305e-05,
1125
+ "loss": 0.227,
1126
+ "step": 88500
1127
+ },
1128
+ {
1129
+ "epoch": 5.73,
1130
+ "learning_rate": 1.4272844272844275e-05,
1131
+ "loss": 0.2221,
1132
+ "step": 89000
1133
+ },
1134
+ {
1135
+ "epoch": 5.76,
1136
+ "learning_rate": 1.4240669240669243e-05,
1137
+ "loss": 0.2315,
1138
+ "step": 89500
1139
+ },
1140
+ {
1141
+ "epoch": 5.79,
1142
+ "learning_rate": 1.420849420849421e-05,
1143
+ "loss": 0.2289,
1144
+ "step": 90000
1145
+ },
1146
+ {
1147
+ "epoch": 5.82,
1148
+ "learning_rate": 1.4176319176319178e-05,
1149
+ "loss": 0.2285,
1150
+ "step": 90500
1151
+ },
1152
+ {
1153
+ "epoch": 5.86,
1154
+ "learning_rate": 1.4144144144144145e-05,
1155
+ "loss": 0.2291,
1156
+ "step": 91000
1157
+ },
1158
+ {
1159
+ "epoch": 5.89,
1160
+ "learning_rate": 1.4111969111969112e-05,
1161
+ "loss": 0.2201,
1162
+ "step": 91500
1163
+ },
1164
+ {
1165
+ "epoch": 5.92,
1166
+ "learning_rate": 1.407979407979408e-05,
1167
+ "loss": 0.2308,
1168
+ "step": 92000
1169
+ },
1170
+ {
1171
+ "epoch": 5.95,
1172
+ "learning_rate": 1.4047619047619048e-05,
1173
+ "loss": 0.2301,
1174
+ "step": 92500
1175
+ },
1176
+ {
1177
+ "epoch": 5.98,
1178
+ "learning_rate": 1.4015444015444018e-05,
1179
+ "loss": 0.2273,
1180
+ "step": 93000
1181
+ },
1182
+ {
1183
+ "epoch": 6.0,
1184
+ "eval_akurasi": 0.5041666666666667,
1185
+ "eval_f1": 0.5357989568515884,
1186
+ "eval_loss": 0.4383452534675598,
1187
+ "eval_roc_auc": 0.7049107142857142,
1188
+ "eval_runtime": 171.6368,
1189
+ "eval_samples_per_second": 58.729,
1190
+ "eval_steps_per_second": 7.341,
1191
+ "step": 93240
1192
+ }
1193
+ ],
1194
+ "logging_steps": 500,
1195
+ "max_steps": 310800,
1196
+ "num_train_epochs": 20,
1197
+ "save_steps": 500,
1198
+ "total_flos": 1.471940774934958e+17,
1199
+ "trial_name": null,
1200
+ "trial_params": null
1201
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb9942c2554989abc0a1bb30074238418c88d422cb183d1c638047b7ecd7070
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff