Woao commited on
Commit
7afa3ee
·
verified ·
1 Parent(s): 3f3b557

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text-classification
6
+ base_model: uer/roberta-base-finetuned-chinanews-chinese
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ ---
10
+
11
+ # Model Trained Using AutoTrain
12
+
13
+ - Problem type: Text Classification
14
+
15
+ ## Validation Metrics
16
+ loss: 0.08590201288461685
17
+
18
+ f1_macro: 0.9552925131881786
19
+
20
+ f1_micro: 0.9736164736164736
21
+
22
+ f1_weighted: 0.9730779143688454
23
+
24
+ precision_macro: 0.9600774753043094
25
+
26
+ precision_micro: 0.9736164736164736
27
+
28
+ precision_weighted: 0.9743888843393359
29
+
30
+ recall_macro: 0.9541124951907006
31
+
32
+ recall_micro: 0.9736164736164736
33
+
34
+ recall_weighted: 0.9736164736164736
35
+
36
+ accuracy: 0.9736164736164736
checkpoint-2331/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "uer/roberta-base-finetuned-chinanews-chinese",
3
+ "_num_labels": 6,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "\u4e3b\u9898\u6d3b\u52a8",
15
+ "1": "\u5e38\u9a7b\u6d3b\u52a8",
16
+ "2": "\u65b0\u4eba\u6d3b\u52a8",
17
+ "3": "\u7279\u6743\u00b7\u57fa\u91d1\u00b7\u6218\u4ee4\u00b7\u5468\u5361",
18
+ "4": "\u8d27\u5e01\u5145\u503c",
19
+ "5": "\u9650\u65f6\u6d3b\u52a8"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "\u4e3b\u9898\u6d3b\u52a8": 0,
25
+ "\u5e38\u9a7b\u6d3b\u52a8": 1,
26
+ "\u65b0\u4eba\u6d3b\u52a8": 2,
27
+ "\u7279\u6743\u00b7\u57fa\u91d1\u00b7\u6218\u4ee4\u00b7\u5468\u5361": 3,
28
+ "\u8d27\u5e01\u5145\u503c": 4,
29
+ "\u9650\u65f6\u6d3b\u52a8": 5
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.41.0",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 21128
44
+ }
checkpoint-2331/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34239ed338c349e0b355afe4a5d5940f1e2699bb75f2070d9dad7bf533b2df9c
3
+ size 409112544
checkpoint-2331/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:106a2105bfdd5bbbd0916b0cbc19034775cc46fd1a967a481dbc103192537670
3
+ size 818340602
checkpoint-2331/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fc7f61f749668a9aaf672694a631dc41e054c97cc1203b13d5e0b7c303dba86
3
+ size 13990
checkpoint-2331/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e512932b9106cd1d1c30e2601797adbf6f8a52f8cb520bf71239496718e7bee
3
+ size 1064
checkpoint-2331/trainer_state.json ADDED
@@ -0,0 +1,747 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.08590201288461685,
3
+ "best_model_checkpoint": "autotrain-EVENT/checkpoint-2331",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2331,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.032175032175032175,
13
+ "grad_norm": 11.68185806274414,
14
+ "learning_rate": 5.341880341880342e-06,
15
+ "loss": 1.7842,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.06435006435006435,
20
+ "grad_norm": 6.230990886688232,
21
+ "learning_rate": 1.0683760683760684e-05,
22
+ "loss": 1.1267,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.09652509652509653,
27
+ "grad_norm": 4.519747257232666,
28
+ "learning_rate": 1.602564102564103e-05,
29
+ "loss": 0.7128,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.1287001287001287,
34
+ "grad_norm": 1.394315481185913,
35
+ "learning_rate": 2.1367521367521368e-05,
36
+ "loss": 0.5326,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.16087516087516088,
41
+ "grad_norm": 28.153669357299805,
42
+ "learning_rate": 2.670940170940171e-05,
43
+ "loss": 0.4819,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.19305019305019305,
48
+ "grad_norm": 1.6043665409088135,
49
+ "learning_rate": 3.205128205128206e-05,
50
+ "loss": 0.354,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.22522522522522523,
55
+ "grad_norm": 6.796542167663574,
56
+ "learning_rate": 3.739316239316239e-05,
57
+ "loss": 0.3478,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.2574002574002574,
62
+ "grad_norm": 1.6112338304519653,
63
+ "learning_rate": 4.2735042735042735e-05,
64
+ "loss": 0.2892,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.28957528957528955,
69
+ "grad_norm": 0.8286625742912292,
70
+ "learning_rate": 4.8076923076923084e-05,
71
+ "loss": 0.2734,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.32175032175032175,
76
+ "grad_norm": 35.574424743652344,
77
+ "learning_rate": 4.961850262279447e-05,
78
+ "loss": 0.3152,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.3539253539253539,
83
+ "grad_norm": 3.241590738296509,
84
+ "learning_rate": 4.9022412970910824e-05,
85
+ "loss": 0.166,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.3861003861003861,
90
+ "grad_norm": 1.9818757772445679,
91
+ "learning_rate": 4.8426323319027184e-05,
92
+ "loss": 0.1839,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.41827541827541825,
97
+ "grad_norm": 0.07353338599205017,
98
+ "learning_rate": 4.7830233667143544e-05,
99
+ "loss": 0.168,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.45045045045045046,
104
+ "grad_norm": 17.200748443603516,
105
+ "learning_rate": 4.72341440152599e-05,
106
+ "loss": 0.2131,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.4826254826254826,
111
+ "grad_norm": 0.17287948727607727,
112
+ "learning_rate": 4.663805436337626e-05,
113
+ "loss": 0.1893,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.5148005148005148,
118
+ "grad_norm": 2.6518495082855225,
119
+ "learning_rate": 4.604196471149261e-05,
120
+ "loss": 0.1,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.546975546975547,
125
+ "grad_norm": 0.2751850485801697,
126
+ "learning_rate": 4.5445875059608964e-05,
127
+ "loss": 0.2003,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.5791505791505791,
132
+ "grad_norm": 0.1038702130317688,
133
+ "learning_rate": 4.4849785407725324e-05,
134
+ "loss": 0.1516,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.6113256113256114,
139
+ "grad_norm": 3.7733001708984375,
140
+ "learning_rate": 4.425369575584168e-05,
141
+ "loss": 0.1621,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.6435006435006435,
146
+ "grad_norm": 11.369443893432617,
147
+ "learning_rate": 4.365760610395804e-05,
148
+ "loss": 0.209,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.6756756756756757,
153
+ "grad_norm": 1.2104507684707642,
154
+ "learning_rate": 4.30615164520744e-05,
155
+ "loss": 0.0893,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.7078507078507078,
160
+ "grad_norm": 6.639780044555664,
161
+ "learning_rate": 4.246542680019075e-05,
162
+ "loss": 0.1771,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.7400257400257401,
167
+ "grad_norm": 0.2439693808555603,
168
+ "learning_rate": 4.186933714830711e-05,
169
+ "loss": 0.149,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.7722007722007722,
174
+ "grad_norm": 0.13589037954807281,
175
+ "learning_rate": 4.1273247496423464e-05,
176
+ "loss": 0.2146,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.8043758043758044,
181
+ "grad_norm": 0.09856387972831726,
182
+ "learning_rate": 4.067715784453982e-05,
183
+ "loss": 0.2026,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.8365508365508365,
188
+ "grad_norm": 8.529484748840332,
189
+ "learning_rate": 4.008106819265618e-05,
190
+ "loss": 0.1483,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.8687258687258688,
195
+ "grad_norm": 0.18708932399749756,
196
+ "learning_rate": 3.948497854077253e-05,
197
+ "loss": 0.1885,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.9009009009009009,
202
+ "grad_norm": 0.09533143043518066,
203
+ "learning_rate": 3.888888888888889e-05,
204
+ "loss": 0.0893,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.9330759330759331,
209
+ "grad_norm": 1.1151599884033203,
210
+ "learning_rate": 3.829279923700525e-05,
211
+ "loss": 0.1439,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.9652509652509652,
216
+ "grad_norm": 0.049121320247650146,
217
+ "learning_rate": 3.7696709585121604e-05,
218
+ "loss": 0.1269,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.9974259974259975,
223
+ "grad_norm": 4.54576301574707,
224
+ "learning_rate": 3.7100619933237964e-05,
225
+ "loss": 0.058,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 1.0,
230
+ "eval_accuracy": 0.9658944658944659,
231
+ "eval_f1_macro": 0.772591124028629,
232
+ "eval_f1_micro": 0.9658944658944659,
233
+ "eval_f1_weighted": 0.9654973088654933,
234
+ "eval_loss": 0.15877199172973633,
235
+ "eval_precision_macro": 0.7681480676677164,
236
+ "eval_precision_micro": 0.9658944658944659,
237
+ "eval_precision_weighted": 0.9664943022041425,
238
+ "eval_recall_macro": 0.7828568464611712,
239
+ "eval_recall_micro": 0.9658944658944659,
240
+ "eval_recall_weighted": 0.9658944658944659,
241
+ "eval_runtime": 250.4762,
242
+ "eval_samples_per_second": 6.204,
243
+ "eval_steps_per_second": 0.391,
244
+ "step": 777
245
+ },
246
+ {
247
+ "epoch": 1.0296010296010296,
248
+ "grad_norm": 0.06902267038822174,
249
+ "learning_rate": 3.650453028135432e-05,
250
+ "loss": 0.0681,
251
+ "step": 800
252
+ },
253
+ {
254
+ "epoch": 1.0617760617760619,
255
+ "grad_norm": 0.03424418717622757,
256
+ "learning_rate": 3.590844062947068e-05,
257
+ "loss": 0.1559,
258
+ "step": 825
259
+ },
260
+ {
261
+ "epoch": 1.093951093951094,
262
+ "grad_norm": 0.06254427880048752,
263
+ "learning_rate": 3.531235097758703e-05,
264
+ "loss": 0.0564,
265
+ "step": 850
266
+ },
267
+ {
268
+ "epoch": 1.1261261261261262,
269
+ "grad_norm": 0.13381192088127136,
270
+ "learning_rate": 3.4716261325703384e-05,
271
+ "loss": 0.1388,
272
+ "step": 875
273
+ },
274
+ {
275
+ "epoch": 1.1583011583011582,
276
+ "grad_norm": 14.801521301269531,
277
+ "learning_rate": 3.4120171673819744e-05,
278
+ "loss": 0.1437,
279
+ "step": 900
280
+ },
281
+ {
282
+ "epoch": 1.1904761904761905,
283
+ "grad_norm": 8.712313652038574,
284
+ "learning_rate": 3.35240820219361e-05,
285
+ "loss": 0.1262,
286
+ "step": 925
287
+ },
288
+ {
289
+ "epoch": 1.2226512226512227,
290
+ "grad_norm": 0.02129649743437767,
291
+ "learning_rate": 3.292799237005246e-05,
292
+ "loss": 0.101,
293
+ "step": 950
294
+ },
295
+ {
296
+ "epoch": 1.2548262548262548,
297
+ "grad_norm": 0.08888272196054459,
298
+ "learning_rate": 3.233190271816882e-05,
299
+ "loss": 0.2086,
300
+ "step": 975
301
+ },
302
+ {
303
+ "epoch": 1.287001287001287,
304
+ "grad_norm": 6.242756366729736,
305
+ "learning_rate": 3.173581306628517e-05,
306
+ "loss": 0.1234,
307
+ "step": 1000
308
+ },
309
+ {
310
+ "epoch": 1.3191763191763193,
311
+ "grad_norm": 0.01962357573211193,
312
+ "learning_rate": 3.113972341440153e-05,
313
+ "loss": 0.0653,
314
+ "step": 1025
315
+ },
316
+ {
317
+ "epoch": 1.3513513513513513,
318
+ "grad_norm": 18.92928695678711,
319
+ "learning_rate": 3.0543633762517884e-05,
320
+ "loss": 0.146,
321
+ "step": 1050
322
+ },
323
+ {
324
+ "epoch": 1.3835263835263836,
325
+ "grad_norm": 2.8306164741516113,
326
+ "learning_rate": 2.994754411063424e-05,
327
+ "loss": 0.1142,
328
+ "step": 1075
329
+ },
330
+ {
331
+ "epoch": 1.4157014157014158,
332
+ "grad_norm": 0.09596404433250427,
333
+ "learning_rate": 2.93514544587506e-05,
334
+ "loss": 0.1631,
335
+ "step": 1100
336
+ },
337
+ {
338
+ "epoch": 1.4478764478764479,
339
+ "grad_norm": 0.200534388422966,
340
+ "learning_rate": 2.8755364806866954e-05,
341
+ "loss": 0.0705,
342
+ "step": 1125
343
+ },
344
+ {
345
+ "epoch": 1.4800514800514801,
346
+ "grad_norm": 6.499765396118164,
347
+ "learning_rate": 2.815927515498331e-05,
348
+ "loss": 0.0771,
349
+ "step": 1150
350
+ },
351
+ {
352
+ "epoch": 1.5122265122265124,
353
+ "grad_norm": 0.01246571820229292,
354
+ "learning_rate": 2.756318550309967e-05,
355
+ "loss": 0.0237,
356
+ "step": 1175
357
+ },
358
+ {
359
+ "epoch": 1.5444015444015444,
360
+ "grad_norm": 106.53581237792969,
361
+ "learning_rate": 2.6967095851216024e-05,
362
+ "loss": 0.0858,
363
+ "step": 1200
364
+ },
365
+ {
366
+ "epoch": 1.5765765765765765,
367
+ "grad_norm": 0.30157119035720825,
368
+ "learning_rate": 2.637100619933238e-05,
369
+ "loss": 0.1932,
370
+ "step": 1225
371
+ },
372
+ {
373
+ "epoch": 1.6087516087516087,
374
+ "grad_norm": 0.030282437801361084,
375
+ "learning_rate": 2.5774916547448734e-05,
376
+ "loss": 0.0628,
377
+ "step": 1250
378
+ },
379
+ {
380
+ "epoch": 1.640926640926641,
381
+ "grad_norm": 0.01327039860188961,
382
+ "learning_rate": 2.5178826895565094e-05,
383
+ "loss": 0.0115,
384
+ "step": 1275
385
+ },
386
+ {
387
+ "epoch": 1.673101673101673,
388
+ "grad_norm": 0.3962545394897461,
389
+ "learning_rate": 2.458273724368145e-05,
390
+ "loss": 0.1223,
391
+ "step": 1300
392
+ },
393
+ {
394
+ "epoch": 1.7052767052767053,
395
+ "grad_norm": 0.060676004737615585,
396
+ "learning_rate": 2.3986647591797807e-05,
397
+ "loss": 0.1351,
398
+ "step": 1325
399
+ },
400
+ {
401
+ "epoch": 1.7374517374517375,
402
+ "grad_norm": 10.573041915893555,
403
+ "learning_rate": 2.3390557939914164e-05,
404
+ "loss": 0.0516,
405
+ "step": 1350
406
+ },
407
+ {
408
+ "epoch": 1.7696267696267696,
409
+ "grad_norm": 0.7964749932289124,
410
+ "learning_rate": 2.279446828803052e-05,
411
+ "loss": 0.0549,
412
+ "step": 1375
413
+ },
414
+ {
415
+ "epoch": 1.8018018018018018,
416
+ "grad_norm": 7.966588020324707,
417
+ "learning_rate": 2.2198378636146877e-05,
418
+ "loss": 0.155,
419
+ "step": 1400
420
+ },
421
+ {
422
+ "epoch": 1.833976833976834,
423
+ "grad_norm": 0.019958429038524628,
424
+ "learning_rate": 2.1602288984263234e-05,
425
+ "loss": 0.0414,
426
+ "step": 1425
427
+ },
428
+ {
429
+ "epoch": 1.8661518661518661,
430
+ "grad_norm": 4.273733615875244,
431
+ "learning_rate": 2.100619933237959e-05,
432
+ "loss": 0.1769,
433
+ "step": 1450
434
+ },
435
+ {
436
+ "epoch": 1.8983268983268984,
437
+ "grad_norm": 0.011619496159255505,
438
+ "learning_rate": 2.0410109680495947e-05,
439
+ "loss": 0.0598,
440
+ "step": 1475
441
+ },
442
+ {
443
+ "epoch": 1.9305019305019306,
444
+ "grad_norm": 3.8245315551757812,
445
+ "learning_rate": 1.9814020028612304e-05,
446
+ "loss": 0.1632,
447
+ "step": 1500
448
+ },
449
+ {
450
+ "epoch": 1.9626769626769627,
451
+ "grad_norm": 0.02121666446328163,
452
+ "learning_rate": 1.921793037672866e-05,
453
+ "loss": 0.0474,
454
+ "step": 1525
455
+ },
456
+ {
457
+ "epoch": 1.9948519948519947,
458
+ "grad_norm": 0.023423343896865845,
459
+ "learning_rate": 1.862184072484502e-05,
460
+ "loss": 0.0394,
461
+ "step": 1550
462
+ },
463
+ {
464
+ "epoch": 2.0,
465
+ "eval_accuracy": 0.9736164736164736,
466
+ "eval_f1_macro": 0.9559989029773911,
467
+ "eval_f1_micro": 0.9736164736164736,
468
+ "eval_f1_weighted": 0.9729748817677593,
469
+ "eval_loss": 0.10379565507173538,
470
+ "eval_precision_macro": 0.9641828592385946,
471
+ "eval_precision_micro": 0.9736164736164736,
472
+ "eval_precision_weighted": 0.9739386934178119,
473
+ "eval_recall_macro": 0.9503030193594619,
474
+ "eval_recall_micro": 0.9736164736164736,
475
+ "eval_recall_weighted": 0.9736164736164736,
476
+ "eval_runtime": 243.5935,
477
+ "eval_samples_per_second": 6.379,
478
+ "eval_steps_per_second": 0.402,
479
+ "step": 1554
480
+ },
481
+ {
482
+ "epoch": 2.027027027027027,
483
+ "grad_norm": 0.014448375441133976,
484
+ "learning_rate": 1.8025751072961374e-05,
485
+ "loss": 0.0738,
486
+ "step": 1575
487
+ },
488
+ {
489
+ "epoch": 2.0592020592020592,
490
+ "grad_norm": 1.0607327222824097,
491
+ "learning_rate": 1.742966142107773e-05,
492
+ "loss": 0.0453,
493
+ "step": 1600
494
+ },
495
+ {
496
+ "epoch": 2.0913770913770913,
497
+ "grad_norm": 0.034898240119218826,
498
+ "learning_rate": 1.6833571769194087e-05,
499
+ "loss": 0.1593,
500
+ "step": 1625
501
+ },
502
+ {
503
+ "epoch": 2.1235521235521237,
504
+ "grad_norm": 3.719592332839966,
505
+ "learning_rate": 1.6237482117310444e-05,
506
+ "loss": 0.105,
507
+ "step": 1650
508
+ },
509
+ {
510
+ "epoch": 2.155727155727156,
511
+ "grad_norm": 0.02683943510055542,
512
+ "learning_rate": 1.56413924654268e-05,
513
+ "loss": 0.0575,
514
+ "step": 1675
515
+ },
516
+ {
517
+ "epoch": 2.187902187902188,
518
+ "grad_norm": 0.014749615453183651,
519
+ "learning_rate": 1.5045302813543157e-05,
520
+ "loss": 0.0777,
521
+ "step": 1700
522
+ },
523
+ {
524
+ "epoch": 2.2200772200772203,
525
+ "grad_norm": 0.016101358458399773,
526
+ "learning_rate": 1.4449213161659514e-05,
527
+ "loss": 0.0226,
528
+ "step": 1725
529
+ },
530
+ {
531
+ "epoch": 2.2522522522522523,
532
+ "grad_norm": 0.18409115076065063,
533
+ "learning_rate": 1.385312350977587e-05,
534
+ "loss": 0.1178,
535
+ "step": 1750
536
+ },
537
+ {
538
+ "epoch": 2.2844272844272844,
539
+ "grad_norm": 0.012963847257196903,
540
+ "learning_rate": 1.3257033857892229e-05,
541
+ "loss": 0.0424,
542
+ "step": 1775
543
+ },
544
+ {
545
+ "epoch": 2.3166023166023164,
546
+ "grad_norm": 0.020922504365444183,
547
+ "learning_rate": 1.2660944206008585e-05,
548
+ "loss": 0.0916,
549
+ "step": 1800
550
+ },
551
+ {
552
+ "epoch": 2.348777348777349,
553
+ "grad_norm": 0.020266762003302574,
554
+ "learning_rate": 1.206485455412494e-05,
555
+ "loss": 0.0398,
556
+ "step": 1825
557
+ },
558
+ {
559
+ "epoch": 2.380952380952381,
560
+ "grad_norm": 0.011511508375406265,
561
+ "learning_rate": 1.1468764902241299e-05,
562
+ "loss": 0.047,
563
+ "step": 1850
564
+ },
565
+ {
566
+ "epoch": 2.413127413127413,
567
+ "grad_norm": 0.011209013871848583,
568
+ "learning_rate": 1.0872675250357654e-05,
569
+ "loss": 0.0416,
570
+ "step": 1875
571
+ },
572
+ {
573
+ "epoch": 2.4453024453024454,
574
+ "grad_norm": 0.019312728196382523,
575
+ "learning_rate": 1.027658559847401e-05,
576
+ "loss": 0.0408,
577
+ "step": 1900
578
+ },
579
+ {
580
+ "epoch": 2.4774774774774775,
581
+ "grad_norm": 0.015620889142155647,
582
+ "learning_rate": 9.680495946590367e-06,
583
+ "loss": 0.0712,
584
+ "step": 1925
585
+ },
586
+ {
587
+ "epoch": 2.5096525096525095,
588
+ "grad_norm": 0.010242036543786526,
589
+ "learning_rate": 9.084406294706724e-06,
590
+ "loss": 0.0537,
591
+ "step": 1950
592
+ },
593
+ {
594
+ "epoch": 2.5418275418275416,
595
+ "grad_norm": 0.03769510239362717,
596
+ "learning_rate": 8.488316642823082e-06,
597
+ "loss": 0.0723,
598
+ "step": 1975
599
+ },
600
+ {
601
+ "epoch": 2.574002574002574,
602
+ "grad_norm": 0.011480485089123249,
603
+ "learning_rate": 7.892226990939437e-06,
604
+ "loss": 0.0222,
605
+ "step": 2000
606
+ },
607
+ {
608
+ "epoch": 2.606177606177606,
609
+ "grad_norm": 5.9189887046813965,
610
+ "learning_rate": 7.296137339055794e-06,
611
+ "loss": 0.0555,
612
+ "step": 2025
613
+ },
614
+ {
615
+ "epoch": 2.6383526383526386,
616
+ "grad_norm": 0.09751153737306595,
617
+ "learning_rate": 6.700047687172151e-06,
618
+ "loss": 0.007,
619
+ "step": 2050
620
+ },
621
+ {
622
+ "epoch": 2.6705276705276706,
623
+ "grad_norm": 0.026520784944295883,
624
+ "learning_rate": 6.103958035288508e-06,
625
+ "loss": 0.03,
626
+ "step": 2075
627
+ },
628
+ {
629
+ "epoch": 2.7027027027027026,
630
+ "grad_norm": 0.007995215244591236,
631
+ "learning_rate": 5.507868383404864e-06,
632
+ "loss": 0.0968,
633
+ "step": 2100
634
+ },
635
+ {
636
+ "epoch": 2.7348777348777347,
637
+ "grad_norm": 0.015287132933735847,
638
+ "learning_rate": 4.911778731521221e-06,
639
+ "loss": 0.0496,
640
+ "step": 2125
641
+ },
642
+ {
643
+ "epoch": 2.767052767052767,
644
+ "grad_norm": 0.014539040625095367,
645
+ "learning_rate": 4.315689079637578e-06,
646
+ "loss": 0.0073,
647
+ "step": 2150
648
+ },
649
+ {
650
+ "epoch": 2.799227799227799,
651
+ "grad_norm": 0.011436503380537033,
652
+ "learning_rate": 3.7195994277539344e-06,
653
+ "loss": 0.0382,
654
+ "step": 2175
655
+ },
656
+ {
657
+ "epoch": 2.8314028314028317,
658
+ "grad_norm": 0.012776638381183147,
659
+ "learning_rate": 3.123509775870291e-06,
660
+ "loss": 0.0606,
661
+ "step": 2200
662
+ },
663
+ {
664
+ "epoch": 2.8635778635778637,
665
+ "grad_norm": 0.011094256304204464,
666
+ "learning_rate": 2.5274201239866477e-06,
667
+ "loss": 0.0281,
668
+ "step": 2225
669
+ },
670
+ {
671
+ "epoch": 2.8957528957528957,
672
+ "grad_norm": 3.787529706954956,
673
+ "learning_rate": 1.9313304721030048e-06,
674
+ "loss": 0.0462,
675
+ "step": 2250
676
+ },
677
+ {
678
+ "epoch": 2.9279279279279278,
679
+ "grad_norm": 0.49334508180618286,
680
+ "learning_rate": 1.3352408202193612e-06,
681
+ "loss": 0.0321,
682
+ "step": 2275
683
+ },
684
+ {
685
+ "epoch": 2.9601029601029603,
686
+ "grad_norm": 0.015266060829162598,
687
+ "learning_rate": 7.391511683357177e-07,
688
+ "loss": 0.0072,
689
+ "step": 2300
690
+ },
691
+ {
692
+ "epoch": 2.9922779922779923,
693
+ "grad_norm": 0.008497793227434158,
694
+ "learning_rate": 1.430615164520744e-07,
695
+ "loss": 0.0373,
696
+ "step": 2325
697
+ },
698
+ {
699
+ "epoch": 3.0,
700
+ "eval_accuracy": 0.9736164736164736,
701
+ "eval_f1_macro": 0.9552925131881786,
702
+ "eval_f1_micro": 0.9736164736164736,
703
+ "eval_f1_weighted": 0.9730779143688454,
704
+ "eval_loss": 0.08590201288461685,
705
+ "eval_precision_macro": 0.9600774753043094,
706
+ "eval_precision_micro": 0.9736164736164736,
707
+ "eval_precision_weighted": 0.9743888843393359,
708
+ "eval_recall_macro": 0.9541124951907006,
709
+ "eval_recall_micro": 0.9736164736164736,
710
+ "eval_recall_weighted": 0.9736164736164736,
711
+ "eval_runtime": 274.6108,
712
+ "eval_samples_per_second": 5.659,
713
+ "eval_steps_per_second": 0.357,
714
+ "step": 2331
715
+ }
716
+ ],
717
+ "logging_steps": 25,
718
+ "max_steps": 2331,
719
+ "num_input_tokens_seen": 0,
720
+ "num_train_epochs": 3,
721
+ "save_steps": 500,
722
+ "stateful_callbacks": {
723
+ "EarlyStoppingCallback": {
724
+ "args": {
725
+ "early_stopping_patience": 5,
726
+ "early_stopping_threshold": 0.01
727
+ },
728
+ "attributes": {
729
+ "early_stopping_patience_counter": 0
730
+ }
731
+ },
732
+ "TrainerControl": {
733
+ "args": {
734
+ "should_epoch_stop": false,
735
+ "should_evaluate": false,
736
+ "should_log": false,
737
+ "should_save": true,
738
+ "should_training_stop": true
739
+ },
740
+ "attributes": {}
741
+ }
742
+ },
743
+ "total_flos": 1226273112769536.0,
744
+ "train_batch_size": 8,
745
+ "trial_name": null,
746
+ "trial_params": null
747
+ }
checkpoint-2331/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e74f5608d1ef20f887d78e8dcd203cb8bbc5c80f52e6eb90871344b27f884b8
3
+ size 5112
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "uer/roberta-base-finetuned-chinanews-chinese",
3
+ "_num_labels": 6,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "\u4e3b\u9898\u6d3b\u52a8",
15
+ "1": "\u5e38\u9a7b\u6d3b\u52a8",
16
+ "2": "\u65b0\u4eba\u6d3b\u52a8",
17
+ "3": "\u7279\u6743\u00b7\u57fa\u91d1\u00b7\u6218\u4ee4\u00b7\u5468\u5361",
18
+ "4": "\u8d27\u5e01\u5145\u503c",
19
+ "5": "\u9650\u65f6\u6d3b\u52a8"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "\u4e3b\u9898\u6d3b\u52a8": 0,
25
+ "\u5e38\u9a7b\u6d3b\u52a8": 1,
26
+ "\u65b0\u4eba\u6d3b\u52a8": 2,
27
+ "\u7279\u6743\u00b7\u57fa\u91d1\u00b7\u6218\u4ee4\u00b7\u5468\u5361": 3,
28
+ "\u8d27\u5e01\u5145\u503c": 4,
29
+ "\u9650\u65f6\u6d3b\u52a8": 5
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.41.0",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 21128
44
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34239ed338c349e0b355afe4a5d5940f1e2699bb75f2070d9dad7bf533b2df9c
3
+ size 409112544
runs/Jun05_05-50-08_r-woao-chinese-class-s80cial6-94945-6uslq/events.out.tfevents.1717566610.r-woao-chinese-class-s80cial6-94945-6uslq.114.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:061dcff7bfacc6474633b051dc80de61d56b076f6dcd588572c61fe15b920d01
3
- size 25655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed0842a0c75ede460948edc551208663422bd7e52152f1842f0d5599f8bf9c8d
3
+ size 27897
runs/Jun05_05-50-08_r-woao-chinese-class-s80cial6-94945-6uslq/events.out.tfevents.1717579625.r-woao-chinese-class-s80cial6-94945-6uslq.114.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd713155ae63ce0e64560d2986de471e12c958553b8432bcdeaa7ff07b4bfea2
3
+ size 921
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e74f5608d1ef20f887d78e8dcd203cb8bbc5c80f52e6eb90871344b27f884b8
3
+ size 5112
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-EVENT/autotrain-data",
3
+ "model": "uer/roberta-base-finetuned-chinanews-chinese",
4
+ "lr": 5e-05,
5
+ "epochs": 3,
6
+ "max_seq_length": 128,
7
+ "batch_size": 8,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "text_column": "autotrain_text",
18
+ "target_column": "autotrain_label",
19
+ "logging_steps": -1,
20
+ "project_name": "autotrain-EVENT",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "evaluation_strategy": "epoch",
26
+ "username": "Woao",
27
+ "log": "tensorboard",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff