cyying commited on
Commit
445a1c2
·
verified ·
1 Parent(s): 5afd48f

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ library_name: transformers
4
+ tags:
5
+ - autotrain
6
+ - text-classification
7
+ base_model: google-bert/bert-base-uncased
8
+ widget:
9
+ - text: "I love AutoTrain"
10
+ ---
11
+
12
+ # Model Trained Using AutoTrain
13
+
14
+ - Problem type: Text Classification
15
+
16
+ ## Validation Metrics
17
+ loss: 0.9738104939460754
18
+
19
+ f1_macro: 0.6658494548344828
20
+
21
+ f1_micro: 0.6706730769230769
22
+
23
+ f1_weighted: 0.6675736368483096
24
+
25
+ precision_macro: 0.6694452026078725
26
+
27
+ precision_micro: 0.6706730769230769
28
+
29
+ precision_weighted: 0.6700176765328316
30
+
31
+ recall_macro: 0.667714178467355
32
+
33
+ recall_micro: 0.6706730769230769
34
+
35
+ recall_weighted: 0.6706730769230769
36
+
37
+ accuracy: 0.6706730769230769
checkpoint-1248/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "_num_labels": 8,
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": "\u53ad\u60e1\u8a9e\u8abf",
15
+ "1": "\u5e73\u6de1\u8a9e\u6c23",
16
+ "2": "\u60b2\u50b7\u8a9e\u8abf",
17
+ "3": "\u61a4\u6012\u8a9e\u8abf",
18
+ "4": "\u7591\u554f\u8a9e\u8abf",
19
+ "5": "\u958b\u5fc3\u8a9e\u8abf",
20
+ "6": "\u95dc\u5207\u8a9e\u8abf",
21
+ "7": "\u9a5a\u5947\u8a9e\u8abf"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "\u53ad\u60e1\u8a9e\u8abf": 0,
27
+ "\u5e73\u6de1\u8a9e\u6c23": 1,
28
+ "\u60b2\u50b7\u8a9e\u8abf": 2,
29
+ "\u61a4\u6012\u8a9e\u8abf": 3,
30
+ "\u7591\u554f\u8a9e\u8abf": 4,
31
+ "\u958b\u5fc3\u8a9e\u8abf": 5,
32
+ "\u95dc\u5207\u8a9e\u8abf": 6,
33
+ "\u9a5a\u5947\u8a9e\u8abf": 7
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "problem_type": "single_label_classification",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-1248/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a60e8f2aab006de9accdf878f2b1055294b2866acd92f007341f08f067a5655
3
+ size 437977104
checkpoint-1248/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c404f35dc0209b05f56419855a6f23b9ec69b1edb25f73524b4b33418454bc5b
3
+ size 876069626
checkpoint-1248/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613e686bdc544fd89b4a2d7ca0e7c8318d2189169f5384dd1e9e906d36381c34
3
+ size 13990
checkpoint-1248/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d05639adb97d4bd2193bb96428534c863cd328cfcc53a3a20e2ffefb203697f
3
+ size 1064
checkpoint-1248/trainer_state.json ADDED
@@ -0,0 +1,530 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9738104939460754,
3
+ "best_model_checkpoint": "autotrain-e3who-rl7wb/checkpoint-1248",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1248,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04807692307692308,
13
+ "grad_norm": 11.674389839172363,
14
+ "learning_rate": 8.000000000000001e-06,
15
+ "loss": 2.0847,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.09615384615384616,
20
+ "grad_norm": 10.00346851348877,
21
+ "learning_rate": 1.6000000000000003e-05,
22
+ "loss": 2.0137,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.14423076923076922,
27
+ "grad_norm": 9.38170337677002,
28
+ "learning_rate": 2.4e-05,
29
+ "loss": 1.9327,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.19230769230769232,
34
+ "grad_norm": 8.871125221252441,
35
+ "learning_rate": 3.2000000000000005e-05,
36
+ "loss": 1.879,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.2403846153846154,
41
+ "grad_norm": 5.923038959503174,
42
+ "learning_rate": 4e-05,
43
+ "loss": 1.7245,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.28846153846153844,
48
+ "grad_norm": 7.439846038818359,
49
+ "learning_rate": 4.8e-05,
50
+ "loss": 1.5266,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.33653846153846156,
55
+ "grad_norm": 6.5186991691589355,
56
+ "learning_rate": 4.9332146037399826e-05,
57
+ "loss": 1.551,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.38461538461538464,
62
+ "grad_norm": 19.113332748413086,
63
+ "learning_rate": 4.844167408726625e-05,
64
+ "loss": 1.5237,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.4326923076923077,
69
+ "grad_norm": 5.98344087600708,
70
+ "learning_rate": 4.755120213713268e-05,
71
+ "loss": 1.5078,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.4807692307692308,
76
+ "grad_norm": 6.7967047691345215,
77
+ "learning_rate": 4.666073018699911e-05,
78
+ "loss": 1.5408,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.5288461538461539,
83
+ "grad_norm": 8.644440650939941,
84
+ "learning_rate": 4.577025823686554e-05,
85
+ "loss": 1.5727,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.5769230769230769,
90
+ "grad_norm": 13.624725341796875,
91
+ "learning_rate": 4.487978628673197e-05,
92
+ "loss": 1.5456,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.625,
97
+ "grad_norm": 8.256715774536133,
98
+ "learning_rate": 4.39893143365984e-05,
99
+ "loss": 1.5259,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.6730769230769231,
104
+ "grad_norm": 5.904226779937744,
105
+ "learning_rate": 4.309884238646483e-05,
106
+ "loss": 1.5871,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.7211538461538461,
111
+ "grad_norm": 6.76925802230835,
112
+ "learning_rate": 4.2208370436331254e-05,
113
+ "loss": 1.478,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.7692307692307693,
118
+ "grad_norm": 6.825554847717285,
119
+ "learning_rate": 4.1317898486197685e-05,
120
+ "loss": 1.4111,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.8173076923076923,
125
+ "grad_norm": 6.132884502410889,
126
+ "learning_rate": 4.0427426536064116e-05,
127
+ "loss": 1.3338,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.8653846153846154,
132
+ "grad_norm": 12.595861434936523,
133
+ "learning_rate": 3.953695458593055e-05,
134
+ "loss": 1.4382,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.9134615384615384,
139
+ "grad_norm": 7.732487678527832,
140
+ "learning_rate": 3.864648263579698e-05,
141
+ "loss": 1.5317,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.9615384615384616,
146
+ "grad_norm": 7.2850446701049805,
147
+ "learning_rate": 3.77560106856634e-05,
148
+ "loss": 1.4916,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 1.0,
153
+ "eval_accuracy": 0.4362980769230769,
154
+ "eval_f1_macro": 0.38823820729318503,
155
+ "eval_f1_micro": 0.4362980769230769,
156
+ "eval_f1_weighted": 0.38644947334537555,
157
+ "eval_loss": 1.4391758441925049,
158
+ "eval_precision_macro": 0.4372530277536922,
159
+ "eval_precision_micro": 0.4362980769230769,
160
+ "eval_precision_weighted": 0.4252989320853903,
161
+ "eval_recall_macro": 0.42858524320512215,
162
+ "eval_recall_micro": 0.4362980769230769,
163
+ "eval_recall_weighted": 0.4362980769230769,
164
+ "eval_runtime": 134.6918,
165
+ "eval_samples_per_second": 6.177,
166
+ "eval_steps_per_second": 0.386,
167
+ "step": 416
168
+ },
169
+ {
170
+ "epoch": 1.0096153846153846,
171
+ "grad_norm": 7.571177959442139,
172
+ "learning_rate": 3.6865538735529834e-05,
173
+ "loss": 1.4211,
174
+ "step": 420
175
+ },
176
+ {
177
+ "epoch": 1.0576923076923077,
178
+ "grad_norm": 10.535785675048828,
179
+ "learning_rate": 3.597506678539626e-05,
180
+ "loss": 1.3545,
181
+ "step": 440
182
+ },
183
+ {
184
+ "epoch": 1.1057692307692308,
185
+ "grad_norm": 5.157609939575195,
186
+ "learning_rate": 3.508459483526269e-05,
187
+ "loss": 1.3541,
188
+ "step": 460
189
+ },
190
+ {
191
+ "epoch": 1.1538461538461537,
192
+ "grad_norm": 5.49186372756958,
193
+ "learning_rate": 3.419412288512912e-05,
194
+ "loss": 1.3949,
195
+ "step": 480
196
+ },
197
+ {
198
+ "epoch": 1.2019230769230769,
199
+ "grad_norm": 8.001138687133789,
200
+ "learning_rate": 3.330365093499555e-05,
201
+ "loss": 1.4223,
202
+ "step": 500
203
+ },
204
+ {
205
+ "epoch": 1.25,
206
+ "grad_norm": 5.453105449676514,
207
+ "learning_rate": 3.241317898486198e-05,
208
+ "loss": 1.4336,
209
+ "step": 520
210
+ },
211
+ {
212
+ "epoch": 1.2980769230769231,
213
+ "grad_norm": 9.639703750610352,
214
+ "learning_rate": 3.1522707034728406e-05,
215
+ "loss": 1.3314,
216
+ "step": 540
217
+ },
218
+ {
219
+ "epoch": 1.3461538461538463,
220
+ "grad_norm": 8.409910202026367,
221
+ "learning_rate": 3.063223508459484e-05,
222
+ "loss": 1.3744,
223
+ "step": 560
224
+ },
225
+ {
226
+ "epoch": 1.3942307692307692,
227
+ "grad_norm": 8.238600730895996,
228
+ "learning_rate": 2.9741763134461265e-05,
229
+ "loss": 1.3158,
230
+ "step": 580
231
+ },
232
+ {
233
+ "epoch": 1.4423076923076923,
234
+ "grad_norm": 11.363844871520996,
235
+ "learning_rate": 2.8851291184327693e-05,
236
+ "loss": 1.23,
237
+ "step": 600
238
+ },
239
+ {
240
+ "epoch": 1.4903846153846154,
241
+ "grad_norm": 9.3771390914917,
242
+ "learning_rate": 2.7960819234194124e-05,
243
+ "loss": 1.3987,
244
+ "step": 620
245
+ },
246
+ {
247
+ "epoch": 1.5384615384615383,
248
+ "grad_norm": 6.3942341804504395,
249
+ "learning_rate": 2.7070347284060555e-05,
250
+ "loss": 1.2284,
251
+ "step": 640
252
+ },
253
+ {
254
+ "epoch": 1.5865384615384617,
255
+ "grad_norm": 11.658981323242188,
256
+ "learning_rate": 2.6179875333926983e-05,
257
+ "loss": 1.2952,
258
+ "step": 660
259
+ },
260
+ {
261
+ "epoch": 1.6346153846153846,
262
+ "grad_norm": 13.555744171142578,
263
+ "learning_rate": 2.5289403383793414e-05,
264
+ "loss": 1.2832,
265
+ "step": 680
266
+ },
267
+ {
268
+ "epoch": 1.6826923076923077,
269
+ "grad_norm": 14.48792552947998,
270
+ "learning_rate": 2.439893143365984e-05,
271
+ "loss": 1.1761,
272
+ "step": 700
273
+ },
274
+ {
275
+ "epoch": 1.7307692307692308,
276
+ "grad_norm": 8.11705207824707,
277
+ "learning_rate": 2.3508459483526273e-05,
278
+ "loss": 1.1465,
279
+ "step": 720
280
+ },
281
+ {
282
+ "epoch": 1.7788461538461537,
283
+ "grad_norm": 9.193824768066406,
284
+ "learning_rate": 2.2617987533392697e-05,
285
+ "loss": 1.2465,
286
+ "step": 740
287
+ },
288
+ {
289
+ "epoch": 1.8269230769230769,
290
+ "grad_norm": 8.696285247802734,
291
+ "learning_rate": 2.1727515583259128e-05,
292
+ "loss": 1.1355,
293
+ "step": 760
294
+ },
295
+ {
296
+ "epoch": 1.875,
297
+ "grad_norm": 11.617859840393066,
298
+ "learning_rate": 2.083704363312556e-05,
299
+ "loss": 1.0957,
300
+ "step": 780
301
+ },
302
+ {
303
+ "epoch": 1.9230769230769231,
304
+ "grad_norm": 8.226522445678711,
305
+ "learning_rate": 1.9946571682991987e-05,
306
+ "loss": 1.1555,
307
+ "step": 800
308
+ },
309
+ {
310
+ "epoch": 1.9711538461538463,
311
+ "grad_norm": 8.735304832458496,
312
+ "learning_rate": 1.9056099732858414e-05,
313
+ "loss": 0.9817,
314
+ "step": 820
315
+ },
316
+ {
317
+ "epoch": 2.0,
318
+ "eval_accuracy": 0.5709134615384616,
319
+ "eval_f1_macro": 0.5526372725386915,
320
+ "eval_f1_micro": 0.5709134615384616,
321
+ "eval_f1_weighted": 0.5547700852360117,
322
+ "eval_loss": 1.1667430400848389,
323
+ "eval_precision_macro": 0.6115987390351798,
324
+ "eval_precision_micro": 0.5709134615384616,
325
+ "eval_precision_weighted": 0.6030497639852268,
326
+ "eval_recall_macro": 0.5580461856746055,
327
+ "eval_recall_micro": 0.5709134615384616,
328
+ "eval_recall_weighted": 0.5709134615384616,
329
+ "eval_runtime": 192.9893,
330
+ "eval_samples_per_second": 4.311,
331
+ "eval_steps_per_second": 0.269,
332
+ "step": 832
333
+ },
334
+ {
335
+ "epoch": 2.019230769230769,
336
+ "grad_norm": 9.844583511352539,
337
+ "learning_rate": 1.8165627782724845e-05,
338
+ "loss": 1.2267,
339
+ "step": 840
340
+ },
341
+ {
342
+ "epoch": 2.0673076923076925,
343
+ "grad_norm": 8.707366943359375,
344
+ "learning_rate": 1.7275155832591277e-05,
345
+ "loss": 1.027,
346
+ "step": 860
347
+ },
348
+ {
349
+ "epoch": 2.1153846153846154,
350
+ "grad_norm": 9.87036418914795,
351
+ "learning_rate": 1.63846838824577e-05,
352
+ "loss": 0.9735,
353
+ "step": 880
354
+ },
355
+ {
356
+ "epoch": 2.1634615384615383,
357
+ "grad_norm": 12.08313274383545,
358
+ "learning_rate": 1.5494211932324132e-05,
359
+ "loss": 1.0652,
360
+ "step": 900
361
+ },
362
+ {
363
+ "epoch": 2.2115384615384617,
364
+ "grad_norm": 14.892265319824219,
365
+ "learning_rate": 1.4603739982190561e-05,
366
+ "loss": 1.0136,
367
+ "step": 920
368
+ },
369
+ {
370
+ "epoch": 2.2596153846153846,
371
+ "grad_norm": 9.868454933166504,
372
+ "learning_rate": 1.3713268032056992e-05,
373
+ "loss": 1.0157,
374
+ "step": 940
375
+ },
376
+ {
377
+ "epoch": 2.3076923076923075,
378
+ "grad_norm": 12.881400108337402,
379
+ "learning_rate": 1.2822796081923418e-05,
380
+ "loss": 0.9707,
381
+ "step": 960
382
+ },
383
+ {
384
+ "epoch": 2.355769230769231,
385
+ "grad_norm": 13.381880760192871,
386
+ "learning_rate": 1.193232413178985e-05,
387
+ "loss": 0.9967,
388
+ "step": 980
389
+ },
390
+ {
391
+ "epoch": 2.4038461538461537,
392
+ "grad_norm": 16.189842224121094,
393
+ "learning_rate": 1.1041852181656279e-05,
394
+ "loss": 0.96,
395
+ "step": 1000
396
+ },
397
+ {
398
+ "epoch": 2.451923076923077,
399
+ "grad_norm": 8.050971984863281,
400
+ "learning_rate": 1.0151380231522706e-05,
401
+ "loss": 1.0216,
402
+ "step": 1020
403
+ },
404
+ {
405
+ "epoch": 2.5,
406
+ "grad_norm": 8.997209548950195,
407
+ "learning_rate": 9.260908281389138e-06,
408
+ "loss": 1.0242,
409
+ "step": 1040
410
+ },
411
+ {
412
+ "epoch": 2.5480769230769234,
413
+ "grad_norm": 9.797513961791992,
414
+ "learning_rate": 8.370436331255565e-06,
415
+ "loss": 0.9184,
416
+ "step": 1060
417
+ },
418
+ {
419
+ "epoch": 2.5961538461538463,
420
+ "grad_norm": 11.301565170288086,
421
+ "learning_rate": 7.4799643811219954e-06,
422
+ "loss": 0.9896,
423
+ "step": 1080
424
+ },
425
+ {
426
+ "epoch": 2.644230769230769,
427
+ "grad_norm": 7.524016380310059,
428
+ "learning_rate": 6.589492430988424e-06,
429
+ "loss": 0.9413,
430
+ "step": 1100
431
+ },
432
+ {
433
+ "epoch": 2.6923076923076925,
434
+ "grad_norm": 11.047348976135254,
435
+ "learning_rate": 5.699020480854853e-06,
436
+ "loss": 0.9651,
437
+ "step": 1120
438
+ },
439
+ {
440
+ "epoch": 2.7403846153846154,
441
+ "grad_norm": 16.3375301361084,
442
+ "learning_rate": 4.808548530721283e-06,
443
+ "loss": 0.945,
444
+ "step": 1140
445
+ },
446
+ {
447
+ "epoch": 2.7884615384615383,
448
+ "grad_norm": 11.701908111572266,
449
+ "learning_rate": 3.918076580587711e-06,
450
+ "loss": 1.0429,
451
+ "step": 1160
452
+ },
453
+ {
454
+ "epoch": 2.8365384615384617,
455
+ "grad_norm": 15.336776733398438,
456
+ "learning_rate": 3.0276046304541406e-06,
457
+ "loss": 0.8851,
458
+ "step": 1180
459
+ },
460
+ {
461
+ "epoch": 2.8846153846153846,
462
+ "grad_norm": 12.694565773010254,
463
+ "learning_rate": 2.13713268032057e-06,
464
+ "loss": 0.9671,
465
+ "step": 1200
466
+ },
467
+ {
468
+ "epoch": 2.9326923076923075,
469
+ "grad_norm": 8.017022132873535,
470
+ "learning_rate": 1.2466607301869992e-06,
471
+ "loss": 0.9224,
472
+ "step": 1220
473
+ },
474
+ {
475
+ "epoch": 2.980769230769231,
476
+ "grad_norm": 8.045291900634766,
477
+ "learning_rate": 3.5618878005342833e-07,
478
+ "loss": 0.8915,
479
+ "step": 1240
480
+ },
481
+ {
482
+ "epoch": 3.0,
483
+ "eval_accuracy": 0.6706730769230769,
484
+ "eval_f1_macro": 0.6658494548344828,
485
+ "eval_f1_micro": 0.6706730769230769,
486
+ "eval_f1_weighted": 0.6675736368483096,
487
+ "eval_loss": 0.9738104939460754,
488
+ "eval_precision_macro": 0.6694452026078725,
489
+ "eval_precision_micro": 0.6706730769230769,
490
+ "eval_precision_weighted": 0.6700176765328316,
491
+ "eval_recall_macro": 0.667714178467355,
492
+ "eval_recall_micro": 0.6706730769230769,
493
+ "eval_recall_weighted": 0.6706730769230769,
494
+ "eval_runtime": 136.1128,
495
+ "eval_samples_per_second": 6.113,
496
+ "eval_steps_per_second": 0.382,
497
+ "step": 1248
498
+ }
499
+ ],
500
+ "logging_steps": 20,
501
+ "max_steps": 1248,
502
+ "num_input_tokens_seen": 0,
503
+ "num_train_epochs": 3,
504
+ "save_steps": 500,
505
+ "stateful_callbacks": {
506
+ "EarlyStoppingCallback": {
507
+ "args": {
508
+ "early_stopping_patience": 5,
509
+ "early_stopping_threshold": 0.01
510
+ },
511
+ "attributes": {
512
+ "early_stopping_patience_counter": 0
513
+ }
514
+ },
515
+ "TrainerControl": {
516
+ "args": {
517
+ "should_epoch_stop": false,
518
+ "should_evaluate": false,
519
+ "should_log": false,
520
+ "should_save": true,
521
+ "should_training_stop": true
522
+ },
523
+ "attributes": {}
524
+ }
525
+ },
526
+ "total_flos": 656563229079552.0,
527
+ "train_batch_size": 8,
528
+ "trial_name": null,
529
+ "trial_params": null
530
+ }
checkpoint-1248/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cac7e8ad270e13f9e93b819288400bfa11f2bcdc7b8516a93d582a19e4cfd8b
3
+ size 5368
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "_num_labels": 8,
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": "\u53ad\u60e1\u8a9e\u8abf",
15
+ "1": "\u5e73\u6de1\u8a9e\u6c23",
16
+ "2": "\u60b2\u50b7\u8a9e\u8abf",
17
+ "3": "\u61a4\u6012\u8a9e\u8abf",
18
+ "4": "\u7591\u554f\u8a9e\u8abf",
19
+ "5": "\u958b\u5fc3\u8a9e\u8abf",
20
+ "6": "\u95dc\u5207\u8a9e\u8abf",
21
+ "7": "\u9a5a\u5947\u8a9e\u8abf"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "\u53ad\u60e1\u8a9e\u8abf": 0,
27
+ "\u5e73\u6de1\u8a9e\u6c23": 1,
28
+ "\u60b2\u50b7\u8a9e\u8abf": 2,
29
+ "\u61a4\u6012\u8a9e\u8abf": 3,
30
+ "\u7591\u554f\u8a9e\u8abf": 4,
31
+ "\u958b\u5fc3\u8a9e\u8abf": 5,
32
+ "\u95dc\u5207\u8a9e\u8abf": 6,
33
+ "\u9a5a\u5947\u8a9e\u8abf": 7
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "problem_type": "single_label_classification",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a60e8f2aab006de9accdf878f2b1055294b2866acd92f007341f08f067a5655
3
+ size 437977104
runs/Feb14_08-42-57_r-cyying-myyuledemo2-eg6jdm08-348d7-rprn9/events.out.tfevents.1739522579.r-cyying-myyuledemo2-eg6jdm08-348d7-rprn9.370.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e166479ea8e7f3c87819b7fab9d335b58144b4d224bbce6ad9004ad9d3d7f74
3
- size 19813
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:710499f78032400ee097d17c1d3ba687aed2c3ee042c7282451dbe2337d66e47
3
+ size 21633
runs/Feb14_08-42-57_r-cyying-myyuledemo2-eg6jdm08-348d7-rprn9/events.out.tfevents.1739530469.r-cyying-myyuledemo2-eg6jdm08-348d7-rprn9.370.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07157da05f11f95e1eaea5c185b659e3fd7c4434764c1eff58091e6b73f0db70
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
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": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cac7e8ad270e13f9e93b819288400bfa11f2bcdc7b8516a93d582a19e4cfd8b
3
+ size 5368
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-e3who-rl7wb/autotrain-data",
3
+ "model": "google-bert/bert-base-uncased",
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-e3who-rl7wb",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "cyying",
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