trentmkelly commited on
Commit
847177f
·
verified ·
1 Parent(s): 6e0f5fb

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ library_name: transformers
4
+ tags:
5
+ - autotrain
6
+ - text-classification
7
+ base_model: thenlper/gte-base
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: 0.02063986472785473
18
+
19
+ f1: 0.9955801104972376
20
+
21
+ precision: 0.9977851605758582
22
+
23
+ recall: 0.9933847850055126
24
+
25
+ auc: 0.9997304018220008
26
+
27
+ accuracy: 0.9939301972685888
checkpoint-1110/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "thenlper/gte-base",
3
+ "_num_labels": 2,
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": "BAD_USER",
15
+ "1": "GOOD_USER"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "BAD_USER": 0,
21
+ "GOOD_USER": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.48.0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-1110/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e64e2836cc8a08fc5b6840908172fc06359a62ad2c75e712845f8edfd88c8c9
3
+ size 437958648
checkpoint-1110/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa8eb590b9a8ad12815c6657124f1c99592efa7fa48f12bc6ef779129317958
3
+ size 876038394
checkpoint-1110/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0131420b5e52f37d69e9b754b7e289f39b40282624765ba4fe9c287f64a4f7
3
+ size 14244
checkpoint-1110/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1541752f301edb197fbd68dc05deb34840a54339fe8909ffa2b783a0db149eac
3
+ size 1064
checkpoint-1110/trainer_state.json ADDED
@@ -0,0 +1,538 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.02063986472785473,
3
+ "best_model_checkpoint": "autotrain-roblox-14-w-social-data/checkpoint-1110",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1110,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.014414414414414415,
13
+ "grad_norm": 1.748003602027893,
14
+ "learning_rate": 2.4024024024024026e-06,
15
+ "loss": 0.7862,
16
+ "step": 16
17
+ },
18
+ {
19
+ "epoch": 0.02882882882882883,
20
+ "grad_norm": 4.580026149749756,
21
+ "learning_rate": 4.804804804804805e-06,
22
+ "loss": 0.7611,
23
+ "step": 32
24
+ },
25
+ {
26
+ "epoch": 0.043243243243243246,
27
+ "grad_norm": 3.4808859825134277,
28
+ "learning_rate": 7.207207207207208e-06,
29
+ "loss": 0.6723,
30
+ "step": 48
31
+ },
32
+ {
33
+ "epoch": 0.05765765765765766,
34
+ "grad_norm": 6.322235584259033,
35
+ "learning_rate": 9.60960960960961e-06,
36
+ "loss": 0.5622,
37
+ "step": 64
38
+ },
39
+ {
40
+ "epoch": 0.07207207207207207,
41
+ "grad_norm": 3.7732388973236084,
42
+ "learning_rate": 1.2012012012012012e-05,
43
+ "loss": 0.3153,
44
+ "step": 80
45
+ },
46
+ {
47
+ "epoch": 0.08648648648648649,
48
+ "grad_norm": 6.7101569175720215,
49
+ "learning_rate": 1.4414414414414416e-05,
50
+ "loss": 0.1514,
51
+ "step": 96
52
+ },
53
+ {
54
+ "epoch": 0.1009009009009009,
55
+ "grad_norm": 0.47935283184051514,
56
+ "learning_rate": 1.6816816816816817e-05,
57
+ "loss": 0.0532,
58
+ "step": 112
59
+ },
60
+ {
61
+ "epoch": 0.11531531531531532,
62
+ "grad_norm": 0.6788657307624817,
63
+ "learning_rate": 1.906906906906907e-05,
64
+ "loss": 0.0379,
65
+ "step": 128
66
+ },
67
+ {
68
+ "epoch": 0.12972972972972974,
69
+ "grad_norm": 0.12879076600074768,
70
+ "learning_rate": 2.147147147147147e-05,
71
+ "loss": 0.124,
72
+ "step": 144
73
+ },
74
+ {
75
+ "epoch": 0.14414414414414414,
76
+ "grad_norm": 1.0692640542984009,
77
+ "learning_rate": 2.3873873873873874e-05,
78
+ "loss": 0.0745,
79
+ "step": 160
80
+ },
81
+ {
82
+ "epoch": 0.15855855855855855,
83
+ "grad_norm": 0.15514345467090607,
84
+ "learning_rate": 2.6276276276276278e-05,
85
+ "loss": 0.0523,
86
+ "step": 176
87
+ },
88
+ {
89
+ "epoch": 0.17297297297297298,
90
+ "grad_norm": 6.552980422973633,
91
+ "learning_rate": 2.8678678678678678e-05,
92
+ "loss": 0.077,
93
+ "step": 192
94
+ },
95
+ {
96
+ "epoch": 0.1873873873873874,
97
+ "grad_norm": 2.865363121032715,
98
+ "learning_rate": 3.108108108108108e-05,
99
+ "loss": 0.0291,
100
+ "step": 208
101
+ },
102
+ {
103
+ "epoch": 0.2018018018018018,
104
+ "grad_norm": 0.10969195514917374,
105
+ "learning_rate": 3.3483483483483485e-05,
106
+ "loss": 0.051,
107
+ "step": 224
108
+ },
109
+ {
110
+ "epoch": 0.21621621621621623,
111
+ "grad_norm": 0.16326627135276794,
112
+ "learning_rate": 3.588588588588589e-05,
113
+ "loss": 0.0775,
114
+ "step": 240
115
+ },
116
+ {
117
+ "epoch": 0.23063063063063063,
118
+ "grad_norm": 0.6071167588233948,
119
+ "learning_rate": 3.8288288288288285e-05,
120
+ "loss": 0.0314,
121
+ "step": 256
122
+ },
123
+ {
124
+ "epoch": 0.24504504504504504,
125
+ "grad_norm": 0.09915253520011902,
126
+ "learning_rate": 4.069069069069069e-05,
127
+ "loss": 0.1501,
128
+ "step": 272
129
+ },
130
+ {
131
+ "epoch": 0.2594594594594595,
132
+ "grad_norm": 0.11047788709402084,
133
+ "learning_rate": 4.30930930930931e-05,
134
+ "loss": 0.081,
135
+ "step": 288
136
+ },
137
+ {
138
+ "epoch": 0.27387387387387385,
139
+ "grad_norm": 1.869780421257019,
140
+ "learning_rate": 4.54954954954955e-05,
141
+ "loss": 0.0638,
142
+ "step": 304
143
+ },
144
+ {
145
+ "epoch": 0.2882882882882883,
146
+ "grad_norm": Infinity,
147
+ "learning_rate": 4.774774774774775e-05,
148
+ "loss": 0.0493,
149
+ "step": 320
150
+ },
151
+ {
152
+ "epoch": 0.3027027027027027,
153
+ "grad_norm": 1.0683149099349976,
154
+ "learning_rate": 4.998331664998332e-05,
155
+ "loss": 0.0897,
156
+ "step": 336
157
+ },
158
+ {
159
+ "epoch": 0.3171171171171171,
160
+ "grad_norm": 0.16674262285232544,
161
+ "learning_rate": 4.9716383049716386e-05,
162
+ "loss": 0.0699,
163
+ "step": 352
164
+ },
165
+ {
166
+ "epoch": 0.33153153153153153,
167
+ "grad_norm": 3.5534563064575195,
168
+ "learning_rate": 4.944944944944945e-05,
169
+ "loss": 0.0077,
170
+ "step": 368
171
+ },
172
+ {
173
+ "epoch": 0.34594594594594597,
174
+ "grad_norm": 0.1930895298719406,
175
+ "learning_rate": 4.918251584918252e-05,
176
+ "loss": 0.1282,
177
+ "step": 384
178
+ },
179
+ {
180
+ "epoch": 0.36036036036036034,
181
+ "grad_norm": 0.3207535147666931,
182
+ "learning_rate": 4.891558224891559e-05,
183
+ "loss": 0.0498,
184
+ "step": 400
185
+ },
186
+ {
187
+ "epoch": 0.3747747747747748,
188
+ "grad_norm": 8.772392272949219,
189
+ "learning_rate": 4.8648648648648654e-05,
190
+ "loss": 0.095,
191
+ "step": 416
192
+ },
193
+ {
194
+ "epoch": 0.3891891891891892,
195
+ "grad_norm": 0.27904969453811646,
196
+ "learning_rate": 4.8381715048381715e-05,
197
+ "loss": 0.0838,
198
+ "step": 432
199
+ },
200
+ {
201
+ "epoch": 0.4036036036036036,
202
+ "grad_norm": 0.10133874416351318,
203
+ "learning_rate": 4.811478144811478e-05,
204
+ "loss": 0.0305,
205
+ "step": 448
206
+ },
207
+ {
208
+ "epoch": 0.418018018018018,
209
+ "grad_norm": 0.04309872165322304,
210
+ "learning_rate": 4.784784784784785e-05,
211
+ "loss": 0.0014,
212
+ "step": 464
213
+ },
214
+ {
215
+ "epoch": 0.43243243243243246,
216
+ "grad_norm": 0.037388645112514496,
217
+ "learning_rate": 4.7580914247580916e-05,
218
+ "loss": 0.0609,
219
+ "step": 480
220
+ },
221
+ {
222
+ "epoch": 0.44684684684684683,
223
+ "grad_norm": 0.02931380271911621,
224
+ "learning_rate": 4.7330663997330666e-05,
225
+ "loss": 0.0413,
226
+ "step": 496
227
+ },
228
+ {
229
+ "epoch": 0.46126126126126127,
230
+ "grad_norm": 0.026952797546982765,
231
+ "learning_rate": 4.706373039706373e-05,
232
+ "loss": 0.0325,
233
+ "step": 512
234
+ },
235
+ {
236
+ "epoch": 0.4756756756756757,
237
+ "grad_norm": 0.035261645913124084,
238
+ "learning_rate": 4.67967967967968e-05,
239
+ "loss": 0.0461,
240
+ "step": 528
241
+ },
242
+ {
243
+ "epoch": 0.4900900900900901,
244
+ "grad_norm": 0.04663768783211708,
245
+ "learning_rate": 4.652986319652987e-05,
246
+ "loss": 0.0623,
247
+ "step": 544
248
+ },
249
+ {
250
+ "epoch": 0.5045045045045045,
251
+ "grad_norm": 0.1027512475848198,
252
+ "learning_rate": 4.6262929596262934e-05,
253
+ "loss": 0.0173,
254
+ "step": 560
255
+ },
256
+ {
257
+ "epoch": 0.518918918918919,
258
+ "grad_norm": 8.449505805969238,
259
+ "learning_rate": 4.5995995995996e-05,
260
+ "loss": 0.0682,
261
+ "step": 576
262
+ },
263
+ {
264
+ "epoch": 0.5333333333333333,
265
+ "grad_norm": 0.04210463538765907,
266
+ "learning_rate": 4.572906239572907e-05,
267
+ "loss": 0.0179,
268
+ "step": 592
269
+ },
270
+ {
271
+ "epoch": 0.5477477477477477,
272
+ "grad_norm": 0.029757114127278328,
273
+ "learning_rate": 4.5462128795462135e-05,
274
+ "loss": 0.0013,
275
+ "step": 608
276
+ },
277
+ {
278
+ "epoch": 0.5621621621621622,
279
+ "grad_norm": 0.08329767733812332,
280
+ "learning_rate": 4.5195195195195196e-05,
281
+ "loss": 0.0479,
282
+ "step": 624
283
+ },
284
+ {
285
+ "epoch": 0.5765765765765766,
286
+ "grad_norm": 4.216843128204346,
287
+ "learning_rate": 4.492826159492826e-05,
288
+ "loss": 0.0498,
289
+ "step": 640
290
+ },
291
+ {
292
+ "epoch": 0.590990990990991,
293
+ "grad_norm": 3.615675687789917,
294
+ "learning_rate": 4.466132799466133e-05,
295
+ "loss": 0.0692,
296
+ "step": 656
297
+ },
298
+ {
299
+ "epoch": 0.6054054054054054,
300
+ "grad_norm": 0.05522392317652702,
301
+ "learning_rate": 4.43943943943944e-05,
302
+ "loss": 0.0234,
303
+ "step": 672
304
+ },
305
+ {
306
+ "epoch": 0.6198198198198198,
307
+ "grad_norm": 0.0599186047911644,
308
+ "learning_rate": 4.4127460794127464e-05,
309
+ "loss": 0.0852,
310
+ "step": 688
311
+ },
312
+ {
313
+ "epoch": 0.6342342342342342,
314
+ "grad_norm": 0.0658278837800026,
315
+ "learning_rate": 4.386052719386053e-05,
316
+ "loss": 0.0218,
317
+ "step": 704
318
+ },
319
+ {
320
+ "epoch": 0.6486486486486487,
321
+ "grad_norm": 0.9090924859046936,
322
+ "learning_rate": 4.35935935935936e-05,
323
+ "loss": 0.0213,
324
+ "step": 720
325
+ },
326
+ {
327
+ "epoch": 0.6630630630630631,
328
+ "grad_norm": 3.09871244430542,
329
+ "learning_rate": 4.3326659993326665e-05,
330
+ "loss": 0.0559,
331
+ "step": 736
332
+ },
333
+ {
334
+ "epoch": 0.6774774774774774,
335
+ "grad_norm": 0.04464685916900635,
336
+ "learning_rate": 4.305972639305973e-05,
337
+ "loss": 0.0291,
338
+ "step": 752
339
+ },
340
+ {
341
+ "epoch": 0.6918918918918919,
342
+ "grad_norm": 2.7168843746185303,
343
+ "learning_rate": 4.27927927927928e-05,
344
+ "loss": 0.055,
345
+ "step": 768
346
+ },
347
+ {
348
+ "epoch": 0.7063063063063063,
349
+ "grad_norm": 0.10941269993782043,
350
+ "learning_rate": 4.2525859192525866e-05,
351
+ "loss": 0.0022,
352
+ "step": 784
353
+ },
354
+ {
355
+ "epoch": 0.7207207207207207,
356
+ "grad_norm": 0.040725983679294586,
357
+ "learning_rate": 4.225892559225893e-05,
358
+ "loss": 0.0175,
359
+ "step": 800
360
+ },
361
+ {
362
+ "epoch": 0.7351351351351352,
363
+ "grad_norm": 0.024307256564497948,
364
+ "learning_rate": 4.199199199199199e-05,
365
+ "loss": 0.0095,
366
+ "step": 816
367
+ },
368
+ {
369
+ "epoch": 0.7495495495495496,
370
+ "grad_norm": 0.034840308129787445,
371
+ "learning_rate": 4.172505839172506e-05,
372
+ "loss": 0.069,
373
+ "step": 832
374
+ },
375
+ {
376
+ "epoch": 0.7639639639639639,
377
+ "grad_norm": 0.027919117361307144,
378
+ "learning_rate": 4.145812479145813e-05,
379
+ "loss": 0.0035,
380
+ "step": 848
381
+ },
382
+ {
383
+ "epoch": 0.7783783783783784,
384
+ "grad_norm": 2.424572706222534,
385
+ "learning_rate": 4.1191191191191194e-05,
386
+ "loss": 0.0963,
387
+ "step": 864
388
+ },
389
+ {
390
+ "epoch": 0.7927927927927928,
391
+ "grad_norm": 0.040964461863040924,
392
+ "learning_rate": 4.092425759092426e-05,
393
+ "loss": 0.0197,
394
+ "step": 880
395
+ },
396
+ {
397
+ "epoch": 0.8072072072072072,
398
+ "grad_norm": 0.017049992457032204,
399
+ "learning_rate": 4.065732399065733e-05,
400
+ "loss": 0.0015,
401
+ "step": 896
402
+ },
403
+ {
404
+ "epoch": 0.8216216216216217,
405
+ "grad_norm": 0.017698146402835846,
406
+ "learning_rate": 4.0390390390390395e-05,
407
+ "loss": 0.0358,
408
+ "step": 912
409
+ },
410
+ {
411
+ "epoch": 0.836036036036036,
412
+ "grad_norm": 0.13524557650089264,
413
+ "learning_rate": 4.012345679012346e-05,
414
+ "loss": 0.0322,
415
+ "step": 928
416
+ },
417
+ {
418
+ "epoch": 0.8504504504504504,
419
+ "grad_norm": 0.0850856751203537,
420
+ "learning_rate": 3.985652318985652e-05,
421
+ "loss": 0.0587,
422
+ "step": 944
423
+ },
424
+ {
425
+ "epoch": 0.8648648648648649,
426
+ "grad_norm": 1.8711559772491455,
427
+ "learning_rate": 3.958958958958959e-05,
428
+ "loss": 0.0221,
429
+ "step": 960
430
+ },
431
+ {
432
+ "epoch": 0.8792792792792793,
433
+ "grad_norm": 0.015208806842565536,
434
+ "learning_rate": 3.932265598932266e-05,
435
+ "loss": 0.0092,
436
+ "step": 976
437
+ },
438
+ {
439
+ "epoch": 0.8936936936936937,
440
+ "grad_norm": 0.043549440801143646,
441
+ "learning_rate": 3.9055722389055724e-05,
442
+ "loss": 0.0631,
443
+ "step": 992
444
+ },
445
+ {
446
+ "epoch": 0.9081081081081082,
447
+ "grad_norm": 0.04594253748655319,
448
+ "learning_rate": 3.878878878878879e-05,
449
+ "loss": 0.0198,
450
+ "step": 1008
451
+ },
452
+ {
453
+ "epoch": 0.9225225225225225,
454
+ "grad_norm": 14.08329963684082,
455
+ "learning_rate": 3.852185518852186e-05,
456
+ "loss": 0.06,
457
+ "step": 1024
458
+ },
459
+ {
460
+ "epoch": 0.9369369369369369,
461
+ "grad_norm": 0.014096206985414028,
462
+ "learning_rate": 3.8254921588254925e-05,
463
+ "loss": 0.0204,
464
+ "step": 1040
465
+ },
466
+ {
467
+ "epoch": 0.9513513513513514,
468
+ "grad_norm": 22.616973876953125,
469
+ "learning_rate": 3.7987987987987985e-05,
470
+ "loss": 0.0582,
471
+ "step": 1056
472
+ },
473
+ {
474
+ "epoch": 0.9657657657657658,
475
+ "grad_norm": 0.3841395974159241,
476
+ "learning_rate": 3.772105438772105e-05,
477
+ "loss": 0.0019,
478
+ "step": 1072
479
+ },
480
+ {
481
+ "epoch": 0.9801801801801802,
482
+ "grad_norm": 0.03729676827788353,
483
+ "learning_rate": 3.745412078745412e-05,
484
+ "loss": 0.001,
485
+ "step": 1088
486
+ },
487
+ {
488
+ "epoch": 0.9945945945945946,
489
+ "grad_norm": 0.025941751897335052,
490
+ "learning_rate": 3.7187187187187186e-05,
491
+ "loss": 0.0282,
492
+ "step": 1104
493
+ },
494
+ {
495
+ "epoch": 1.0,
496
+ "eval_accuracy": 0.9939301972685888,
497
+ "eval_auc": 0.9997304018220008,
498
+ "eval_f1": 0.9955801104972376,
499
+ "eval_loss": 0.02063986472785473,
500
+ "eval_precision": 0.9977851605758582,
501
+ "eval_recall": 0.9933847850055126,
502
+ "eval_runtime": 4.7719,
503
+ "eval_samples_per_second": 276.202,
504
+ "eval_steps_per_second": 8.802,
505
+ "step": 1110
506
+ }
507
+ ],
508
+ "logging_steps": 16,
509
+ "max_steps": 3330,
510
+ "num_input_tokens_seen": 0,
511
+ "num_train_epochs": 3,
512
+ "save_steps": 500,
513
+ "stateful_callbacks": {
514
+ "EarlyStoppingCallback": {
515
+ "args": {
516
+ "early_stopping_patience": 5,
517
+ "early_stopping_threshold": 0.01
518
+ },
519
+ "attributes": {
520
+ "early_stopping_patience_counter": 0
521
+ }
522
+ },
523
+ "TrainerControl": {
524
+ "args": {
525
+ "should_epoch_stop": false,
526
+ "should_evaluate": false,
527
+ "should_log": false,
528
+ "should_save": true,
529
+ "should_training_stop": false
530
+ },
531
+ "attributes": {}
532
+ }
533
+ },
534
+ "total_flos": 2335768393958400.0,
535
+ "train_batch_size": 16,
536
+ "trial_name": null,
537
+ "trial_params": null
538
+ }
checkpoint-1110/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e312d4de3db6b614a6893b34d4d8dd3bfbc53a82e69bcf95d108a927694cd2d
3
+ size 5432
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "thenlper/gte-base",
3
+ "_num_labels": 2,
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": "BAD_USER",
15
+ "1": "GOOD_USER"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "BAD_USER": 0,
21
+ "GOOD_USER": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.48.0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e64e2836cc8a08fc5b6840908172fc06359a62ad2c75e712845f8edfd88c8c9
3
+ size 437958648
runs/May24_20-36-18_r-trentmkelly-autotrain-advanced-yq4u9ix4-1f629-5aao4/events.out.tfevents.1748118980.r-trentmkelly-autotrain-advanced-yq4u9ix4-1f629-5aao4.75.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2807ce7bdb4e53adba1e23b8750cfd3a6e184960c1e533b0d477c16ea0855896
3
- size 44277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18a724dd5d30773d27a12d8fe0b422b58be38e456b38e862ac0f180f648ebfa8
3
+ size 51058
runs/May24_20-36-18_r-trentmkelly-autotrain-advanced-yq4u9ix4-1f629-5aao4/events.out.tfevents.1748119699.r-trentmkelly-autotrain-advanced-yq4u9ix4-1f629-5aao4.75.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae3546587d7d93876d79cd00a8c2f197fe71ab15382b017432674d34b3bd602
3
+ size 607
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "max_length": 128,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "[PAD]",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "[UNK]"
63
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e312d4de3db6b614a6893b34d4d8dd3bfbc53a82e69bcf95d108a927694cd2d
3
+ size 5432
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-roblox-14-w-social-data/autotrain-data",
3
+ "model": "thenlper/gte-base",
4
+ "lr": 5e-05,
5
+ "epochs": 3,
6
+ "max_seq_length": 256,
7
+ "batch_size": 16,
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-roblox-14-w-social-data",
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": "trentmkelly",
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