aimanfadillah commited on
Commit
6bc0dd1
·
verified ·
1 Parent(s): f7b36c9

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: distilbert/distilbert-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: 3.0925960540771484
18
+
19
+ f1_macro: 0.2675876194485524
20
+
21
+ f1_micro: 0.5051039697542533
22
+
23
+ f1_weighted: 0.4266553262031796
24
+
25
+ precision_macro: 0.2522810784129609
26
+
27
+ precision_micro: 0.5051039697542533
28
+
29
+ precision_weighted: 0.40593727556638787
30
+
31
+ recall_macro: 0.33
32
+
33
+ recall_micro: 0.5051039697542533
34
+
35
+ recall_weighted: 0.5051039697542533
36
+
37
+ accuracy: 0.5051039697542533
checkpoint-2648/config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2648/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58d18f01a94fd13c42e421849d96257e2bf141b3d8e2fd588a546c9b8353fbe6
3
+ size 271809860
checkpoint-2648/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a0a0837505425635015512c9c070ae035d093703072ef47dec9b21e42e54df
3
+ size 543678842
checkpoint-2648/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536d09f7e6108ee575831efd9e9d2ef1fd188a8a0079232a7eef716bd8298d8d
3
+ size 13990
checkpoint-2648/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da23c7e793638b7d9e4c42fff47432ea27bfd4db1688801de7b2f308465d5c7c
3
+ size 1064
checkpoint-2648/trainer_state.json ADDED
@@ -0,0 +1,849 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.0925960540771484,
3
+ "best_model_checkpoint": "matching-buyback/checkpoint-2648",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2648,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0377643504531722,
13
+ "grad_norm": 2.148848295211792,
14
+ "learning_rate": 4.716981132075472e-06,
15
+ "loss": 7.1736,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.0755287009063444,
20
+ "grad_norm": 1.9532533884048462,
21
+ "learning_rate": 9.433962264150944e-06,
22
+ "loss": 7.1696,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.11329305135951662,
27
+ "grad_norm": 1.8605287075042725,
28
+ "learning_rate": 1.4150943396226415e-05,
29
+ "loss": 7.1706,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.1510574018126888,
34
+ "grad_norm": 1.7690376043319702,
35
+ "learning_rate": 1.8867924528301888e-05,
36
+ "loss": 7.168,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.18882175226586104,
41
+ "grad_norm": 1.6989686489105225,
42
+ "learning_rate": 2.358490566037736e-05,
43
+ "loss": 7.1623,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.22658610271903323,
48
+ "grad_norm": 1.9419589042663574,
49
+ "learning_rate": 2.830188679245283e-05,
50
+ "loss": 7.1582,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.26435045317220546,
55
+ "grad_norm": 6.193149089813232,
56
+ "learning_rate": 3.30188679245283e-05,
57
+ "loss": 7.142,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.3021148036253776,
62
+ "grad_norm": 3.8507258892059326,
63
+ "learning_rate": 3.7735849056603776e-05,
64
+ "loss": 7.1296,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.33987915407854985,
69
+ "grad_norm": 3.860013246536255,
70
+ "learning_rate": 4.245283018867925e-05,
71
+ "loss": 7.129,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.3776435045317221,
76
+ "grad_norm": 3.5848217010498047,
77
+ "learning_rate": 4.716981132075472e-05,
78
+ "loss": 7.104,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.41540785498489424,
83
+ "grad_norm": 3.5513248443603516,
84
+ "learning_rate": 4.979018044481746e-05,
85
+ "loss": 7.0868,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.45317220543806647,
90
+ "grad_norm": 3.685840368270874,
91
+ "learning_rate": 4.9265631556861106e-05,
92
+ "loss": 6.9957,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.4909365558912387,
97
+ "grad_norm": 3.6940855979919434,
98
+ "learning_rate": 4.874108266890474e-05,
99
+ "loss": 6.9211,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.5287009063444109,
104
+ "grad_norm": 4.479358673095703,
105
+ "learning_rate": 4.8216533780948384e-05,
106
+ "loss": 6.8176,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.5664652567975831,
111
+ "grad_norm": 4.331283092498779,
112
+ "learning_rate": 4.769198489299203e-05,
113
+ "loss": 6.7406,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.6042296072507553,
118
+ "grad_norm": 4.426012992858887,
119
+ "learning_rate": 4.716743600503567e-05,
120
+ "loss": 6.6516,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.6419939577039275,
125
+ "grad_norm": 4.232052326202393,
126
+ "learning_rate": 4.664288711707932e-05,
127
+ "loss": 6.6214,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.6797583081570997,
132
+ "grad_norm": 5.0197601318359375,
133
+ "learning_rate": 4.6118338229122954e-05,
134
+ "loss": 6.4544,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.7175226586102719,
139
+ "grad_norm": 5.322621822357178,
140
+ "learning_rate": 4.5593789341166596e-05,
141
+ "loss": 6.4331,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.7552870090634441,
146
+ "grad_norm": 5.3774871826171875,
147
+ "learning_rate": 4.5069240453210245e-05,
148
+ "loss": 6.3182,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.7930513595166163,
153
+ "grad_norm": 5.22687292098999,
154
+ "learning_rate": 4.454469156525388e-05,
155
+ "loss": 6.2782,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.8308157099697885,
160
+ "grad_norm": 4.664173603057861,
161
+ "learning_rate": 4.402014267729753e-05,
162
+ "loss": 6.2099,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.8685800604229608,
167
+ "grad_norm": 5.771005153656006,
168
+ "learning_rate": 4.349559378934117e-05,
169
+ "loss": 6.1739,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.9063444108761329,
174
+ "grad_norm": 5.225096225738525,
175
+ "learning_rate": 4.297104490138481e-05,
176
+ "loss": 6.1653,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.9441087613293051,
181
+ "grad_norm": 5.635812282562256,
182
+ "learning_rate": 4.244649601342846e-05,
183
+ "loss": 6.0278,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.9818731117824774,
188
+ "grad_norm": 5.488772392272949,
189
+ "learning_rate": 4.192194712547209e-05,
190
+ "loss": 6.0308,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 1.0,
195
+ "eval_accuracy": 0.026465028355387523,
196
+ "eval_f1_macro": 0.0018394084225980786,
197
+ "eval_f1_micro": 0.026465028355387523,
198
+ "eval_f1_weighted": 0.002693831801885104,
199
+ "eval_loss": 5.7428083419799805,
200
+ "eval_precision_macro": 0.0011073227324794681,
201
+ "eval_precision_micro": 0.026465028355387523,
202
+ "eval_precision_weighted": 0.0015115244261337012,
203
+ "eval_recall_macro": 0.014671814671814672,
204
+ "eval_recall_micro": 0.026465028355387523,
205
+ "eval_recall_weighted": 0.026465028355387523,
206
+ "eval_runtime": 258.8851,
207
+ "eval_samples_per_second": 10.217,
208
+ "eval_steps_per_second": 0.321,
209
+ "step": 662
210
+ },
211
+ {
212
+ "epoch": 1.0196374622356494,
213
+ "grad_norm": 5.648388385772705,
214
+ "learning_rate": 4.139739823751574e-05,
215
+ "loss": 5.8178,
216
+ "step": 675
217
+ },
218
+ {
219
+ "epoch": 1.0574018126888218,
220
+ "grad_norm": 6.245723724365234,
221
+ "learning_rate": 4.0872849349559384e-05,
222
+ "loss": 5.6123,
223
+ "step": 700
224
+ },
225
+ {
226
+ "epoch": 1.095166163141994,
227
+ "grad_norm": 6.041352272033691,
228
+ "learning_rate": 4.034830046160302e-05,
229
+ "loss": 5.7037,
230
+ "step": 725
231
+ },
232
+ {
233
+ "epoch": 1.1329305135951662,
234
+ "grad_norm": 6.065165996551514,
235
+ "learning_rate": 3.982375157364667e-05,
236
+ "loss": 5.6632,
237
+ "step": 750
238
+ },
239
+ {
240
+ "epoch": 1.1706948640483383,
241
+ "grad_norm": 5.901498794555664,
242
+ "learning_rate": 3.9299202685690305e-05,
243
+ "loss": 5.6154,
244
+ "step": 775
245
+ },
246
+ {
247
+ "epoch": 1.2084592145015105,
248
+ "grad_norm": 6.365645885467529,
249
+ "learning_rate": 3.8774653797733954e-05,
250
+ "loss": 5.4768,
251
+ "step": 800
252
+ },
253
+ {
254
+ "epoch": 1.2462235649546827,
255
+ "grad_norm": 6.6829705238342285,
256
+ "learning_rate": 3.8250104909777596e-05,
257
+ "loss": 5.3382,
258
+ "step": 825
259
+ },
260
+ {
261
+ "epoch": 1.283987915407855,
262
+ "grad_norm": 5.9976019859313965,
263
+ "learning_rate": 3.772555602182123e-05,
264
+ "loss": 5.4,
265
+ "step": 850
266
+ },
267
+ {
268
+ "epoch": 1.3217522658610272,
269
+ "grad_norm": 6.049790859222412,
270
+ "learning_rate": 3.720100713386488e-05,
271
+ "loss": 5.3734,
272
+ "step": 875
273
+ },
274
+ {
275
+ "epoch": 1.3595166163141994,
276
+ "grad_norm": 7.126038074493408,
277
+ "learning_rate": 3.667645824590852e-05,
278
+ "loss": 5.2598,
279
+ "step": 900
280
+ },
281
+ {
282
+ "epoch": 1.3972809667673716,
283
+ "grad_norm": 6.60282564163208,
284
+ "learning_rate": 3.6151909357952166e-05,
285
+ "loss": 5.2374,
286
+ "step": 925
287
+ },
288
+ {
289
+ "epoch": 1.4350453172205437,
290
+ "grad_norm": 6.773179054260254,
291
+ "learning_rate": 3.562736046999581e-05,
292
+ "loss": 5.172,
293
+ "step": 950
294
+ },
295
+ {
296
+ "epoch": 1.4728096676737161,
297
+ "grad_norm": 6.833974361419678,
298
+ "learning_rate": 3.5102811582039444e-05,
299
+ "loss": 5.1996,
300
+ "step": 975
301
+ },
302
+ {
303
+ "epoch": 1.510574018126888,
304
+ "grad_norm": 6.419187068939209,
305
+ "learning_rate": 3.457826269408309e-05,
306
+ "loss": 5.1801,
307
+ "step": 1000
308
+ },
309
+ {
310
+ "epoch": 1.5483383685800605,
311
+ "grad_norm": 6.803603649139404,
312
+ "learning_rate": 3.405371380612673e-05,
313
+ "loss": 4.988,
314
+ "step": 1025
315
+ },
316
+ {
317
+ "epoch": 1.5861027190332326,
318
+ "grad_norm": 6.773290157318115,
319
+ "learning_rate": 3.352916491817038e-05,
320
+ "loss": 5.0186,
321
+ "step": 1050
322
+ },
323
+ {
324
+ "epoch": 1.6238670694864048,
325
+ "grad_norm": 6.730032920837402,
326
+ "learning_rate": 3.300461603021402e-05,
327
+ "loss": 5.0032,
328
+ "step": 1075
329
+ },
330
+ {
331
+ "epoch": 1.6616314199395772,
332
+ "grad_norm": 7.288454532623291,
333
+ "learning_rate": 3.2480067142257656e-05,
334
+ "loss": 4.908,
335
+ "step": 1100
336
+ },
337
+ {
338
+ "epoch": 1.6993957703927491,
339
+ "grad_norm": 6.888255596160889,
340
+ "learning_rate": 3.1955518254301305e-05,
341
+ "loss": 4.937,
342
+ "step": 1125
343
+ },
344
+ {
345
+ "epoch": 1.7371601208459215,
346
+ "grad_norm": 6.915685176849365,
347
+ "learning_rate": 3.143096936634494e-05,
348
+ "loss": 4.9246,
349
+ "step": 1150
350
+ },
351
+ {
352
+ "epoch": 1.7749244712990937,
353
+ "grad_norm": 6.667412757873535,
354
+ "learning_rate": 3.090642047838859e-05,
355
+ "loss": 4.8717,
356
+ "step": 1175
357
+ },
358
+ {
359
+ "epoch": 1.8126888217522659,
360
+ "grad_norm": 6.816399097442627,
361
+ "learning_rate": 3.0381871590432233e-05,
362
+ "loss": 4.9049,
363
+ "step": 1200
364
+ },
365
+ {
366
+ "epoch": 1.850453172205438,
367
+ "grad_norm": 7.150826930999756,
368
+ "learning_rate": 2.985732270247587e-05,
369
+ "loss": 4.705,
370
+ "step": 1225
371
+ },
372
+ {
373
+ "epoch": 1.8882175226586102,
374
+ "grad_norm": 7.209892272949219,
375
+ "learning_rate": 2.9332773814519514e-05,
376
+ "loss": 4.8234,
377
+ "step": 1250
378
+ },
379
+ {
380
+ "epoch": 1.9259818731117826,
381
+ "grad_norm": 7.008028507232666,
382
+ "learning_rate": 2.8808224926563153e-05,
383
+ "loss": 4.6716,
384
+ "step": 1275
385
+ },
386
+ {
387
+ "epoch": 1.9637462235649545,
388
+ "grad_norm": 7.195932865142822,
389
+ "learning_rate": 2.82836760386068e-05,
390
+ "loss": 4.6394,
391
+ "step": 1300
392
+ },
393
+ {
394
+ "epoch": 2.0,
395
+ "eval_accuracy": 0.21890359168241966,
396
+ "eval_f1_macro": 0.07847614280788937,
397
+ "eval_f1_micro": 0.21890359168241966,
398
+ "eval_f1_weighted": 0.14378778601568412,
399
+ "eval_loss": 4.332443714141846,
400
+ "eval_precision_macro": 0.07050179882195226,
401
+ "eval_precision_micro": 0.21890359168241966,
402
+ "eval_precision_weighted": 0.12910697824366127,
403
+ "eval_recall_macro": 0.12453024453024451,
404
+ "eval_recall_micro": 0.21890359168241966,
405
+ "eval_recall_weighted": 0.21890359168241966,
406
+ "eval_runtime": 274.1069,
407
+ "eval_samples_per_second": 9.65,
408
+ "eval_steps_per_second": 0.303,
409
+ "step": 1324
410
+ },
411
+ {
412
+ "epoch": 2.001510574018127,
413
+ "grad_norm": 7.194442272186279,
414
+ "learning_rate": 2.7759127150650445e-05,
415
+ "loss": 4.5155,
416
+ "step": 1325
417
+ },
418
+ {
419
+ "epoch": 2.039274924471299,
420
+ "grad_norm": 7.649657726287842,
421
+ "learning_rate": 2.7234578262694084e-05,
422
+ "loss": 4.3742,
423
+ "step": 1350
424
+ },
425
+ {
426
+ "epoch": 2.0770392749244713,
427
+ "grad_norm": 6.8479084968566895,
428
+ "learning_rate": 2.6710029374737726e-05,
429
+ "loss": 4.4017,
430
+ "step": 1375
431
+ },
432
+ {
433
+ "epoch": 2.1148036253776437,
434
+ "grad_norm": 7.72012186050415,
435
+ "learning_rate": 2.6185480486781372e-05,
436
+ "loss": 4.2114,
437
+ "step": 1400
438
+ },
439
+ {
440
+ "epoch": 2.1525679758308156,
441
+ "grad_norm": 7.429843425750732,
442
+ "learning_rate": 2.566093159882501e-05,
443
+ "loss": 4.3608,
444
+ "step": 1425
445
+ },
446
+ {
447
+ "epoch": 2.190332326283988,
448
+ "grad_norm": 7.590367794036865,
449
+ "learning_rate": 2.5136382710868657e-05,
450
+ "loss": 4.2724,
451
+ "step": 1450
452
+ },
453
+ {
454
+ "epoch": 2.22809667673716,
455
+ "grad_norm": 7.643247127532959,
456
+ "learning_rate": 2.46118338229123e-05,
457
+ "loss": 4.149,
458
+ "step": 1475
459
+ },
460
+ {
461
+ "epoch": 2.2658610271903323,
462
+ "grad_norm": 7.686148643493652,
463
+ "learning_rate": 2.4087284934955938e-05,
464
+ "loss": 4.1981,
465
+ "step": 1500
466
+ },
467
+ {
468
+ "epoch": 2.3036253776435047,
469
+ "grad_norm": 7.800241470336914,
470
+ "learning_rate": 2.356273604699958e-05,
471
+ "loss": 4.2175,
472
+ "step": 1525
473
+ },
474
+ {
475
+ "epoch": 2.3413897280966767,
476
+ "grad_norm": 7.715053558349609,
477
+ "learning_rate": 2.3038187159043223e-05,
478
+ "loss": 4.1977,
479
+ "step": 1550
480
+ },
481
+ {
482
+ "epoch": 2.379154078549849,
483
+ "grad_norm": 7.797581195831299,
484
+ "learning_rate": 2.251363827108687e-05,
485
+ "loss": 4.1727,
486
+ "step": 1575
487
+ },
488
+ {
489
+ "epoch": 2.416918429003021,
490
+ "grad_norm": 7.720523834228516,
491
+ "learning_rate": 2.198908938313051e-05,
492
+ "loss": 4.0437,
493
+ "step": 1600
494
+ },
495
+ {
496
+ "epoch": 2.4546827794561934,
497
+ "grad_norm": 7.72569465637207,
498
+ "learning_rate": 2.146454049517415e-05,
499
+ "loss": 4.0182,
500
+ "step": 1625
501
+ },
502
+ {
503
+ "epoch": 2.4924471299093653,
504
+ "grad_norm": 7.541537761688232,
505
+ "learning_rate": 2.0939991607217792e-05,
506
+ "loss": 4.0712,
507
+ "step": 1650
508
+ },
509
+ {
510
+ "epoch": 2.5302114803625377,
511
+ "grad_norm": 7.888173580169678,
512
+ "learning_rate": 2.0415442719261435e-05,
513
+ "loss": 3.9628,
514
+ "step": 1675
515
+ },
516
+ {
517
+ "epoch": 2.56797583081571,
518
+ "grad_norm": 7.701706886291504,
519
+ "learning_rate": 1.989089383130508e-05,
520
+ "loss": 3.9174,
521
+ "step": 1700
522
+ },
523
+ {
524
+ "epoch": 2.605740181268882,
525
+ "grad_norm": 7.674171447753906,
526
+ "learning_rate": 1.9366344943348723e-05,
527
+ "loss": 3.8891,
528
+ "step": 1725
529
+ },
530
+ {
531
+ "epoch": 2.6435045317220545,
532
+ "grad_norm": 7.812932014465332,
533
+ "learning_rate": 1.8841796055392362e-05,
534
+ "loss": 3.9667,
535
+ "step": 1750
536
+ },
537
+ {
538
+ "epoch": 2.6812688821752264,
539
+ "grad_norm": 8.138640403747559,
540
+ "learning_rate": 1.8317247167436005e-05,
541
+ "loss": 3.9761,
542
+ "step": 1775
543
+ },
544
+ {
545
+ "epoch": 2.719033232628399,
546
+ "grad_norm": 7.94352912902832,
547
+ "learning_rate": 1.7792698279479647e-05,
548
+ "loss": 3.8518,
549
+ "step": 1800
550
+ },
551
+ {
552
+ "epoch": 2.756797583081571,
553
+ "grad_norm": 7.7708539962768555,
554
+ "learning_rate": 1.7268149391523293e-05,
555
+ "loss": 3.6874,
556
+ "step": 1825
557
+ },
558
+ {
559
+ "epoch": 2.794561933534743,
560
+ "grad_norm": 8.06053638458252,
561
+ "learning_rate": 1.6743600503566935e-05,
562
+ "loss": 3.8025,
563
+ "step": 1850
564
+ },
565
+ {
566
+ "epoch": 2.8323262839879155,
567
+ "grad_norm": 7.878209590911865,
568
+ "learning_rate": 1.6219051615610574e-05,
569
+ "loss": 3.7442,
570
+ "step": 1875
571
+ },
572
+ {
573
+ "epoch": 2.8700906344410875,
574
+ "grad_norm": 8.10824203491211,
575
+ "learning_rate": 1.5694502727654217e-05,
576
+ "loss": 3.8247,
577
+ "step": 1900
578
+ },
579
+ {
580
+ "epoch": 2.90785498489426,
581
+ "grad_norm": 7.619449138641357,
582
+ "learning_rate": 1.5169953839697862e-05,
583
+ "loss": 3.6439,
584
+ "step": 1925
585
+ },
586
+ {
587
+ "epoch": 2.9456193353474323,
588
+ "grad_norm": 8.001503944396973,
589
+ "learning_rate": 1.4645404951741503e-05,
590
+ "loss": 3.6267,
591
+ "step": 1950
592
+ },
593
+ {
594
+ "epoch": 2.983383685800604,
595
+ "grad_norm": 7.938083648681641,
596
+ "learning_rate": 1.4120856063785145e-05,
597
+ "loss": 3.6283,
598
+ "step": 1975
599
+ },
600
+ {
601
+ "epoch": 3.0,
602
+ "eval_accuracy": 0.45255198487712667,
603
+ "eval_f1_macro": 0.22372025748723245,
604
+ "eval_f1_micro": 0.45255198487712667,
605
+ "eval_f1_weighted": 0.36915380230770156,
606
+ "eval_loss": 3.410895347595215,
607
+ "eval_precision_macro": 0.210819340352679,
608
+ "eval_precision_micro": 0.45255198487712667,
609
+ "eval_precision_weighted": 0.34998443503067106,
610
+ "eval_recall_macro": 0.28555984555984554,
611
+ "eval_recall_micro": 0.45255198487712667,
612
+ "eval_recall_weighted": 0.45255198487712667,
613
+ "eval_runtime": 240.6652,
614
+ "eval_samples_per_second": 10.99,
615
+ "eval_steps_per_second": 0.345,
616
+ "step": 1986
617
+ },
618
+ {
619
+ "epoch": 3.0211480362537766,
620
+ "grad_norm": 8.365966796875,
621
+ "learning_rate": 1.3596307175828788e-05,
622
+ "loss": 3.6007,
623
+ "step": 2000
624
+ },
625
+ {
626
+ "epoch": 3.0589123867069485,
627
+ "grad_norm": 8.145760536193848,
628
+ "learning_rate": 1.3071758287872429e-05,
629
+ "loss": 3.5455,
630
+ "step": 2025
631
+ },
632
+ {
633
+ "epoch": 3.096676737160121,
634
+ "grad_norm": 7.752460479736328,
635
+ "learning_rate": 1.2547209399916074e-05,
636
+ "loss": 3.3978,
637
+ "step": 2050
638
+ },
639
+ {
640
+ "epoch": 3.134441087613293,
641
+ "grad_norm": 8.035235404968262,
642
+ "learning_rate": 1.2022660511959715e-05,
643
+ "loss": 3.5076,
644
+ "step": 2075
645
+ },
646
+ {
647
+ "epoch": 3.1722054380664653,
648
+ "grad_norm": 8.423967361450195,
649
+ "learning_rate": 1.1498111624003358e-05,
650
+ "loss": 3.4326,
651
+ "step": 2100
652
+ },
653
+ {
654
+ "epoch": 3.2099697885196377,
655
+ "grad_norm": 8.095000267028809,
656
+ "learning_rate": 1.0973562736047e-05,
657
+ "loss": 3.4518,
658
+ "step": 2125
659
+ },
660
+ {
661
+ "epoch": 3.2477341389728096,
662
+ "grad_norm": 8.297784805297852,
663
+ "learning_rate": 1.0449013848090642e-05,
664
+ "loss": 3.4024,
665
+ "step": 2150
666
+ },
667
+ {
668
+ "epoch": 3.285498489425982,
669
+ "grad_norm": 8.063372611999512,
670
+ "learning_rate": 9.924464960134285e-06,
671
+ "loss": 3.4202,
672
+ "step": 2175
673
+ },
674
+ {
675
+ "epoch": 3.323262839879154,
676
+ "grad_norm": 7.8603515625,
677
+ "learning_rate": 9.399916072177927e-06,
678
+ "loss": 3.4905,
679
+ "step": 2200
680
+ },
681
+ {
682
+ "epoch": 3.3610271903323263,
683
+ "grad_norm": 8.366976737976074,
684
+ "learning_rate": 8.87536718422157e-06,
685
+ "loss": 3.395,
686
+ "step": 2225
687
+ },
688
+ {
689
+ "epoch": 3.3987915407854983,
690
+ "grad_norm": 8.408001899719238,
691
+ "learning_rate": 8.350818296265214e-06,
692
+ "loss": 3.4572,
693
+ "step": 2250
694
+ },
695
+ {
696
+ "epoch": 3.4365558912386707,
697
+ "grad_norm": 7.793301582336426,
698
+ "learning_rate": 7.826269408308854e-06,
699
+ "loss": 3.3398,
700
+ "step": 2275
701
+ },
702
+ {
703
+ "epoch": 3.474320241691843,
704
+ "grad_norm": 8.445042610168457,
705
+ "learning_rate": 7.301720520352497e-06,
706
+ "loss": 3.3126,
707
+ "step": 2300
708
+ },
709
+ {
710
+ "epoch": 3.512084592145015,
711
+ "grad_norm": 8.048064231872559,
712
+ "learning_rate": 6.77717163239614e-06,
713
+ "loss": 3.3747,
714
+ "step": 2325
715
+ },
716
+ {
717
+ "epoch": 3.5498489425981874,
718
+ "grad_norm": 8.69857120513916,
719
+ "learning_rate": 6.252622744439782e-06,
720
+ "loss": 3.424,
721
+ "step": 2350
722
+ },
723
+ {
724
+ "epoch": 3.5876132930513593,
725
+ "grad_norm": 8.197694778442383,
726
+ "learning_rate": 5.728073856483424e-06,
727
+ "loss": 3.3231,
728
+ "step": 2375
729
+ },
730
+ {
731
+ "epoch": 3.6253776435045317,
732
+ "grad_norm": 8.308802604675293,
733
+ "learning_rate": 5.2035249685270664e-06,
734
+ "loss": 3.2876,
735
+ "step": 2400
736
+ },
737
+ {
738
+ "epoch": 3.663141993957704,
739
+ "grad_norm": 8.097749710083008,
740
+ "learning_rate": 4.67897608057071e-06,
741
+ "loss": 3.201,
742
+ "step": 2425
743
+ },
744
+ {
745
+ "epoch": 3.700906344410876,
746
+ "grad_norm": 8.310770988464355,
747
+ "learning_rate": 4.154427192614352e-06,
748
+ "loss": 3.3542,
749
+ "step": 2450
750
+ },
751
+ {
752
+ "epoch": 3.7386706948640485,
753
+ "grad_norm": 8.366157531738281,
754
+ "learning_rate": 3.6298783046579945e-06,
755
+ "loss": 3.4844,
756
+ "step": 2475
757
+ },
758
+ {
759
+ "epoch": 3.7764350453172204,
760
+ "grad_norm": 8.279153823852539,
761
+ "learning_rate": 3.1053294167016365e-06,
762
+ "loss": 3.2068,
763
+ "step": 2500
764
+ },
765
+ {
766
+ "epoch": 3.814199395770393,
767
+ "grad_norm": 8.165327072143555,
768
+ "learning_rate": 2.5807805287452793e-06,
769
+ "loss": 3.3177,
770
+ "step": 2525
771
+ },
772
+ {
773
+ "epoch": 3.851963746223565,
774
+ "grad_norm": 8.91379165649414,
775
+ "learning_rate": 2.0562316407889217e-06,
776
+ "loss": 3.2367,
777
+ "step": 2550
778
+ },
779
+ {
780
+ "epoch": 3.889728096676737,
781
+ "grad_norm": 8.2485990524292,
782
+ "learning_rate": 1.5316827528325641e-06,
783
+ "loss": 3.3136,
784
+ "step": 2575
785
+ },
786
+ {
787
+ "epoch": 3.9274924471299095,
788
+ "grad_norm": 7.780291557312012,
789
+ "learning_rate": 1.0071338648762065e-06,
790
+ "loss": 3.273,
791
+ "step": 2600
792
+ },
793
+ {
794
+ "epoch": 3.9652567975830815,
795
+ "grad_norm": 8.575440406799316,
796
+ "learning_rate": 4.82584976919849e-07,
797
+ "loss": 3.3768,
798
+ "step": 2625
799
+ },
800
+ {
801
+ "epoch": 4.0,
802
+ "eval_accuracy": 0.5051039697542533,
803
+ "eval_f1_macro": 0.2675876194485524,
804
+ "eval_f1_micro": 0.5051039697542533,
805
+ "eval_f1_weighted": 0.4266553262031796,
806
+ "eval_loss": 3.0925960540771484,
807
+ "eval_precision_macro": 0.2522810784129609,
808
+ "eval_precision_micro": 0.5051039697542533,
809
+ "eval_precision_weighted": 0.40593727556638787,
810
+ "eval_recall_macro": 0.33,
811
+ "eval_recall_micro": 0.5051039697542533,
812
+ "eval_recall_weighted": 0.5051039697542533,
813
+ "eval_runtime": 244.9673,
814
+ "eval_samples_per_second": 10.797,
815
+ "eval_steps_per_second": 0.339,
816
+ "step": 2648
817
+ }
818
+ ],
819
+ "logging_steps": 25,
820
+ "max_steps": 2648,
821
+ "num_input_tokens_seen": 0,
822
+ "num_train_epochs": 4,
823
+ "save_steps": 500,
824
+ "stateful_callbacks": {
825
+ "EarlyStoppingCallback": {
826
+ "args": {
827
+ "early_stopping_patience": 5,
828
+ "early_stopping_threshold": 0.01
829
+ },
830
+ "attributes": {
831
+ "early_stopping_patience_counter": 0
832
+ }
833
+ },
834
+ "TrainerControl": {
835
+ "args": {
836
+ "should_epoch_stop": false,
837
+ "should_evaluate": false,
838
+ "should_log": false,
839
+ "should_save": true,
840
+ "should_training_stop": true
841
+ },
842
+ "attributes": {}
843
+ }
844
+ },
845
+ "total_flos": 2867373216675840.0,
846
+ "train_batch_size": 16,
847
+ "trial_name": null,
848
+ "trial_params": null
849
+ }
checkpoint-2648/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8976efb026de4cae8eeae2591832f4b40560e4205decc79e257258b73c1e7552
3
+ size 5368
config.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58d18f01a94fd13c42e421849d96257e2bf141b3d8e2fd588a546c9b8353fbe6
3
+ size 271809860
runs/Sep16_16-11-15_r-aimanfadillah-training-standardize-93trnrqb-97210-xfee3/events.out.tfevents.1758039077.r-aimanfadillah-training-standardize-93trnrqb-97210-xfee3.63.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:529769466ad3eb008dde7e30552ddcab53436cba129aa4828d30ed97d16c94fc
3
- size 160486
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a9b7aab86fc3e183c100a17b497567919e46f1d8b6684f9756977ab1ba0bdd4
3
+ size 162517
runs/Sep16_16-11-15_r-aimanfadillah-training-standardize-93trnrqb-97210-xfee3/events.out.tfevents.1758055859.r-aimanfadillah-training-standardize-93trnrqb-97210-xfee3.63.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd83633ea2555259c0c151854ccf15ec40b793068a1d7a58f4637da8ae0d39db
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": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8976efb026de4cae8eeae2591832f4b40560e4205decc79e257258b73c1e7552
3
+ size 5368
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "matching-buyback/autotrain-data",
3
+ "model": "distilbert/distilbert-base-uncased",
4
+ "lr": 5e-05,
5
+ "epochs": 4,
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": "matching-buyback",
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": "aimanfadillah",
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