MHGanainy commited on
Commit
2f3ab50
·
verified ·
1 Parent(s): ec523c9

MHGanainy/16-clusters-imbalanced-8

Browse files
Files changed (5) hide show
  1. README.md +2 -0
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. train_results.json +8 -0
  5. trainer_state.json +504 -0
README.md CHANGED
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
  # 16-clusters-imbalanced-8
16
 
17
  This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
 
 
18
 
19
  ## Model description
20
 
 
15
  # 16-clusters-imbalanced-8
16
 
17
  This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.9228
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 1.9227662086486816,
4
+ "eval_runtime": 90.8042,
5
+ "eval_samples_per_second": 13.546,
6
+ "eval_steps_per_second": 1.696,
7
+ "perplexity": 6.839852784361548,
8
+ "total_flos": 1.215516124053504e+17,
9
+ "train_loss": 2.0444058272706354,
10
+ "train_runtime": 2120.799,
11
+ "train_samples_per_second": 6.308,
12
+ "train_steps_per_second": 3.154
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 1.9227662086486816,
4
+ "eval_runtime": 90.8042,
5
+ "eval_samples_per_second": 13.546,
6
+ "eval_steps_per_second": 1.696,
7
+ "perplexity": 6.839852784361548
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 1.215516124053504e+17,
4
+ "train_loss": 2.0444058272706354,
5
+ "train_runtime": 2120.799,
6
+ "train_samples_per_second": 6.308,
7
+ "train_steps_per_second": 3.154
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,504 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6689,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.014949917775452235,
13
+ "grad_norm": 0.09534981846809387,
14
+ "learning_rate": 6.666666666666667e-06,
15
+ "loss": 2.4036,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.02989983555090447,
20
+ "grad_norm": 0.20187412202358246,
21
+ "learning_rate": 1.3333333333333333e-05,
22
+ "loss": 2.3891,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.044849753326356705,
27
+ "grad_norm": 0.28210878372192383,
28
+ "learning_rate": 2e-05,
29
+ "loss": 2.338,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.05979967110180894,
34
+ "grad_norm": 0.40970563888549805,
35
+ "learning_rate": 1.9987913057228085e-05,
36
+ "loss": 2.2689,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.07474958887726117,
41
+ "grad_norm": 0.49385392665863037,
42
+ "learning_rate": 1.995168144774945e-05,
43
+ "loss": 2.1997,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.08969950665271341,
48
+ "grad_norm": 0.523034393787384,
49
+ "learning_rate": 1.989139275744216e-05,
50
+ "loss": 2.2136,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.10464942442816565,
55
+ "grad_norm": 0.5628554224967957,
56
+ "learning_rate": 1.9807192727496118e-05,
57
+ "loss": 2.1828,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.11959934220361788,
62
+ "grad_norm": 0.6401134133338928,
63
+ "learning_rate": 1.9699284902099995e-05,
64
+ "loss": 2.1685,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.1345492599790701,
69
+ "grad_norm": 0.6661084890365601,
70
+ "learning_rate": 1.9567930136395833e-05,
71
+ "loss": 2.1815,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.14949917775452234,
76
+ "grad_norm": 0.6044815182685852,
77
+ "learning_rate": 1.941344596589081e-05,
78
+ "loss": 2.1246,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.16444909552997458,
83
+ "grad_norm": 0.8036034107208252,
84
+ "learning_rate": 1.923620583885054e-05,
85
+ "loss": 2.17,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.17939901330542682,
90
+ "grad_norm": 0.7904087901115417,
91
+ "learning_rate": 1.9036638213529502e-05,
92
+ "loss": 2.1114,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.19434893108087906,
97
+ "grad_norm": 0.7112478613853455,
98
+ "learning_rate": 1.8815225522420974e-05,
99
+ "loss": 2.0999,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.2092988488563313,
104
+ "grad_norm": 0.7812981605529785,
105
+ "learning_rate": 1.857250300603024e-05,
106
+ "loss": 2.1258,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.22424876663178353,
111
+ "grad_norm": 0.7886794805526733,
112
+ "learning_rate": 1.8309057418990312e-05,
113
+ "loss": 2.0669,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.23919868440723577,
118
+ "grad_norm": 1.2216062545776367,
119
+ "learning_rate": 1.8025525611648004e-05,
120
+ "loss": 2.0778,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.254148602182688,
125
+ "grad_norm": 0.6833907961845398,
126
+ "learning_rate": 1.772259299054919e-05,
127
+ "loss": 2.0822,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.2690985199581402,
132
+ "grad_norm": 0.7946938276290894,
133
+ "learning_rate": 1.740099186154486e-05,
134
+ "loss": 2.0679,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.28404843773359245,
139
+ "grad_norm": 0.8658699989318848,
140
+ "learning_rate": 1.706149965952335e-05,
141
+ "loss": 2.083,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.2989983555090447,
146
+ "grad_norm": 0.9359118342399597,
147
+ "learning_rate": 1.6704937069048125e-05,
148
+ "loss": 2.0376,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.3139482732844969,
153
+ "grad_norm": 0.8539633750915527,
154
+ "learning_rate": 1.6332166040444325e-05,
155
+ "loss": 2.0303,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.32889819105994916,
160
+ "grad_norm": 1.2063894271850586,
161
+ "learning_rate": 1.5944087706129897e-05,
162
+ "loss": 2.0159,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.3438481088354014,
167
+ "grad_norm": 0.9335761666297913,
168
+ "learning_rate": 1.554164020222842e-05,
169
+ "loss": 2.0396,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.35879802661085364,
174
+ "grad_norm": 1.0571390390396118,
175
+ "learning_rate": 1.512579640072957e-05,
176
+ "loss": 2.0499,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.3737479443863059,
181
+ "grad_norm": 0.9539825916290283,
182
+ "learning_rate": 1.4697561557679496e-05,
183
+ "loss": 2.075,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.3886978621617581,
188
+ "grad_norm": 0.9199327230453491,
189
+ "learning_rate": 1.4257970883086375e-05,
190
+ "loss": 2.0483,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.40364777993721035,
195
+ "grad_norm": 0.8960707783699036,
196
+ "learning_rate": 1.3808087038415587e-05,
197
+ "loss": 2.0356,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.4185976977126626,
202
+ "grad_norm": 0.9793922305107117,
203
+ "learning_rate": 1.3348997567724035e-05,
204
+ "loss": 2.0384,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.4335476154881148,
209
+ "grad_norm": 0.9594945907592773,
210
+ "learning_rate": 1.2881812268643615e-05,
211
+ "loss": 2.0479,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.44849753326356706,
216
+ "grad_norm": 0.8938071131706238,
217
+ "learning_rate": 1.2407660509569089e-05,
218
+ "loss": 1.9737,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.4634474510390193,
223
+ "grad_norm": 0.9922735691070557,
224
+ "learning_rate": 1.192768849953589e-05,
225
+ "loss": 2.0189,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.47839736881447154,
230
+ "grad_norm": 1.1176081895828247,
231
+ "learning_rate": 1.1443056517387501e-05,
232
+ "loss": 2.0092,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.4933472865899238,
237
+ "grad_norm": 1.1819413900375366,
238
+ "learning_rate": 1.0954936106930646e-05,
239
+ "loss": 1.952,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.508297204365376,
244
+ "grad_norm": 1.1036977767944336,
245
+ "learning_rate": 1.0464507244858733e-05,
246
+ "loss": 1.9881,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.5232471221408282,
251
+ "grad_norm": 0.8991079330444336,
252
+ "learning_rate": 9.97295548828967e-06,
253
+ "loss": 2.0025,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.5381970399162804,
258
+ "grad_norm": 1.0416226387023926,
259
+ "learning_rate": 9.481469108813673e-06,
260
+ "loss": 1.9782,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.5531469576917327,
265
+ "grad_norm": 1.1091338396072388,
266
+ "learning_rate": 8.991236219979127e-06,
267
+ "loss": 1.955,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.5680968754671849,
272
+ "grad_norm": 1.1093144416809082,
273
+ "learning_rate": 8.503441905160476e-06,
274
+ "loss": 1.9671,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.5830467932426372,
279
+ "grad_norm": 1.1423636674880981,
280
+ "learning_rate": 8.019265352751264e-06,
281
+ "loss": 1.9745,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.5979967110180894,
286
+ "grad_norm": 1.053029179573059,
287
+ "learning_rate": 7.539877005607577e-06,
288
+ "loss": 1.9616,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.6129466287935417,
293
+ "grad_norm": 1.101280689239502,
294
+ "learning_rate": 7.066435731632912e-06,
295
+ "loss": 1.9893,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.6278965465689939,
300
+ "grad_norm": 0.8910824060440063,
301
+ "learning_rate": 6.600086022344145e-06,
302
+ "loss": 1.9976,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.6428464643444461,
307
+ "grad_norm": 0.9344325661659241,
308
+ "learning_rate": 6.141955226190851e-06,
309
+ "loss": 1.9563,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.6577963821198983,
314
+ "grad_norm": 1.0802608728408813,
315
+ "learning_rate": 5.69315082331606e-06,
316
+ "loss": 2.0009,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.6727462998953506,
321
+ "grad_norm": 1.1256142854690552,
322
+ "learning_rate": 5.2547577483464396e-06,
323
+ "loss": 1.9526,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.6876962176708028,
328
+ "grad_norm": 0.9710372090339661,
329
+ "learning_rate": 4.8278357676837474e-06,
330
+ "loss": 2.046,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.7026461354462551,
335
+ "grad_norm": 1.6460671424865723,
336
+ "learning_rate": 4.4134169176376416e-06,
337
+ "loss": 1.982,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.7175960532217073,
342
+ "grad_norm": 1.0602085590362549,
343
+ "learning_rate": 4.0125030095929505e-06,
344
+ "loss": 2.0024,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.7325459709971596,
349
+ "grad_norm": 0.9644867181777954,
350
+ "learning_rate": 3.6260632082422733e-06,
351
+ "loss": 1.9592,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.7474958887726117,
356
+ "grad_norm": 1.122348427772522,
357
+ "learning_rate": 3.255031688738354e-06,
358
+ "loss": 1.9671,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.7624458065480639,
363
+ "grad_norm": 1.3032220602035522,
364
+ "learning_rate": 2.9003053784297598e-06,
365
+ "loss": 1.9744,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.7773957243235162,
370
+ "grad_norm": 1.0730985403060913,
371
+ "learning_rate": 2.5627417886389614e-06,
372
+ "loss": 1.9526,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.7923456420989684,
377
+ "grad_norm": 0.9929338097572327,
378
+ "learning_rate": 2.2431569417243016e-06,
379
+ "loss": 2.016,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.8072955598744207,
384
+ "grad_norm": 0.9761891961097717,
385
+ "learning_rate": 1.942323398436864e-06,
386
+ "loss": 1.9794,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.8222454776498729,
391
+ "grad_norm": 1.0812045335769653,
392
+ "learning_rate": 1.660968390340969e-06,
393
+ "loss": 1.9758,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.8371953954253252,
398
+ "grad_norm": 1.8594285249710083,
399
+ "learning_rate": 1.3997720618128995e-06,
400
+ "loss": 1.9317,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.8521453132007774,
405
+ "grad_norm": 0.884612500667572,
406
+ "learning_rate": 1.1593658258676953e-06,
407
+ "loss": 1.9349,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.8670952309762296,
412
+ "grad_norm": 1.1157561540603638,
413
+ "learning_rate": 9.403308377885268e-07,
414
+ "loss": 2.0075,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.8820451487516818,
419
+ "grad_norm": 0.8770403861999512,
420
+ "learning_rate": 7.43196590248586e-07,
421
+ "loss": 1.9874,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.8969950665271341,
426
+ "grad_norm": 0.9389327764511108,
427
+ "learning_rate": 5.684396333215559e-07,
428
+ "loss": 1.9794,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 0.9119449843025863,
433
+ "grad_norm": 1.3195427656173706,
434
+ "learning_rate": 4.1648242247490753e-07,
435
+ "loss": 1.973,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 0.9268949020780386,
440
+ "grad_norm": 1.1389738321304321,
441
+ "learning_rate": 2.876922973308993e-07,
442
+ "loss": 1.9679,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 0.9418448198534908,
447
+ "grad_norm": 0.9646668434143066,
448
+ "learning_rate": 1.8238059366397222e-07,
449
+ "loss": 1.9918,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 0.9567947376289431,
454
+ "grad_norm": 1.3664929866790771,
455
+ "learning_rate": 1.0080189078121138e-07,
456
+ "loss": 1.9648,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 0.9717446554043953,
461
+ "grad_norm": 1.1920166015625,
462
+ "learning_rate": 4.3153396105249935e-08,
463
+ "loss": 2.0209,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 0.9866945731798475,
468
+ "grad_norm": 1.018936276435852,
469
+ "learning_rate": 9.57446844729315e-09,
470
+ "loss": 1.9294,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 1.0,
475
+ "step": 6689,
476
+ "total_flos": 1.215516124053504e+17,
477
+ "train_loss": 2.0444058272706354,
478
+ "train_runtime": 2120.799,
479
+ "train_samples_per_second": 6.308,
480
+ "train_steps_per_second": 3.154
481
+ }
482
+ ],
483
+ "logging_steps": 100,
484
+ "max_steps": 6689,
485
+ "num_input_tokens_seen": 0,
486
+ "num_train_epochs": 1,
487
+ "save_steps": 500,
488
+ "stateful_callbacks": {
489
+ "TrainerControl": {
490
+ "args": {
491
+ "should_epoch_stop": false,
492
+ "should_evaluate": false,
493
+ "should_log": false,
494
+ "should_save": true,
495
+ "should_training_stop": true
496
+ },
497
+ "attributes": {}
498
+ }
499
+ },
500
+ "total_flos": 1.215516124053504e+17,
501
+ "train_batch_size": 2,
502
+ "trial_name": null,
503
+ "trial_params": null
504
+ }