MHGanainy commited on
Commit
7cbffd2
1 Parent(s): 561250e

MHGanainy/gpt2-xl-lora-multi-512-6

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 +805 -0
README.md CHANGED
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
  # gpt2-xl-lora-multi-512-6
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
  # gpt2-xl-lora-multi-512-6
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: 1.8904
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 1.89044189453125,
4
+ "eval_runtime": 108.7389,
5
+ "eval_samples_per_second": 144.373,
6
+ "eval_steps_per_second": 9.031,
7
+ "perplexity": 6.622294390243397,
8
+ "total_flos": 1.59124040841796e+18,
9
+ "train_loss": 2.048668092511076,
10
+ "train_runtime": 3400.905,
11
+ "train_samples_per_second": 51.372,
12
+ "train_steps_per_second": 3.211
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 1.89044189453125,
4
+ "eval_runtime": 108.7389,
5
+ "eval_samples_per_second": 144.373,
6
+ "eval_steps_per_second": 9.031,
7
+ "perplexity": 6.622294390243397
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 1.59124040841796e+18,
4
+ "train_loss": 2.048668092511076,
5
+ "train_runtime": 3400.905,
6
+ "train_samples_per_second": 51.372,
7
+ "train_steps_per_second": 3.211
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,805 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10920,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009157509157509158,
13
+ "grad_norm": 0.05460265651345253,
14
+ "learning_rate": 2.289639381797367e-07,
15
+ "loss": 2.2583,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.018315018315018316,
20
+ "grad_norm": 0.07254950702190399,
21
+ "learning_rate": 4.579278763594734e-07,
22
+ "loss": 2.2556,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.027472527472527472,
27
+ "grad_norm": 0.07023929059505463,
28
+ "learning_rate": 6.868918145392102e-07,
29
+ "loss": 2.2658,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.03663003663003663,
34
+ "grad_norm": 0.08579763770103455,
35
+ "learning_rate": 9.158557527189468e-07,
36
+ "loss": 2.2546,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.045787545787545784,
41
+ "grad_norm": 0.13748684525489807,
42
+ "learning_rate": 1.1448196908986836e-06,
43
+ "loss": 2.2453,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.054945054945054944,
48
+ "grad_norm": 0.0766037255525589,
49
+ "learning_rate": 1.3737836290784203e-06,
50
+ "loss": 2.2471,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.0641025641025641,
55
+ "grad_norm": 0.18016816675662994,
56
+ "learning_rate": 1.6027475672581568e-06,
57
+ "loss": 2.2481,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.07326007326007326,
62
+ "grad_norm": 0.10347414016723633,
63
+ "learning_rate": 1.8317115054378937e-06,
64
+ "loss": 2.2388,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.08241758241758242,
69
+ "grad_norm": 0.14010679721832275,
70
+ "learning_rate": 2.0606754436176306e-06,
71
+ "loss": 2.2189,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.09157509157509157,
76
+ "grad_norm": 0.12083210051059723,
77
+ "learning_rate": 2.2896393817973673e-06,
78
+ "loss": 2.2308,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.10073260073260074,
83
+ "grad_norm": 0.13420909643173218,
84
+ "learning_rate": 2.5186033199771035e-06,
85
+ "loss": 2.215,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.10989010989010989,
90
+ "grad_norm": 0.15881897509098053,
91
+ "learning_rate": 2.7475672581568406e-06,
92
+ "loss": 2.2177,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.11904761904761904,
97
+ "grad_norm": 0.1493181735277176,
98
+ "learning_rate": 2.97424155695478e-06,
99
+ "loss": 2.2062,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.1282051282051282,
104
+ "grad_norm": 0.17832180857658386,
105
+ "learning_rate": 3.2032054951345167e-06,
106
+ "loss": 2.2018,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.13736263736263737,
111
+ "grad_norm": 0.16811606287956238,
112
+ "learning_rate": 3.4321694333142534e-06,
113
+ "loss": 2.1941,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.14652014652014653,
118
+ "grad_norm": 0.16803540289402008,
119
+ "learning_rate": 3.66113337149399e-06,
120
+ "loss": 2.1665,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.15567765567765568,
125
+ "grad_norm": 0.18348592519760132,
126
+ "learning_rate": 3.890097309673726e-06,
127
+ "loss": 2.1702,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.16483516483516483,
132
+ "grad_norm": 0.19313548505306244,
133
+ "learning_rate": 4.119061247853463e-06,
134
+ "loss": 2.154,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.17399267399267399,
139
+ "grad_norm": 0.1911778450012207,
140
+ "learning_rate": 4.3480251860332005e-06,
141
+ "loss": 2.1665,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.18315018315018314,
146
+ "grad_norm": 0.20000025629997253,
147
+ "learning_rate": 4.574699484831139e-06,
148
+ "loss": 2.1645,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.19230769230769232,
153
+ "grad_norm": 0.23437415063381195,
154
+ "learning_rate": 4.803663423010876e-06,
155
+ "loss": 2.1638,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.20146520146520147,
160
+ "grad_norm": 0.23130947351455688,
161
+ "learning_rate": 5.032627361190613e-06,
162
+ "loss": 2.1656,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.21062271062271062,
167
+ "grad_norm": 0.22546882927417755,
168
+ "learning_rate": 5.26159129937035e-06,
169
+ "loss": 2.1426,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.21978021978021978,
174
+ "grad_norm": 0.23832601308822632,
175
+ "learning_rate": 5.490555237550086e-06,
176
+ "loss": 2.1404,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.22893772893772893,
181
+ "grad_norm": 0.2475137710571289,
182
+ "learning_rate": 5.719519175729823e-06,
183
+ "loss": 2.132,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.23809523809523808,
188
+ "grad_norm": 0.27017173171043396,
189
+ "learning_rate": 5.94848311390956e-06,
190
+ "loss": 2.1334,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.24725274725274726,
195
+ "grad_norm": 0.31527864933013916,
196
+ "learning_rate": 6.177447052089296e-06,
197
+ "loss": 2.1221,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.2564102564102564,
202
+ "grad_norm": 0.39517447352409363,
203
+ "learning_rate": 6.406410990269033e-06,
204
+ "loss": 2.1134,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.26556776556776557,
209
+ "grad_norm": 0.2927546501159668,
210
+ "learning_rate": 6.6353749284487705e-06,
211
+ "loss": 2.1196,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.27472527472527475,
216
+ "grad_norm": 0.28731632232666016,
217
+ "learning_rate": 6.864338866628507e-06,
218
+ "loss": 2.0895,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.2838827838827839,
223
+ "grad_norm": 0.33531680703163147,
224
+ "learning_rate": 7.093302804808243e-06,
225
+ "loss": 2.0915,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.29304029304029305,
230
+ "grad_norm": 0.2969292998313904,
231
+ "learning_rate": 7.32226674298798e-06,
232
+ "loss": 2.0853,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.3021978021978022,
237
+ "grad_norm": 0.32316532731056213,
238
+ "learning_rate": 7.551230681167717e-06,
239
+ "loss": 2.0859,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.31135531135531136,
244
+ "grad_norm": 0.3245663344860077,
245
+ "learning_rate": 7.780194619347453e-06,
246
+ "loss": 2.0655,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.32051282051282054,
251
+ "grad_norm": 0.6936108469963074,
252
+ "learning_rate": 8.00915855752719e-06,
253
+ "loss": 2.06,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.32967032967032966,
258
+ "grad_norm": 0.36271369457244873,
259
+ "learning_rate": 8.238122495706927e-06,
260
+ "loss": 2.0726,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.33882783882783885,
265
+ "grad_norm": 0.3658630847930908,
266
+ "learning_rate": 8.467086433886663e-06,
267
+ "loss": 2.0698,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.34798534798534797,
272
+ "grad_norm": 0.4526204764842987,
273
+ "learning_rate": 8.696050372066401e-06,
274
+ "loss": 2.0497,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.35714285714285715,
279
+ "grad_norm": 0.3695688843727112,
280
+ "learning_rate": 8.925014310246137e-06,
281
+ "loss": 2.0638,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.3663003663003663,
286
+ "grad_norm": 0.3850938379764557,
287
+ "learning_rate": 9.153978248425874e-06,
288
+ "loss": 2.0525,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.37545787545787546,
293
+ "grad_norm": 0.42660748958587646,
294
+ "learning_rate": 9.38294218660561e-06,
295
+ "loss": 2.06,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.38461538461538464,
300
+ "grad_norm": 0.41539886593818665,
301
+ "learning_rate": 9.611906124785348e-06,
302
+ "loss": 2.0474,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.39377289377289376,
307
+ "grad_norm": 0.40648505091667175,
308
+ "learning_rate": 9.840870062965084e-06,
309
+ "loss": 2.0379,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.40293040293040294,
314
+ "grad_norm": 0.5012279152870178,
315
+ "learning_rate": 1.006983400114482e-05,
316
+ "loss": 2.043,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.41208791208791207,
321
+ "grad_norm": 0.38856762647628784,
322
+ "learning_rate": 1.0298797939324557e-05,
323
+ "loss": 2.0299,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.42124542124542125,
328
+ "grad_norm": 0.4283836781978607,
329
+ "learning_rate": 1.0527761877504295e-05,
330
+ "loss": 2.0429,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.43040293040293043,
335
+ "grad_norm": 0.5659844279289246,
336
+ "learning_rate": 1.075672581568403e-05,
337
+ "loss": 2.0415,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.43956043956043955,
342
+ "grad_norm": 0.47702351212501526,
343
+ "learning_rate": 1.0985689753863767e-05,
344
+ "loss": 2.0181,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.44871794871794873,
349
+ "grad_norm": 0.4613106846809387,
350
+ "learning_rate": 1.1212364052661706e-05,
351
+ "loss": 2.0224,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.45787545787545786,
356
+ "grad_norm": 0.4302317500114441,
357
+ "learning_rate": 1.1441327990841444e-05,
358
+ "loss": 2.031,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.46703296703296704,
363
+ "grad_norm": 0.41913115978240967,
364
+ "learning_rate": 1.167029192902118e-05,
365
+ "loss": 2.0182,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.47619047619047616,
370
+ "grad_norm": 0.5346239805221558,
371
+ "learning_rate": 1.1899255867200917e-05,
372
+ "loss": 2.0158,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.48534798534798534,
377
+ "grad_norm": 0.4939456284046173,
378
+ "learning_rate": 1.2128219805380655e-05,
379
+ "loss": 2.0215,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.4945054945054945,
384
+ "grad_norm": 0.42702722549438477,
385
+ "learning_rate": 1.2357183743560391e-05,
386
+ "loss": 2.0081,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.5036630036630036,
391
+ "grad_norm": 0.5567723512649536,
392
+ "learning_rate": 1.2586147681740126e-05,
393
+ "loss": 2.0116,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.5128205128205128,
398
+ "grad_norm": 0.4391794204711914,
399
+ "learning_rate": 1.2815111619919864e-05,
400
+ "loss": 2.0117,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.521978021978022,
405
+ "grad_norm": 0.6212931275367737,
406
+ "learning_rate": 1.30440755580996e-05,
407
+ "loss": 2.0111,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.5311355311355311,
412
+ "grad_norm": 0.4400519132614136,
413
+ "learning_rate": 1.3273039496279336e-05,
414
+ "loss": 2.0099,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.5402930402930403,
419
+ "grad_norm": 0.5068506598472595,
420
+ "learning_rate": 1.3502003434459074e-05,
421
+ "loss": 2.014,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.5494505494505495,
426
+ "grad_norm": 0.5231282711029053,
427
+ "learning_rate": 1.373096737263881e-05,
428
+ "loss": 2.0055,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 0.5586080586080586,
433
+ "grad_norm": 0.5154737234115601,
434
+ "learning_rate": 1.3959931310818547e-05,
435
+ "loss": 2.0046,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 0.5677655677655677,
440
+ "grad_norm": 0.4546205699443817,
441
+ "learning_rate": 1.4188895248998285e-05,
442
+ "loss": 1.9846,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 0.5769230769230769,
447
+ "grad_norm": 0.5952470302581787,
448
+ "learning_rate": 1.441785918717802e-05,
449
+ "loss": 1.9931,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 0.5860805860805861,
454
+ "grad_norm": 0.4483753740787506,
455
+ "learning_rate": 1.4646823125357757e-05,
456
+ "loss": 1.9976,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 0.5952380952380952,
461
+ "grad_norm": 0.5263549089431763,
462
+ "learning_rate": 1.4875787063537495e-05,
463
+ "loss": 1.9938,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 0.6043956043956044,
468
+ "grad_norm": 0.5647267699241638,
469
+ "learning_rate": 1.5104751001717231e-05,
470
+ "loss": 2.0073,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 0.6135531135531136,
475
+ "grad_norm": 0.4960547089576721,
476
+ "learning_rate": 1.5333714939896968e-05,
477
+ "loss": 1.9973,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 0.6227106227106227,
482
+ "grad_norm": 0.6195764541625977,
483
+ "learning_rate": 1.5562678878076704e-05,
484
+ "loss": 1.9929,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 0.6318681318681318,
489
+ "grad_norm": 0.48598435521125793,
490
+ "learning_rate": 1.579164281625644e-05,
491
+ "loss": 1.9864,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 0.6410256410256411,
496
+ "grad_norm": 0.6534644365310669,
497
+ "learning_rate": 1.6020606754436176e-05,
498
+ "loss": 1.9883,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 0.6501831501831502,
503
+ "grad_norm": 0.5080538392066956,
504
+ "learning_rate": 1.6249570692615916e-05,
505
+ "loss": 1.9651,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 0.6593406593406593,
510
+ "grad_norm": 0.502566397190094,
511
+ "learning_rate": 1.6478534630795652e-05,
512
+ "loss": 1.9877,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 0.6684981684981685,
517
+ "grad_norm": 0.5017273426055908,
518
+ "learning_rate": 1.670749856897539e-05,
519
+ "loss": 1.9841,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 0.6776556776556777,
524
+ "grad_norm": 0.6656813621520996,
525
+ "learning_rate": 1.6936462507155125e-05,
526
+ "loss": 1.9798,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 0.6868131868131868,
531
+ "grad_norm": 0.5949518084526062,
532
+ "learning_rate": 1.716542644533486e-05,
533
+ "loss": 1.9929,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 0.6959706959706959,
538
+ "grad_norm": 0.738613486289978,
539
+ "learning_rate": 1.7394390383514597e-05,
540
+ "loss": 1.996,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 0.7051282051282052,
545
+ "grad_norm": 0.5886286497116089,
546
+ "learning_rate": 1.7623354321694334e-05,
547
+ "loss": 1.9669,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 0.7142857142857143,
552
+ "grad_norm": 0.552151083946228,
553
+ "learning_rate": 1.785231825987407e-05,
554
+ "loss": 1.9565,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 0.7234432234432234,
559
+ "grad_norm": 0.5507295727729797,
560
+ "learning_rate": 1.808128219805381e-05,
561
+ "loss": 1.9857,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 0.7326007326007326,
566
+ "grad_norm": 0.7184144258499146,
567
+ "learning_rate": 1.8310246136233546e-05,
568
+ "loss": 1.969,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 0.7417582417582418,
573
+ "grad_norm": 0.5713202953338623,
574
+ "learning_rate": 1.8539210074413282e-05,
575
+ "loss": 1.9797,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 0.7509157509157509,
580
+ "grad_norm": 0.563890278339386,
581
+ "learning_rate": 1.8768174012593018e-05,
582
+ "loss": 1.9643,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 0.76007326007326,
587
+ "grad_norm": 0.6094496846199036,
588
+ "learning_rate": 1.8997137950772755e-05,
589
+ "loss": 1.9758,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 0.7692307692307693,
594
+ "grad_norm": 0.8818446397781372,
595
+ "learning_rate": 1.922610188895249e-05,
596
+ "loss": 1.966,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 0.7783882783882784,
601
+ "grad_norm": 0.5603904128074646,
602
+ "learning_rate": 1.945506582713223e-05,
603
+ "loss": 1.97,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 0.7875457875457875,
608
+ "grad_norm": 0.6132967472076416,
609
+ "learning_rate": 1.9684029765311963e-05,
610
+ "loss": 1.9606,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 0.7967032967032966,
615
+ "grad_norm": 0.5720909237861633,
616
+ "learning_rate": 1.99129937034917e-05,
617
+ "loss": 1.9789,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 0.8058608058608059,
622
+ "grad_norm": 0.5442408919334412,
623
+ "learning_rate": 1.9960293406409122e-05,
624
+ "loss": 1.9667,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 0.815018315018315,
629
+ "grad_norm": 0.6531534194946289,
630
+ "learning_rate": 1.9729957256223114e-05,
631
+ "loss": 1.9748,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 0.8241758241758241,
636
+ "grad_norm": 0.5392922163009644,
637
+ "learning_rate": 1.9298823053295396e-05,
638
+ "loss": 1.9635,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 0.8333333333333334,
643
+ "grad_norm": 0.6137576699256897,
644
+ "learning_rate": 1.8675788155151654e-05,
645
+ "loss": 1.9586,
646
+ "step": 9100
647
+ },
648
+ {
649
+ "epoch": 0.8424908424908425,
650
+ "grad_norm": 0.5812509655952454,
651
+ "learning_rate": 1.787371019220515e-05,
652
+ "loss": 1.9504,
653
+ "step": 9200
654
+ },
655
+ {
656
+ "epoch": 0.8516483516483516,
657
+ "grad_norm": 0.6085131764411926,
658
+ "learning_rate": 1.6909141723615757e-05,
659
+ "loss": 1.9583,
660
+ "step": 9300
661
+ },
662
+ {
663
+ "epoch": 0.8608058608058609,
664
+ "grad_norm": 0.5231878757476807,
665
+ "learning_rate": 1.5801988640553246e-05,
666
+ "loss": 1.959,
667
+ "step": 9400
668
+ },
669
+ {
670
+ "epoch": 0.86996336996337,
671
+ "grad_norm": 0.5782052278518677,
672
+ "learning_rate": 1.4575099366429102e-05,
673
+ "loss": 1.9578,
674
+ "step": 9500
675
+ },
676
+ {
677
+ "epoch": 0.8791208791208791,
678
+ "grad_norm": 0.7281983494758606,
679
+ "learning_rate": 1.3253793331810845e-05,
680
+ "loss": 1.9626,
681
+ "step": 9600
682
+ },
683
+ {
684
+ "epoch": 0.8882783882783882,
685
+ "grad_norm": 0.5513895750045776,
686
+ "learning_rate": 1.1865338454926736e-05,
687
+ "loss": 1.954,
688
+ "step": 9700
689
+ },
690
+ {
691
+ "epoch": 0.8974358974358975,
692
+ "grad_norm": 0.6550291180610657,
693
+ "learning_rate": 1.0438388411045472e-05,
694
+ "loss": 1.9417,
695
+ "step": 9800
696
+ },
697
+ {
698
+ "epoch": 0.9065934065934066,
699
+ "grad_norm": 0.6144053936004639,
700
+ "learning_rate": 9.002391303856074e-06,
701
+ "loss": 1.938,
702
+ "step": 9900
703
+ },
704
+ {
705
+ "epoch": 0.9157509157509157,
706
+ "grad_norm": 0.6759700775146484,
707
+ "learning_rate": 7.586981942153e-06,
708
+ "loss": 1.964,
709
+ "step": 10000
710
+ },
711
+ {
712
+ "epoch": 0.924908424908425,
713
+ "grad_norm": 0.6374625563621521,
714
+ "learning_rate": 6.221370263470199e-06,
715
+ "loss": 1.9537,
716
+ "step": 10100
717
+ },
718
+ {
719
+ "epoch": 0.9340659340659341,
720
+ "grad_norm": 0.6961682438850403,
721
+ "learning_rate": 4.933738525823817e-06,
722
+ "loss": 1.9329,
723
+ "step": 10200
724
+ },
725
+ {
726
+ "epoch": 0.9432234432234432,
727
+ "grad_norm": 0.6878940463066101,
728
+ "learning_rate": 3.750659707774723e-06,
729
+ "loss": 1.9359,
730
+ "step": 10300
731
+ },
732
+ {
733
+ "epoch": 0.9523809523809523,
734
+ "grad_norm": 0.5925911068916321,
735
+ "learning_rate": 2.696549119344161e-06,
736
+ "loss": 1.9381,
737
+ "step": 10400
738
+ },
739
+ {
740
+ "epoch": 0.9615384615384616,
741
+ "grad_norm": 0.5766844749450684,
742
+ "learning_rate": 1.7931605409401575e-06,
743
+ "loss": 1.9414,
744
+ "step": 10500
745
+ },
746
+ {
747
+ "epoch": 0.9706959706959707,
748
+ "grad_norm": 0.5555196404457092,
749
+ "learning_rate": 1.0591372885234885e-06,
750
+ "loss": 1.9472,
751
+ "step": 10600
752
+ },
753
+ {
754
+ "epoch": 0.9798534798534798,
755
+ "grad_norm": 0.7189186811447144,
756
+ "learning_rate": 5.096274697241354e-07,
757
+ "loss": 1.9425,
758
+ "step": 10700
759
+ },
760
+ {
761
+ "epoch": 0.989010989010989,
762
+ "grad_norm": 0.5945115685462952,
763
+ "learning_rate": 1.5597137090428095e-07,
764
+ "loss": 1.9325,
765
+ "step": 10800
766
+ },
767
+ {
768
+ "epoch": 0.9981684981684982,
769
+ "grad_norm": 0.5117030739784241,
770
+ "learning_rate": 5.467426590739511e-09,
771
+ "loss": 1.9445,
772
+ "step": 10900
773
+ },
774
+ {
775
+ "epoch": 1.0,
776
+ "step": 10920,
777
+ "total_flos": 1.59124040841796e+18,
778
+ "train_loss": 2.048668092511076,
779
+ "train_runtime": 3400.905,
780
+ "train_samples_per_second": 51.372,
781
+ "train_steps_per_second": 3.211
782
+ }
783
+ ],
784
+ "logging_steps": 100,
785
+ "max_steps": 10920,
786
+ "num_input_tokens_seen": 0,
787
+ "num_train_epochs": 1,
788
+ "save_steps": 500,
789
+ "stateful_callbacks": {
790
+ "TrainerControl": {
791
+ "args": {
792
+ "should_epoch_stop": false,
793
+ "should_evaluate": false,
794
+ "should_log": false,
795
+ "should_save": true,
796
+ "should_training_stop": true
797
+ },
798
+ "attributes": {}
799
+ }
800
+ },
801
+ "total_flos": 1.59124040841796e+18,
802
+ "train_batch_size": 2,
803
+ "trial_name": null,
804
+ "trial_params": null
805
+ }