prajjwal1 commited on
Commit
9a31c4c
1 Parent(s): 0060a29
added_tokens.json ADDED
@@ -0,0 +1 @@
 
1
+ {"[PAD]": 246534}
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ctrl",
3
+ "architectures": [
4
+ "CTRLLMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "dff": 8192,
8
+ "embd_pdrop": 0.1,
9
+ "from_tf": false,
10
+ "id2label": {
11
+ "0": "LABEL_0"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "label2id": {
15
+ "LABEL_0": 0
16
+ },
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "ctrl",
19
+ "n_ctx": 512,
20
+ "n_embd": 1280,
21
+ "n_head": 16,
22
+ "n_layer": 48,
23
+ "n_positions": 50000,
24
+ "resid_pdrop": 0.1,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "transformers_version": "4.4.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 246535
33
+ }
eval_results_clm.txt ADDED
@@ -0,0 +1 @@
 
1
+ perplexity = 4.45607431027852
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee3ec1714194e355cf8e76eb9c979c40d865c55b5bb097d9546919ce3179fcf
3
+ size 6552165349
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "pad_token": "[PAD]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "model_max_length": 256, "name_or_path": "ctrl"}
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ epoch = 3.0
2
+ train_runtime = 192268.3522
3
+ train_samples_per_second = 0.355
trainer_state.json ADDED
@@ -0,0 +1,839 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 68268,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.963379621491768e-05,
13
+ "loss": 1.7826,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.926759242983536e-05,
19
+ "loss": 1.5222,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.07,
24
+ "learning_rate": 4.890138864475303e-05,
25
+ "loss": 1.4992,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.09,
30
+ "learning_rate": 4.853518485967071e-05,
31
+ "loss": 1.4969,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.11,
36
+ "learning_rate": 4.816898107458839e-05,
37
+ "loss": 1.4997,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.13,
42
+ "learning_rate": 4.780277728950607e-05,
43
+ "loss": 1.4956,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "learning_rate": 4.7436573504423745e-05,
49
+ "loss": 1.4934,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.18,
54
+ "learning_rate": 4.707036971934142e-05,
55
+ "loss": 1.4995,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.2,
60
+ "learning_rate": 4.6704165934259096e-05,
61
+ "loss": 1.4932,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.22,
66
+ "learning_rate": 4.633796214917678e-05,
67
+ "loss": 1.4914,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.24,
72
+ "learning_rate": 4.5971758364094454e-05,
73
+ "loss": 1.4894,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.26,
78
+ "learning_rate": 4.5605554579012136e-05,
79
+ "loss": 1.4955,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.29,
84
+ "learning_rate": 4.5239350793929805e-05,
85
+ "loss": 1.4833,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.31,
90
+ "learning_rate": 4.487314700884749e-05,
91
+ "loss": 1.4888,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.33,
96
+ "learning_rate": 4.450694322376516e-05,
97
+ "loss": 1.4858,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.35,
102
+ "learning_rate": 4.414073943868284e-05,
103
+ "loss": 1.4881,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.37,
108
+ "learning_rate": 4.377453565360052e-05,
109
+ "loss": 1.4882,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.4,
114
+ "learning_rate": 4.3408331868518196e-05,
115
+ "loss": 1.4854,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.42,
120
+ "learning_rate": 4.304212808343587e-05,
121
+ "loss": 1.4933,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.44,
126
+ "learning_rate": 4.267592429835355e-05,
127
+ "loss": 1.4912,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.46,
132
+ "learning_rate": 4.230972051327123e-05,
133
+ "loss": 1.4782,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.48,
138
+ "learning_rate": 4.1943516728188905e-05,
139
+ "loss": 1.4891,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.51,
144
+ "learning_rate": 4.157731294310658e-05,
145
+ "loss": 1.4848,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.53,
150
+ "learning_rate": 4.1211109158024256e-05,
151
+ "loss": 1.4839,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.55,
156
+ "learning_rate": 4.084490537294194e-05,
157
+ "loss": 1.4822,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.57,
162
+ "learning_rate": 4.0478701587859614e-05,
163
+ "loss": 1.4835,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.59,
168
+ "learning_rate": 4.0112497802777296e-05,
169
+ "loss": 1.4849,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.62,
174
+ "learning_rate": 3.9746294017694965e-05,
175
+ "loss": 1.4839,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.64,
180
+ "learning_rate": 3.938009023261265e-05,
181
+ "loss": 1.4838,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.66,
186
+ "learning_rate": 3.901388644753032e-05,
187
+ "loss": 1.4827,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.68,
192
+ "learning_rate": 3.8647682662448e-05,
193
+ "loss": 1.4803,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.7,
198
+ "learning_rate": 3.828147887736568e-05,
199
+ "loss": 1.4756,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.73,
204
+ "learning_rate": 3.7915275092283356e-05,
205
+ "loss": 1.4815,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.75,
210
+ "learning_rate": 3.754907130720103e-05,
211
+ "loss": 1.4737,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.77,
216
+ "learning_rate": 3.718286752211871e-05,
217
+ "loss": 1.4749,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.79,
222
+ "learning_rate": 3.681666373703639e-05,
223
+ "loss": 1.4952,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.81,
228
+ "learning_rate": 3.6450459951954065e-05,
229
+ "loss": 1.4818,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.83,
234
+ "learning_rate": 3.608425616687174e-05,
235
+ "loss": 1.4868,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.86,
240
+ "learning_rate": 3.5718052381789416e-05,
241
+ "loss": 1.4774,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.88,
246
+ "learning_rate": 3.53518485967071e-05,
247
+ "loss": 1.4758,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.9,
252
+ "learning_rate": 3.4985644811624774e-05,
253
+ "loss": 1.4752,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.92,
258
+ "learning_rate": 3.4619441026542456e-05,
259
+ "loss": 1.4782,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.94,
264
+ "learning_rate": 3.425323724146013e-05,
265
+ "loss": 1.4807,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.97,
270
+ "learning_rate": 3.388703345637781e-05,
271
+ "loss": 1.4754,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.99,
276
+ "learning_rate": 3.352082967129548e-05,
277
+ "loss": 1.4764,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 1.01,
282
+ "learning_rate": 3.3154625886213165e-05,
283
+ "loss": 1.4096,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.03,
288
+ "learning_rate": 3.278842210113084e-05,
289
+ "loss": 1.3221,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 1.05,
294
+ "learning_rate": 3.2422218316048517e-05,
295
+ "loss": 1.3234,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 1.08,
300
+ "learning_rate": 3.205601453096619e-05,
301
+ "loss": 1.3303,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 1.1,
306
+ "learning_rate": 3.168981074588387e-05,
307
+ "loss": 1.3323,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 1.12,
312
+ "learning_rate": 3.132360696080155e-05,
313
+ "loss": 1.3368,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 1.14,
318
+ "learning_rate": 3.0957403175719225e-05,
319
+ "loss": 1.3301,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 1.16,
324
+ "learning_rate": 3.05911993906369e-05,
325
+ "loss": 1.3436,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 1.19,
330
+ "learning_rate": 3.022499560555458e-05,
331
+ "loss": 1.3404,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 1.21,
336
+ "learning_rate": 2.985879182047226e-05,
337
+ "loss": 1.33,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 1.23,
342
+ "learning_rate": 2.9492588035389934e-05,
343
+ "loss": 1.3362,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 1.25,
348
+ "learning_rate": 2.9126384250307613e-05,
349
+ "loss": 1.3349,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 1.27,
354
+ "learning_rate": 2.876018046522529e-05,
355
+ "loss": 1.3422,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 1.3,
360
+ "learning_rate": 2.839397668014297e-05,
361
+ "loss": 1.3331,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 1.32,
366
+ "learning_rate": 2.8027772895060643e-05,
367
+ "loss": 1.3389,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 1.34,
372
+ "learning_rate": 2.7661569109978326e-05,
373
+ "loss": 1.3308,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 1.36,
378
+ "learning_rate": 2.7295365324896e-05,
379
+ "loss": 1.3319,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 1.38,
384
+ "learning_rate": 2.6929161539813673e-05,
385
+ "loss": 1.3305,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 1.41,
390
+ "learning_rate": 2.6562957754731356e-05,
391
+ "loss": 1.3361,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 1.43,
396
+ "learning_rate": 2.6196753969649028e-05,
397
+ "loss": 1.3386,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 1.45,
402
+ "learning_rate": 2.583055018456671e-05,
403
+ "loss": 1.3307,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 1.47,
408
+ "learning_rate": 2.5464346399484386e-05,
409
+ "loss": 1.3332,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 1.49,
414
+ "learning_rate": 2.5098142614402065e-05,
415
+ "loss": 1.3437,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 1.52,
420
+ "learning_rate": 2.4731938829319744e-05,
421
+ "loss": 1.341,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 1.54,
426
+ "learning_rate": 2.4365735044237416e-05,
427
+ "loss": 1.3401,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 1.56,
432
+ "learning_rate": 2.3999531259155095e-05,
433
+ "loss": 1.3393,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 1.58,
438
+ "learning_rate": 2.3633327474072774e-05,
439
+ "loss": 1.3426,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 1.6,
444
+ "learning_rate": 2.326712368899045e-05,
445
+ "loss": 1.3376,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 1.63,
450
+ "learning_rate": 2.2900919903908128e-05,
451
+ "loss": 1.334,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 1.65,
456
+ "learning_rate": 2.2534716118825804e-05,
457
+ "loss": 1.3362,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 1.67,
462
+ "learning_rate": 2.2168512333743483e-05,
463
+ "loss": 1.3303,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 1.69,
468
+ "learning_rate": 2.180230854866116e-05,
469
+ "loss": 1.3385,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 1.71,
474
+ "learning_rate": 2.1436104763578837e-05,
475
+ "loss": 1.3364,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 1.74,
480
+ "learning_rate": 2.1069900978496516e-05,
481
+ "loss": 1.3394,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 1.76,
486
+ "learning_rate": 2.070369719341419e-05,
487
+ "loss": 1.3315,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 1.78,
492
+ "learning_rate": 2.033749340833187e-05,
493
+ "loss": 1.3435,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 1.8,
498
+ "learning_rate": 1.997128962324955e-05,
499
+ "loss": 1.3421,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 1.82,
504
+ "learning_rate": 1.9605085838167225e-05,
505
+ "loss": 1.3384,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 1.85,
510
+ "learning_rate": 1.9238882053084904e-05,
511
+ "loss": 1.3388,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 1.87,
516
+ "learning_rate": 1.887267826800258e-05,
517
+ "loss": 1.3366,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 1.89,
522
+ "learning_rate": 1.8506474482920255e-05,
523
+ "loss": 1.347,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 1.91,
528
+ "learning_rate": 1.8140270697837934e-05,
529
+ "loss": 1.336,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 1.93,
534
+ "learning_rate": 1.777406691275561e-05,
535
+ "loss": 1.337,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 1.96,
540
+ "learning_rate": 1.7407863127673288e-05,
541
+ "loss": 1.3428,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 1.98,
546
+ "learning_rate": 1.7041659342590964e-05,
547
+ "loss": 1.3451,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 2.0,
552
+ "learning_rate": 1.6675455557508643e-05,
553
+ "loss": 1.3463,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 2.02,
558
+ "learning_rate": 1.630925177242632e-05,
559
+ "loss": 1.2271,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 2.04,
564
+ "learning_rate": 1.5943047987343997e-05,
565
+ "loss": 1.2264,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 2.07,
570
+ "learning_rate": 1.5576844202261676e-05,
571
+ "loss": 1.2323,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 2.09,
576
+ "learning_rate": 1.5210640417179353e-05,
577
+ "loss": 1.2248,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 2.11,
582
+ "learning_rate": 1.484443663209703e-05,
583
+ "loss": 1.2215,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 2.13,
588
+ "learning_rate": 1.4478232847014708e-05,
589
+ "loss": 1.2293,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 2.15,
594
+ "learning_rate": 1.4112029061932385e-05,
595
+ "loss": 1.2319,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 2.18,
600
+ "learning_rate": 1.3745825276850064e-05,
601
+ "loss": 1.2262,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 2.2,
606
+ "learning_rate": 1.3379621491767741e-05,
607
+ "loss": 1.2289,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 2.22,
612
+ "learning_rate": 1.3013417706685415e-05,
613
+ "loss": 1.2317,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 2.24,
618
+ "learning_rate": 1.2647213921603094e-05,
619
+ "loss": 1.2269,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 2.26,
624
+ "learning_rate": 1.2281010136520773e-05,
625
+ "loss": 1.2277,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 2.29,
630
+ "learning_rate": 1.1914806351438449e-05,
631
+ "loss": 1.2306,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 2.31,
636
+ "learning_rate": 1.1548602566356126e-05,
637
+ "loss": 1.2358,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 2.33,
642
+ "learning_rate": 1.1182398781273803e-05,
643
+ "loss": 1.2277,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 2.35,
648
+ "learning_rate": 1.081619499619148e-05,
649
+ "loss": 1.2271,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 2.37,
654
+ "learning_rate": 1.0449991211109159e-05,
655
+ "loss": 1.2384,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 2.39,
660
+ "learning_rate": 1.0083787426026836e-05,
661
+ "loss": 1.2308,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 2.42,
666
+ "learning_rate": 9.717583640944514e-06,
667
+ "loss": 1.223,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 2.44,
672
+ "learning_rate": 9.35137985586219e-06,
673
+ "loss": 1.2304,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 2.46,
678
+ "learning_rate": 8.985176070779868e-06,
679
+ "loss": 1.2296,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 2.48,
684
+ "learning_rate": 8.618972285697545e-06,
685
+ "loss": 1.2297,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 2.5,
690
+ "learning_rate": 8.252768500615223e-06,
691
+ "loss": 1.2309,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 2.53,
696
+ "learning_rate": 7.8865647155329e-06,
697
+ "loss": 1.2306,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 2.55,
702
+ "learning_rate": 7.520360930450578e-06,
703
+ "loss": 1.228,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 2.57,
708
+ "learning_rate": 7.154157145368255e-06,
709
+ "loss": 1.2297,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 2.59,
714
+ "learning_rate": 6.787953360285932e-06,
715
+ "loss": 1.2363,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 2.61,
720
+ "learning_rate": 6.4217495752036104e-06,
721
+ "loss": 1.2327,
722
+ "step": 59500
723
+ },
724
+ {
725
+ "epoch": 2.64,
726
+ "learning_rate": 6.055545790121287e-06,
727
+ "loss": 1.2316,
728
+ "step": 60000
729
+ },
730
+ {
731
+ "epoch": 2.66,
732
+ "learning_rate": 5.689342005038965e-06,
733
+ "loss": 1.23,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 2.68,
738
+ "learning_rate": 5.323138219956641e-06,
739
+ "loss": 1.2277,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 2.7,
744
+ "learning_rate": 4.956934434874319e-06,
745
+ "loss": 1.2272,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 2.72,
750
+ "learning_rate": 4.590730649791997e-06,
751
+ "loss": 1.2312,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 2.75,
756
+ "learning_rate": 4.224526864709674e-06,
757
+ "loss": 1.2337,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 2.77,
762
+ "learning_rate": 3.858323079627351e-06,
763
+ "loss": 1.228,
764
+ "step": 63000
765
+ },
766
+ {
767
+ "epoch": 2.79,
768
+ "learning_rate": 3.4921192945450287e-06,
769
+ "loss": 1.2276,
770
+ "step": 63500
771
+ },
772
+ {
773
+ "epoch": 2.81,
774
+ "learning_rate": 3.125915509462706e-06,
775
+ "loss": 1.2256,
776
+ "step": 64000
777
+ },
778
+ {
779
+ "epoch": 2.83,
780
+ "learning_rate": 2.7597117243803832e-06,
781
+ "loss": 1.2339,
782
+ "step": 64500
783
+ },
784
+ {
785
+ "epoch": 2.86,
786
+ "learning_rate": 2.3935079392980604e-06,
787
+ "loss": 1.2302,
788
+ "step": 65000
789
+ },
790
+ {
791
+ "epoch": 2.88,
792
+ "learning_rate": 2.027304154215738e-06,
793
+ "loss": 1.2282,
794
+ "step": 65500
795
+ },
796
+ {
797
+ "epoch": 2.9,
798
+ "learning_rate": 1.6611003691334153e-06,
799
+ "loss": 1.2263,
800
+ "step": 66000
801
+ },
802
+ {
803
+ "epoch": 2.92,
804
+ "learning_rate": 1.2948965840510928e-06,
805
+ "loss": 1.2292,
806
+ "step": 66500
807
+ },
808
+ {
809
+ "epoch": 2.94,
810
+ "learning_rate": 9.286927989687702e-07,
811
+ "loss": 1.2356,
812
+ "step": 67000
813
+ },
814
+ {
815
+ "epoch": 2.97,
816
+ "learning_rate": 5.624890138864476e-07,
817
+ "loss": 1.2314,
818
+ "step": 67500
819
+ },
820
+ {
821
+ "epoch": 2.99,
822
+ "learning_rate": 1.962852288041249e-07,
823
+ "loss": 1.2327,
824
+ "step": 68000
825
+ },
826
+ {
827
+ "epoch": 3.0,
828
+ "step": 68268,
829
+ "total_flos": 2748096779848450560,
830
+ "train_runtime": 192268.3522,
831
+ "train_samples_per_second": 0.355
832
+ }
833
+ ],
834
+ "max_steps": 68268,
835
+ "num_train_epochs": 3,
836
+ "total_flos": 2748096779848450560,
837
+ "trial_name": null,
838
+ "trial_params": null
839
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2f7b153c29f53d30846916226338fcc753f1dfd4d88079b8d09374e08f887a
3
+ size 2159
vocab.json ADDED
The diff for this file is too large to render. See raw diff