pgfeldman commited on
Commit
3461cb8
1 Parent(s): 07952a2

Upload 12 files

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_loss": 2.7187864780426025,
4
+ "eval_runtime": 682.2645,
5
+ "eval_samples": 9883,
6
+ "eval_samples_per_second": 14.486,
7
+ "eval_steps_per_second": 1.812,
8
+ "perplexity": 15.16191176361028,
9
+ "train_loss": 2.9834200300580593,
10
+ "train_runtime": 15417.1336,
11
+ "train_samples": 9883,
12
+ "train_samples_per_second": 3.846,
13
+ "train_steps_per_second": 3.846
14
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.10.0.dev0",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_loss": 2.7187864780426025,
4
+ "eval_runtime": 682.2645,
5
+ "eval_samples": 9883,
6
+ "eval_samples_per_second": 14.486,
7
+ "eval_steps_per_second": 1.812,
8
+ "perplexity": 15.16191176361028
9
+ }
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:ce2fa70f569a99abfd0fc0ed52559390139ef1318ee7d5331aaafab87c50e65b
3
+ size 510407951
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "train_loss": 2.9834200300580593,
4
+ "train_runtime": 15417.1336,
5
+ "train_samples": 9883,
6
+ "train_samples_per_second": 3.846,
7
+ "train_steps_per_second": 3.846
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.0,
5
+ "global_step": 59298,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 4.957840062059429e-05,
13
+ "loss": 3.4611,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "learning_rate": 4.915680124118858e-05,
19
+ "loss": 3.3849,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.15,
24
+ "learning_rate": 4.8735201861782864e-05,
25
+ "loss": 3.3355,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.2,
30
+ "learning_rate": 4.831360248237715e-05,
31
+ "loss": 3.3087,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.25,
36
+ "learning_rate": 4.7892003102971434e-05,
37
+ "loss": 3.2799,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.3,
42
+ "learning_rate": 4.747040372356572e-05,
43
+ "loss": 3.2638,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.35,
48
+ "learning_rate": 4.704880434416001e-05,
49
+ "loss": 3.2501,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.4,
54
+ "learning_rate": 4.6627204964754295e-05,
55
+ "loss": 3.2575,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.46,
60
+ "learning_rate": 4.620560558534858e-05,
61
+ "loss": 3.25,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.51,
66
+ "learning_rate": 4.5784006205942865e-05,
67
+ "loss": 3.214,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.56,
72
+ "learning_rate": 4.536240682653715e-05,
73
+ "loss": 3.2253,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.61,
78
+ "learning_rate": 4.494080744713144e-05,
79
+ "loss": 3.2102,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.66,
84
+ "learning_rate": 4.4519208067725726e-05,
85
+ "loss": 3.1872,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.71,
90
+ "learning_rate": 4.409760868832001e-05,
91
+ "loss": 3.1946,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.76,
96
+ "learning_rate": 4.36760093089143e-05,
97
+ "loss": 3.1831,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.81,
102
+ "learning_rate": 4.325440992950859e-05,
103
+ "loss": 3.1851,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.86,
108
+ "learning_rate": 4.283281055010287e-05,
109
+ "loss": 3.1794,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.91,
114
+ "learning_rate": 4.241121117069716e-05,
115
+ "loss": 3.1698,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.96,
120
+ "learning_rate": 4.198961179129144e-05,
121
+ "loss": 3.16,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.01,
126
+ "learning_rate": 4.1568012411885734e-05,
127
+ "loss": 3.1365,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.06,
132
+ "learning_rate": 4.114641303248002e-05,
133
+ "loss": 3.0765,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.11,
138
+ "learning_rate": 4.0724813653074304e-05,
139
+ "loss": 3.0774,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.16,
144
+ "learning_rate": 4.0303214273668596e-05,
145
+ "loss": 3.0747,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.21,
150
+ "learning_rate": 3.9881614894262874e-05,
151
+ "loss": 3.0726,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 1.26,
156
+ "learning_rate": 3.9460015514857165e-05,
157
+ "loss": 3.0738,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 1.32,
162
+ "learning_rate": 3.903841613545145e-05,
163
+ "loss": 3.0799,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 1.37,
168
+ "learning_rate": 3.8616816756045735e-05,
169
+ "loss": 3.059,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 1.42,
174
+ "learning_rate": 3.819521737664003e-05,
175
+ "loss": 3.0648,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 1.47,
180
+ "learning_rate": 3.777361799723431e-05,
181
+ "loss": 3.0643,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 1.52,
186
+ "learning_rate": 3.7352018617828597e-05,
187
+ "loss": 3.0737,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 1.57,
192
+ "learning_rate": 3.693041923842288e-05,
193
+ "loss": 3.0672,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 1.62,
198
+ "learning_rate": 3.6508819859017166e-05,
199
+ "loss": 3.071,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 1.67,
204
+ "learning_rate": 3.608722047961146e-05,
205
+ "loss": 3.058,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 1.72,
210
+ "learning_rate": 3.566562110020574e-05,
211
+ "loss": 3.0572,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 1.77,
216
+ "learning_rate": 3.524402172080003e-05,
217
+ "loss": 3.063,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.82,
222
+ "learning_rate": 3.482242234139432e-05,
223
+ "loss": 3.0507,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.87,
228
+ "learning_rate": 3.44008229619886e-05,
229
+ "loss": 3.0435,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.92,
234
+ "learning_rate": 3.397922358258289e-05,
235
+ "loss": 3.0538,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.97,
240
+ "learning_rate": 3.3557624203177174e-05,
241
+ "loss": 3.0411,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 2.02,
246
+ "learning_rate": 3.313602482377146e-05,
247
+ "loss": 3.0106,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 2.07,
252
+ "learning_rate": 3.271442544436575e-05,
253
+ "loss": 2.9677,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 2.12,
258
+ "learning_rate": 3.2292826064960036e-05,
259
+ "loss": 2.9598,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 2.18,
264
+ "learning_rate": 3.187122668555432e-05,
265
+ "loss": 2.9693,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 2.23,
270
+ "learning_rate": 3.1449627306148605e-05,
271
+ "loss": 2.9833,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 2.28,
276
+ "learning_rate": 3.102802792674289e-05,
277
+ "loss": 2.9675,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 2.33,
282
+ "learning_rate": 3.060642854733718e-05,
283
+ "loss": 2.9713,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 2.38,
288
+ "learning_rate": 3.0184829167931467e-05,
289
+ "loss": 2.9768,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 2.43,
294
+ "learning_rate": 2.9763229788525755e-05,
295
+ "loss": 2.9765,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 2.48,
300
+ "learning_rate": 2.934163040912004e-05,
301
+ "loss": 2.9698,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 2.53,
306
+ "learning_rate": 2.892003102971432e-05,
307
+ "loss": 2.9934,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 2.58,
312
+ "learning_rate": 2.849843165030861e-05,
313
+ "loss": 2.9721,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 2.63,
318
+ "learning_rate": 2.8076832270902898e-05,
319
+ "loss": 2.9766,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 2.68,
324
+ "learning_rate": 2.7655232891497186e-05,
325
+ "loss": 2.986,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 2.73,
330
+ "learning_rate": 2.723363351209147e-05,
331
+ "loss": 2.9856,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 2.78,
336
+ "learning_rate": 2.681203413268576e-05,
337
+ "loss": 2.9851,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 2.83,
342
+ "learning_rate": 2.6390434753280048e-05,
343
+ "loss": 2.9722,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 2.88,
348
+ "learning_rate": 2.596883537387433e-05,
349
+ "loss": 2.9713,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 2.93,
354
+ "learning_rate": 2.5547235994468614e-05,
355
+ "loss": 2.9698,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 2.98,
360
+ "learning_rate": 2.5125636615062902e-05,
361
+ "loss": 2.9742,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 3.04,
366
+ "learning_rate": 2.470403723565719e-05,
367
+ "loss": 2.9437,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 3.09,
372
+ "learning_rate": 2.428243785625148e-05,
373
+ "loss": 2.9012,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 3.14,
378
+ "learning_rate": 2.3860838476845764e-05,
379
+ "loss": 2.903,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 3.19,
384
+ "learning_rate": 2.343923909744005e-05,
385
+ "loss": 2.9115,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 3.24,
390
+ "learning_rate": 2.3017639718034337e-05,
391
+ "loss": 2.9079,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 3.29,
396
+ "learning_rate": 2.2596040338628622e-05,
397
+ "loss": 2.9209,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 3.34,
402
+ "learning_rate": 2.217444095922291e-05,
403
+ "loss": 2.9072,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 3.39,
408
+ "learning_rate": 2.1752841579817195e-05,
409
+ "loss": 2.9141,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 3.44,
414
+ "learning_rate": 2.1331242200411483e-05,
415
+ "loss": 2.9196,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 3.49,
420
+ "learning_rate": 2.0909642821005768e-05,
421
+ "loss": 2.9225,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 3.54,
426
+ "learning_rate": 2.0488043441600056e-05,
427
+ "loss": 2.9171,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 3.59,
432
+ "learning_rate": 2.006644406219434e-05,
433
+ "loss": 2.9171,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 3.64,
438
+ "learning_rate": 1.9644844682788626e-05,
439
+ "loss": 2.9088,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 3.69,
444
+ "learning_rate": 1.9223245303382915e-05,
445
+ "loss": 2.9169,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 3.74,
450
+ "learning_rate": 1.8801645923977203e-05,
451
+ "loss": 2.9197,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 3.79,
456
+ "learning_rate": 1.8380046544571484e-05,
457
+ "loss": 2.9118,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 3.84,
462
+ "learning_rate": 1.7958447165165773e-05,
463
+ "loss": 2.9153,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 3.9,
468
+ "learning_rate": 1.753684778576006e-05,
469
+ "loss": 2.9104,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 3.95,
474
+ "learning_rate": 1.711524840635435e-05,
475
+ "loss": 2.9136,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 4.0,
480
+ "learning_rate": 1.669364902694863e-05,
481
+ "loss": 2.9218,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 4.05,
486
+ "learning_rate": 1.627204964754292e-05,
487
+ "loss": 2.8708,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 4.1,
492
+ "learning_rate": 1.5850450268137207e-05,
493
+ "loss": 2.865,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 4.15,
498
+ "learning_rate": 1.5428850888731492e-05,
499
+ "loss": 2.8641,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 4.2,
504
+ "learning_rate": 1.5007251509325779e-05,
505
+ "loss": 2.8758,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 4.25,
510
+ "learning_rate": 1.4585652129920065e-05,
511
+ "loss": 2.866,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 4.3,
516
+ "learning_rate": 1.416405275051435e-05,
517
+ "loss": 2.8814,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 4.35,
522
+ "learning_rate": 1.3742453371108638e-05,
523
+ "loss": 2.8632,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 4.4,
528
+ "learning_rate": 1.3320853991702925e-05,
529
+ "loss": 2.8634,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 4.45,
534
+ "learning_rate": 1.2899254612297213e-05,
535
+ "loss": 2.8605,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 4.5,
540
+ "learning_rate": 1.2477655232891498e-05,
541
+ "loss": 2.8665,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 4.55,
546
+ "learning_rate": 1.2056055853485785e-05,
547
+ "loss": 2.8697,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 4.6,
552
+ "learning_rate": 1.163445647408007e-05,
553
+ "loss": 2.8756,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 4.65,
558
+ "learning_rate": 1.1212857094674358e-05,
559
+ "loss": 2.8565,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 4.71,
564
+ "learning_rate": 1.0791257715268643e-05,
565
+ "loss": 2.8682,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 4.76,
570
+ "learning_rate": 1.0369658335862931e-05,
571
+ "loss": 2.8639,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 4.81,
576
+ "learning_rate": 9.948058956457216e-06,
577
+ "loss": 2.8667,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 4.86,
582
+ "learning_rate": 9.526459577051503e-06,
583
+ "loss": 2.8715,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 4.91,
588
+ "learning_rate": 9.104860197645789e-06,
589
+ "loss": 2.8704,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 4.96,
594
+ "learning_rate": 8.683260818240076e-06,
595
+ "loss": 2.8771,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 5.01,
600
+ "learning_rate": 8.261661438834362e-06,
601
+ "loss": 2.8545,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 5.06,
606
+ "learning_rate": 7.840062059428649e-06,
607
+ "loss": 2.8237,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 5.11,
612
+ "learning_rate": 7.418462680022935e-06,
613
+ "loss": 2.832,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 5.16,
618
+ "learning_rate": 6.996863300617222e-06,
619
+ "loss": 2.8298,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 5.21,
624
+ "learning_rate": 6.575263921211508e-06,
625
+ "loss": 2.8336,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 5.26,
630
+ "learning_rate": 6.153664541805794e-06,
631
+ "loss": 2.8441,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 5.31,
636
+ "learning_rate": 5.732065162400081e-06,
637
+ "loss": 2.8493,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 5.36,
642
+ "learning_rate": 5.3104657829943675e-06,
643
+ "loss": 2.8324,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 5.41,
648
+ "learning_rate": 4.888866403588654e-06,
649
+ "loss": 2.8422,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 5.46,
654
+ "learning_rate": 4.467267024182941e-06,
655
+ "loss": 2.8419,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 5.51,
660
+ "learning_rate": 4.045667644777227e-06,
661
+ "loss": 2.8283,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 5.57,
666
+ "learning_rate": 3.6240682653715134e-06,
667
+ "loss": 2.8451,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 5.62,
672
+ "learning_rate": 3.2024688859658e-06,
673
+ "loss": 2.8294,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 5.67,
678
+ "learning_rate": 2.7808695065600866e-06,
679
+ "loss": 2.8356,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 5.72,
684
+ "learning_rate": 2.359270127154373e-06,
685
+ "loss": 2.8375,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 5.77,
690
+ "learning_rate": 1.9376707477486594e-06,
691
+ "loss": 2.8328,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 5.82,
696
+ "learning_rate": 1.516071368342946e-06,
697
+ "loss": 2.8397,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 5.87,
702
+ "learning_rate": 1.0944719889372323e-06,
703
+ "loss": 2.8305,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 5.92,
708
+ "learning_rate": 6.728726095315188e-07,
709
+ "loss": 2.8395,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 5.97,
714
+ "learning_rate": 2.5127323012580527e-07,
715
+ "loss": 2.8332,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 6.0,
720
+ "step": 59298,
721
+ "total_flos": 3.0988189827072e+16,
722
+ "train_loss": 2.9834200300580593,
723
+ "train_runtime": 15417.1336,
724
+ "train_samples_per_second": 3.846,
725
+ "train_steps_per_second": 3.846
726
+ }
727
+ ],
728
+ "max_steps": 59298,
729
+ "num_train_epochs": 6,
730
+ "total_flos": 3.0988189827072e+16,
731
+ "trial_name": null,
732
+ "trial_params": null
733
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7186258064e8b804af9a2b71e93991bd1de0ef40df767a79417b4640e3d24b
3
+ size 2607
vocab.json ADDED
The diff for this file is too large to render. See raw diff