anoaky commited on
Commit
25d385c
·
verified ·
1 Parent(s): 0aa5de1

Training in progress, epoch 1, checkpoint

Browse files
checkpoint-1108/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.47.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
checkpoint-1108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a770181b755e196d444318da29c49d85933c7a74e44c646a3f539580854ce767
3
+ size 437958648
checkpoint-1108/trainer_state.json ADDED
@@ -0,0 +1,818 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.996845425867508,
5
+ "eval_steps": 500,
6
+ "global_step": 1108,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.018026137899954935,
13
+ "grad_norm": 18.020910263061523,
14
+ "learning_rate": 4.9548736462093865e-05,
15
+ "loss": 0.6809,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03605227579990987,
20
+ "grad_norm": 30.794422149658203,
21
+ "learning_rate": 4.909747292418773e-05,
22
+ "loss": 0.572,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.054078413699864804,
27
+ "grad_norm": 24.659021377563477,
28
+ "learning_rate": 4.864620938628159e-05,
29
+ "loss": 0.554,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.07210455159981974,
34
+ "grad_norm": 17.13719367980957,
35
+ "learning_rate": 4.819494584837546e-05,
36
+ "loss": 0.5261,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.09013068949977468,
41
+ "grad_norm": 50.614078521728516,
42
+ "learning_rate": 4.7743682310469314e-05,
43
+ "loss": 0.5696,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.10815682739972961,
48
+ "grad_norm": 16.31667137145996,
49
+ "learning_rate": 4.7292418772563177e-05,
50
+ "loss": 0.4876,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.12618296529968454,
55
+ "grad_norm": 41.160762786865234,
56
+ "learning_rate": 4.684115523465704e-05,
57
+ "loss": 0.4647,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.14420910319963948,
62
+ "grad_norm": 20.278989791870117,
63
+ "learning_rate": 4.63898916967509e-05,
64
+ "loss": 0.4525,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.16223524109959442,
69
+ "grad_norm": 21.479433059692383,
70
+ "learning_rate": 4.5938628158844764e-05,
71
+ "loss": 0.4511,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.18026137899954936,
76
+ "grad_norm": 20.85803985595703,
77
+ "learning_rate": 4.548736462093863e-05,
78
+ "loss": 0.4828,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.19828751689950427,
83
+ "grad_norm": 19.689502716064453,
84
+ "learning_rate": 4.5036101083032495e-05,
85
+ "loss": 0.4785,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.21631365479945922,
90
+ "grad_norm": 23.28278350830078,
91
+ "learning_rate": 4.458483754512636e-05,
92
+ "loss": 0.4593,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.23433979269941416,
97
+ "grad_norm": 55.461483001708984,
98
+ "learning_rate": 4.413357400722022e-05,
99
+ "loss": 0.4265,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.25236593059936907,
104
+ "grad_norm": 21.591472625732422,
105
+ "learning_rate": 4.368231046931408e-05,
106
+ "loss": 0.4611,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.270392068499324,
111
+ "grad_norm": 31.00871467590332,
112
+ "learning_rate": 4.3231046931407945e-05,
113
+ "loss": 0.4489,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.28841820639927895,
118
+ "grad_norm": 21.315185546875,
119
+ "learning_rate": 4.277978339350181e-05,
120
+ "loss": 0.4755,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.3064443442992339,
125
+ "grad_norm": 25.012041091918945,
126
+ "learning_rate": 4.232851985559567e-05,
127
+ "loss": 0.4703,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.32447048219918884,
132
+ "grad_norm": 18.25890350341797,
133
+ "learning_rate": 4.187725631768953e-05,
134
+ "loss": 0.4456,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.3424966200991438,
139
+ "grad_norm": 19.33783721923828,
140
+ "learning_rate": 4.1425992779783394e-05,
141
+ "loss": 0.4764,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.3605227579990987,
146
+ "grad_norm": 21.992473602294922,
147
+ "learning_rate": 4.0974729241877256e-05,
148
+ "loss": 0.4204,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.3785488958990536,
153
+ "grad_norm": 20.253664016723633,
154
+ "learning_rate": 4.052346570397112e-05,
155
+ "loss": 0.4471,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.39657503379900855,
160
+ "grad_norm": 17.41029167175293,
161
+ "learning_rate": 4.007220216606498e-05,
162
+ "loss": 0.4387,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.4146011716989635,
167
+ "grad_norm": 18.28990364074707,
168
+ "learning_rate": 3.962093862815885e-05,
169
+ "loss": 0.4283,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.43262730959891843,
174
+ "grad_norm": 48.463008880615234,
175
+ "learning_rate": 3.916967509025271e-05,
176
+ "loss": 0.4447,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.45065344749887337,
181
+ "grad_norm": 15.58568000793457,
182
+ "learning_rate": 3.8718411552346575e-05,
183
+ "loss": 0.4257,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4686795853988283,
188
+ "grad_norm": 31.015850067138672,
189
+ "learning_rate": 3.826714801444044e-05,
190
+ "loss": 0.4463,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.48670572329878325,
195
+ "grad_norm": 18.325271606445312,
196
+ "learning_rate": 3.78158844765343e-05,
197
+ "loss": 0.4207,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5047318611987381,
202
+ "grad_norm": 20.241615295410156,
203
+ "learning_rate": 3.7364620938628155e-05,
204
+ "loss": 0.4084,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.5227579990986931,
209
+ "grad_norm": 19.043285369873047,
210
+ "learning_rate": 3.6913357400722025e-05,
211
+ "loss": 0.4345,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.540784136998648,
216
+ "grad_norm": 19.568265914916992,
217
+ "learning_rate": 3.646209386281589e-05,
218
+ "loss": 0.4393,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.558810274898603,
223
+ "grad_norm": 26.981136322021484,
224
+ "learning_rate": 3.601083032490975e-05,
225
+ "loss": 0.4532,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5768364127985579,
230
+ "grad_norm": 17.03878402709961,
231
+ "learning_rate": 3.555956678700361e-05,
232
+ "loss": 0.4208,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5948625506985128,
237
+ "grad_norm": 16.008604049682617,
238
+ "learning_rate": 3.5108303249097474e-05,
239
+ "loss": 0.4396,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.6128886885984678,
244
+ "grad_norm": 20.344444274902344,
245
+ "learning_rate": 3.4657039711191336e-05,
246
+ "loss": 0.4318,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.6309148264984227,
251
+ "grad_norm": 18.641759872436523,
252
+ "learning_rate": 3.42057761732852e-05,
253
+ "loss": 0.4481,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6489409643983777,
258
+ "grad_norm": 25.64444351196289,
259
+ "learning_rate": 3.375451263537907e-05,
260
+ "loss": 0.4053,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6669671022983326,
265
+ "grad_norm": 23.601179122924805,
266
+ "learning_rate": 3.330324909747293e-05,
267
+ "loss": 0.4463,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6849932401982876,
272
+ "grad_norm": 29.48953628540039,
273
+ "learning_rate": 3.2851985559566786e-05,
274
+ "loss": 0.4086,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.7030193780982424,
279
+ "grad_norm": 15.503927230834961,
280
+ "learning_rate": 3.240072202166065e-05,
281
+ "loss": 0.4402,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.7210455159981974,
286
+ "grad_norm": 29.575830459594727,
287
+ "learning_rate": 3.194945848375451e-05,
288
+ "loss": 0.43,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.7390716538981523,
293
+ "grad_norm": 26.154592514038086,
294
+ "learning_rate": 3.149819494584837e-05,
295
+ "loss": 0.432,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7570977917981072,
300
+ "grad_norm": 25.37771987915039,
301
+ "learning_rate": 3.104693140794224e-05,
302
+ "loss": 0.4277,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7751239296980622,
307
+ "grad_norm": 31.5076904296875,
308
+ "learning_rate": 3.0595667870036104e-05,
309
+ "loss": 0.4131,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7931500675980171,
314
+ "grad_norm": 16.534198760986328,
315
+ "learning_rate": 3.0144404332129967e-05,
316
+ "loss": 0.433,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.8111762054979721,
321
+ "grad_norm": 19.064289093017578,
322
+ "learning_rate": 2.969314079422383e-05,
323
+ "loss": 0.3964,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.829202343397927,
328
+ "grad_norm": 18.9260196685791,
329
+ "learning_rate": 2.924187725631769e-05,
330
+ "loss": 0.396,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.847228481297882,
335
+ "grad_norm": 27.17948341369629,
336
+ "learning_rate": 2.879061371841155e-05,
337
+ "loss": 0.4079,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8652546191978369,
342
+ "grad_norm": 21.348743438720703,
343
+ "learning_rate": 2.8339350180505413e-05,
344
+ "loss": 0.4545,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8832807570977917,
349
+ "grad_norm": 15.41019344329834,
350
+ "learning_rate": 2.7888086642599282e-05,
351
+ "loss": 0.4024,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.9013068949977467,
356
+ "grad_norm": 26.81648826599121,
357
+ "learning_rate": 2.7436823104693144e-05,
358
+ "loss": 0.3888,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.9193330328977016,
363
+ "grad_norm": 27.93416976928711,
364
+ "learning_rate": 2.6985559566787007e-05,
365
+ "loss": 0.4086,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.9373591707976566,
370
+ "grad_norm": 14.353543281555176,
371
+ "learning_rate": 2.6534296028880866e-05,
372
+ "loss": 0.416,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.9553853086976115,
377
+ "grad_norm": 15.367998123168945,
378
+ "learning_rate": 2.6083032490974728e-05,
379
+ "loss": 0.4184,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9734114465975665,
384
+ "grad_norm": 22.00202178955078,
385
+ "learning_rate": 2.563176895306859e-05,
386
+ "loss": 0.4294,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9914375844975214,
391
+ "grad_norm": 15.376652717590332,
392
+ "learning_rate": 2.518050541516246e-05,
393
+ "loss": 0.4068,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 1.0,
398
+ "eval_f1": 0.8437814956661963,
399
+ "eval_fn": 317,
400
+ "eval_fp": 458,
401
+ "eval_loss": 0.3667502701282501,
402
+ "eval_precision": 0.8204625637005096,
403
+ "eval_recall": 0.8684647302904565,
404
+ "eval_runtime": 14.8642,
405
+ "eval_samples_per_second": 314.379,
406
+ "eval_steps_per_second": 39.356,
407
+ "eval_tn": 1805,
408
+ "eval_tp": 2093,
409
+ "step": 555
410
+ },
411
+ {
412
+ "epoch": 1.0090130689499774,
413
+ "grad_norm": 33.98088455200195,
414
+ "learning_rate": 2.472924187725632e-05,
415
+ "loss": 0.3578,
416
+ "step": 560
417
+ },
418
+ {
419
+ "epoch": 1.0270392068499323,
420
+ "grad_norm": 24.8944091796875,
421
+ "learning_rate": 2.427797833935018e-05,
422
+ "loss": 0.3203,
423
+ "step": 570
424
+ },
425
+ {
426
+ "epoch": 1.0450653447498874,
427
+ "grad_norm": 17.574607849121094,
428
+ "learning_rate": 2.3826714801444043e-05,
429
+ "loss": 0.335,
430
+ "step": 580
431
+ },
432
+ {
433
+ "epoch": 1.0630914826498423,
434
+ "grad_norm": 26.903356552124023,
435
+ "learning_rate": 2.3375451263537906e-05,
436
+ "loss": 0.289,
437
+ "step": 590
438
+ },
439
+ {
440
+ "epoch": 1.0811176205497972,
441
+ "grad_norm": 31.987625122070312,
442
+ "learning_rate": 2.292418772563177e-05,
443
+ "loss": 0.3511,
444
+ "step": 600
445
+ },
446
+ {
447
+ "epoch": 1.099143758449752,
448
+ "grad_norm": 29.54005241394043,
449
+ "learning_rate": 2.2472924187725634e-05,
450
+ "loss": 0.3126,
451
+ "step": 610
452
+ },
453
+ {
454
+ "epoch": 1.117169896349707,
455
+ "grad_norm": 22.088634490966797,
456
+ "learning_rate": 2.2021660649819496e-05,
457
+ "loss": 0.3004,
458
+ "step": 620
459
+ },
460
+ {
461
+ "epoch": 1.135196034249662,
462
+ "grad_norm": 30.805749893188477,
463
+ "learning_rate": 2.157039711191336e-05,
464
+ "loss": 0.3323,
465
+ "step": 630
466
+ },
467
+ {
468
+ "epoch": 1.153222172149617,
469
+ "grad_norm": 16.607519149780273,
470
+ "learning_rate": 2.111913357400722e-05,
471
+ "loss": 0.3345,
472
+ "step": 640
473
+ },
474
+ {
475
+ "epoch": 1.1712483100495719,
476
+ "grad_norm": 25.248517990112305,
477
+ "learning_rate": 2.0667870036101083e-05,
478
+ "loss": 0.3001,
479
+ "step": 650
480
+ },
481
+ {
482
+ "epoch": 1.1892744479495267,
483
+ "grad_norm": 29.825464248657227,
484
+ "learning_rate": 2.0216606498194946e-05,
485
+ "loss": 0.3146,
486
+ "step": 660
487
+ },
488
+ {
489
+ "epoch": 1.2073005858494819,
490
+ "grad_norm": 30.085296630859375,
491
+ "learning_rate": 1.976534296028881e-05,
492
+ "loss": 0.3335,
493
+ "step": 670
494
+ },
495
+ {
496
+ "epoch": 1.2253267237494367,
497
+ "grad_norm": 23.349525451660156,
498
+ "learning_rate": 1.9314079422382674e-05,
499
+ "loss": 0.27,
500
+ "step": 680
501
+ },
502
+ {
503
+ "epoch": 1.2433528616493916,
504
+ "grad_norm": 34.48153305053711,
505
+ "learning_rate": 1.8862815884476533e-05,
506
+ "loss": 0.3333,
507
+ "step": 690
508
+ },
509
+ {
510
+ "epoch": 1.2613789995493465,
511
+ "grad_norm": 49.01852798461914,
512
+ "learning_rate": 1.84115523465704e-05,
513
+ "loss": 0.275,
514
+ "step": 700
515
+ },
516
+ {
517
+ "epoch": 1.2794051374493014,
518
+ "grad_norm": 24.860200881958008,
519
+ "learning_rate": 1.796028880866426e-05,
520
+ "loss": 0.311,
521
+ "step": 710
522
+ },
523
+ {
524
+ "epoch": 1.2974312753492563,
525
+ "grad_norm": 30.17133331298828,
526
+ "learning_rate": 1.7509025270758123e-05,
527
+ "loss": 0.2988,
528
+ "step": 720
529
+ },
530
+ {
531
+ "epoch": 1.3154574132492114,
532
+ "grad_norm": 47.71062469482422,
533
+ "learning_rate": 1.7057761732851986e-05,
534
+ "loss": 0.2696,
535
+ "step": 730
536
+ },
537
+ {
538
+ "epoch": 1.3334835511491663,
539
+ "grad_norm": 40.605262756347656,
540
+ "learning_rate": 1.6606498194945848e-05,
541
+ "loss": 0.2966,
542
+ "step": 740
543
+ },
544
+ {
545
+ "epoch": 1.3515096890491212,
546
+ "grad_norm": 23.67529296875,
547
+ "learning_rate": 1.615523465703971e-05,
548
+ "loss": 0.2967,
549
+ "step": 750
550
+ },
551
+ {
552
+ "epoch": 1.3695358269490763,
553
+ "grad_norm": 25.661808013916016,
554
+ "learning_rate": 1.5703971119133576e-05,
555
+ "loss": 0.2856,
556
+ "step": 760
557
+ },
558
+ {
559
+ "epoch": 1.3875619648490312,
560
+ "grad_norm": 21.13004493713379,
561
+ "learning_rate": 1.5252707581227438e-05,
562
+ "loss": 0.3415,
563
+ "step": 770
564
+ },
565
+ {
566
+ "epoch": 1.405588102748986,
567
+ "grad_norm": 24.510709762573242,
568
+ "learning_rate": 1.4801444043321299e-05,
569
+ "loss": 0.3044,
570
+ "step": 780
571
+ },
572
+ {
573
+ "epoch": 1.423614240648941,
574
+ "grad_norm": 22.614412307739258,
575
+ "learning_rate": 1.4350180505415165e-05,
576
+ "loss": 0.3042,
577
+ "step": 790
578
+ },
579
+ {
580
+ "epoch": 1.4416403785488958,
581
+ "grad_norm": 26.001209259033203,
582
+ "learning_rate": 1.3898916967509026e-05,
583
+ "loss": 0.2906,
584
+ "step": 800
585
+ },
586
+ {
587
+ "epoch": 1.4596665164488507,
588
+ "grad_norm": 26.30026626586914,
589
+ "learning_rate": 1.3447653429602888e-05,
590
+ "loss": 0.2603,
591
+ "step": 810
592
+ },
593
+ {
594
+ "epoch": 1.4776926543488058,
595
+ "grad_norm": 26.163490295410156,
596
+ "learning_rate": 1.299638989169675e-05,
597
+ "loss": 0.2768,
598
+ "step": 820
599
+ },
600
+ {
601
+ "epoch": 1.4957187922487607,
602
+ "grad_norm": 48.625335693359375,
603
+ "learning_rate": 1.2545126353790614e-05,
604
+ "loss": 0.3203,
605
+ "step": 830
606
+ },
607
+ {
608
+ "epoch": 1.5137449301487156,
609
+ "grad_norm": 19.079364776611328,
610
+ "learning_rate": 1.2093862815884477e-05,
611
+ "loss": 0.3069,
612
+ "step": 840
613
+ },
614
+ {
615
+ "epoch": 1.5317710680486707,
616
+ "grad_norm": 21.295671463012695,
617
+ "learning_rate": 1.164259927797834e-05,
618
+ "loss": 0.2658,
619
+ "step": 850
620
+ },
621
+ {
622
+ "epoch": 1.5497972059486256,
623
+ "grad_norm": 26.641357421875,
624
+ "learning_rate": 1.1191335740072201e-05,
625
+ "loss": 0.281,
626
+ "step": 860
627
+ },
628
+ {
629
+ "epoch": 1.5678233438485805,
630
+ "grad_norm": 33.70462417602539,
631
+ "learning_rate": 1.0740072202166066e-05,
632
+ "loss": 0.2754,
633
+ "step": 870
634
+ },
635
+ {
636
+ "epoch": 1.5858494817485354,
637
+ "grad_norm": 30.827627182006836,
638
+ "learning_rate": 1.028880866425993e-05,
639
+ "loss": 0.2913,
640
+ "step": 880
641
+ },
642
+ {
643
+ "epoch": 1.6038756196484902,
644
+ "grad_norm": 19.456621170043945,
645
+ "learning_rate": 9.83754512635379e-06,
646
+ "loss": 0.3002,
647
+ "step": 890
648
+ },
649
+ {
650
+ "epoch": 1.6219017575484451,
651
+ "grad_norm": 22.82554817199707,
652
+ "learning_rate": 9.386281588447654e-06,
653
+ "loss": 0.3197,
654
+ "step": 900
655
+ },
656
+ {
657
+ "epoch": 1.6399278954484002,
658
+ "grad_norm": 22.25665283203125,
659
+ "learning_rate": 8.935018050541517e-06,
660
+ "loss": 0.3069,
661
+ "step": 910
662
+ },
663
+ {
664
+ "epoch": 1.6579540333483551,
665
+ "grad_norm": 30.897809982299805,
666
+ "learning_rate": 8.483754512635379e-06,
667
+ "loss": 0.2965,
668
+ "step": 920
669
+ },
670
+ {
671
+ "epoch": 1.67598017124831,
672
+ "grad_norm": 21.626707077026367,
673
+ "learning_rate": 8.032490974729243e-06,
674
+ "loss": 0.287,
675
+ "step": 930
676
+ },
677
+ {
678
+ "epoch": 1.694006309148265,
679
+ "grad_norm": 32.338802337646484,
680
+ "learning_rate": 7.581227436823105e-06,
681
+ "loss": 0.2863,
682
+ "step": 940
683
+ },
684
+ {
685
+ "epoch": 1.71203244704822,
686
+ "grad_norm": 21.633394241333008,
687
+ "learning_rate": 7.129963898916968e-06,
688
+ "loss": 0.2822,
689
+ "step": 950
690
+ },
691
+ {
692
+ "epoch": 1.7300585849481749,
693
+ "grad_norm": 18.33571434020996,
694
+ "learning_rate": 6.678700361010831e-06,
695
+ "loss": 0.2676,
696
+ "step": 960
697
+ },
698
+ {
699
+ "epoch": 1.7480847228481298,
700
+ "grad_norm": 29.97617530822754,
701
+ "learning_rate": 6.227436823104693e-06,
702
+ "loss": 0.2652,
703
+ "step": 970
704
+ },
705
+ {
706
+ "epoch": 1.7661108607480847,
707
+ "grad_norm": 37.65591812133789,
708
+ "learning_rate": 5.776173285198557e-06,
709
+ "loss": 0.2956,
710
+ "step": 980
711
+ },
712
+ {
713
+ "epoch": 1.7841369986480395,
714
+ "grad_norm": 33.256507873535156,
715
+ "learning_rate": 5.324909747292419e-06,
716
+ "loss": 0.3358,
717
+ "step": 990
718
+ },
719
+ {
720
+ "epoch": 1.8021631365479944,
721
+ "grad_norm": 24.32988739013672,
722
+ "learning_rate": 4.873646209386281e-06,
723
+ "loss": 0.3075,
724
+ "step": 1000
725
+ },
726
+ {
727
+ "epoch": 1.8201892744479495,
728
+ "grad_norm": 40.130863189697266,
729
+ "learning_rate": 4.422382671480145e-06,
730
+ "loss": 0.2682,
731
+ "step": 1010
732
+ },
733
+ {
734
+ "epoch": 1.8382154123479044,
735
+ "grad_norm": 20.9071044921875,
736
+ "learning_rate": 3.971119133574008e-06,
737
+ "loss": 0.2849,
738
+ "step": 1020
739
+ },
740
+ {
741
+ "epoch": 1.8562415502478595,
742
+ "grad_norm": 39.87733840942383,
743
+ "learning_rate": 3.51985559566787e-06,
744
+ "loss": 0.2967,
745
+ "step": 1030
746
+ },
747
+ {
748
+ "epoch": 1.8742676881478144,
749
+ "grad_norm": 27.898658752441406,
750
+ "learning_rate": 3.068592057761733e-06,
751
+ "loss": 0.2846,
752
+ "step": 1040
753
+ },
754
+ {
755
+ "epoch": 1.8922938260477693,
756
+ "grad_norm": 34.07933807373047,
757
+ "learning_rate": 2.6173285198555957e-06,
758
+ "loss": 0.2228,
759
+ "step": 1050
760
+ },
761
+ {
762
+ "epoch": 1.9103199639477242,
763
+ "grad_norm": 20.768266677856445,
764
+ "learning_rate": 2.1660649819494585e-06,
765
+ "loss": 0.269,
766
+ "step": 1060
767
+ },
768
+ {
769
+ "epoch": 1.928346101847679,
770
+ "grad_norm": 29.845983505249023,
771
+ "learning_rate": 1.7148014440433215e-06,
772
+ "loss": 0.2628,
773
+ "step": 1070
774
+ },
775
+ {
776
+ "epoch": 1.946372239747634,
777
+ "grad_norm": 31.16872787475586,
778
+ "learning_rate": 1.263537906137184e-06,
779
+ "loss": 0.2821,
780
+ "step": 1080
781
+ },
782
+ {
783
+ "epoch": 1.9643983776475888,
784
+ "grad_norm": 24.65738868713379,
785
+ "learning_rate": 8.122743682310469e-07,
786
+ "loss": 0.2961,
787
+ "step": 1090
788
+ },
789
+ {
790
+ "epoch": 1.982424515547544,
791
+ "grad_norm": 33.531166076660156,
792
+ "learning_rate": 3.610108303249098e-07,
793
+ "loss": 0.2663,
794
+ "step": 1100
795
+ }
796
+ ],
797
+ "logging_steps": 10,
798
+ "max_steps": 1108,
799
+ "num_input_tokens_seen": 0,
800
+ "num_train_epochs": 2,
801
+ "save_steps": 500,
802
+ "stateful_callbacks": {
803
+ "TrainerControl": {
804
+ "args": {
805
+ "should_epoch_stop": false,
806
+ "should_evaluate": false,
807
+ "should_log": false,
808
+ "should_save": true,
809
+ "should_training_stop": true
810
+ },
811
+ "attributes": {}
812
+ }
813
+ },
814
+ "total_flos": 9326760690401280.0,
815
+ "train_batch_size": 8,
816
+ "trial_name": null,
817
+ "trial_params": null
818
+ }
checkpoint-1108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6e342c007f2cc362633cfcfb92e24456b08c362b2ac6fe5da2a0eb85b9d1d1
3
+ size 5432