nqv2291 commited on
Commit
18273cc
1 Parent(s): 80fcabb

Upload folder using huggingface_hub

Browse files
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.41.2"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:105b3d9c5385600639b059be2572b933c7892f83fb218e075f78e96f63d4ae8f
3
  size 4918393736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:358467db5b2f529693d2a513351636168206ede3a9fa08ba63069c4ac2459ade
3
  size 4918393736
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09632327c3e79e08454e90754e81908e8d7942e1e269603e03eb592c4b496945
3
+ size 7520802
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8f0d0a78543f87a93a7c55970c4df21701e51da5028304bb86079edbb1270d
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5671c0de422189dff152cae166eb49cff39ac2aa88bdb353ba6e07d93451bf
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,921 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9827003787491043,
5
+ "eval_steps": 200,
6
+ "global_step": 1200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008189169822909202,
13
+ "grad_norm": 4.80268669128418,
14
+ "learning_rate": 0.0001,
15
+ "loss": 1.6951,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.016378339645818404,
20
+ "grad_norm": 2.047800302505493,
21
+ "learning_rate": 0.0001,
22
+ "loss": 0.983,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.024567509468727607,
27
+ "grad_norm": 1.5396971702575684,
28
+ "learning_rate": 0.0001,
29
+ "loss": 0.9092,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.03275667929163681,
34
+ "grad_norm": 4.307969093322754,
35
+ "learning_rate": 0.0001,
36
+ "loss": 0.8544,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.04094584911454601,
41
+ "grad_norm": 2.1945383548736572,
42
+ "learning_rate": 0.0001,
43
+ "loss": 0.8015,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.04913501893745521,
48
+ "grad_norm": 1.5352895259857178,
49
+ "learning_rate": 0.0001,
50
+ "loss": 0.7917,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.057324188760364415,
55
+ "grad_norm": 1.9893757104873657,
56
+ "learning_rate": 0.0001,
57
+ "loss": 0.7561,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.06551335858327362,
62
+ "grad_norm": 1.067208170890808,
63
+ "learning_rate": 0.0001,
64
+ "loss": 0.7457,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.07370252840618283,
69
+ "grad_norm": 1.8355977535247803,
70
+ "learning_rate": 0.0001,
71
+ "loss": 0.7197,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.08189169822909202,
76
+ "grad_norm": 0.9938833713531494,
77
+ "learning_rate": 0.0001,
78
+ "loss": 0.6959,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.09008086805200123,
83
+ "grad_norm": 1.5569779872894287,
84
+ "learning_rate": 0.0001,
85
+ "loss": 0.6875,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.09827003787491043,
90
+ "grad_norm": 1.362318515777588,
91
+ "learning_rate": 0.0001,
92
+ "loss": 0.7031,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.10645920769781964,
97
+ "grad_norm": 0.9789265990257263,
98
+ "learning_rate": 0.0001,
99
+ "loss": 0.6744,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.11464837752072883,
104
+ "grad_norm": 0.9227413535118103,
105
+ "learning_rate": 0.0001,
106
+ "loss": 0.6496,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.12283754734363804,
111
+ "grad_norm": 1.0309714078903198,
112
+ "learning_rate": 0.0001,
113
+ "loss": 0.6365,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.13102671716654724,
118
+ "grad_norm": 1.2037794589996338,
119
+ "learning_rate": 0.0001,
120
+ "loss": 0.6629,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.13921588698945644,
125
+ "grad_norm": 0.8785035014152527,
126
+ "learning_rate": 0.0001,
127
+ "loss": 0.6462,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.14740505681236565,
132
+ "grad_norm": 1.5502973794937134,
133
+ "learning_rate": 0.0001,
134
+ "loss": 0.6146,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.15559422663527486,
139
+ "grad_norm": 0.9982532858848572,
140
+ "learning_rate": 0.0001,
141
+ "loss": 0.6205,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.16378339645818404,
146
+ "grad_norm": 1.0146996974945068,
147
+ "learning_rate": 0.0001,
148
+ "loss": 0.6107,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.16378339645818404,
153
+ "eval_loss": 0.5019610524177551,
154
+ "eval_runtime": 993.1256,
155
+ "eval_samples_per_second": 36.249,
156
+ "eval_steps_per_second": 18.125,
157
+ "step": 200
158
+ },
159
+ {
160
+ "epoch": 0.17197256628109325,
161
+ "grad_norm": 1.0556907653808594,
162
+ "learning_rate": 0.0001,
163
+ "loss": 0.6103,
164
+ "step": 210
165
+ },
166
+ {
167
+ "epoch": 0.18016173610400246,
168
+ "grad_norm": 1.069365382194519,
169
+ "learning_rate": 0.0001,
170
+ "loss": 0.6309,
171
+ "step": 220
172
+ },
173
+ {
174
+ "epoch": 0.18835090592691167,
175
+ "grad_norm": 1.2085084915161133,
176
+ "learning_rate": 0.0001,
177
+ "loss": 0.598,
178
+ "step": 230
179
+ },
180
+ {
181
+ "epoch": 0.19654007574982085,
182
+ "grad_norm": 0.8124738931655884,
183
+ "learning_rate": 0.0001,
184
+ "loss": 0.603,
185
+ "step": 240
186
+ },
187
+ {
188
+ "epoch": 0.20472924557273006,
189
+ "grad_norm": 1.032139778137207,
190
+ "learning_rate": 0.0001,
191
+ "loss": 0.611,
192
+ "step": 250
193
+ },
194
+ {
195
+ "epoch": 0.21291841539563927,
196
+ "grad_norm": 0.8203685283660889,
197
+ "learning_rate": 0.0001,
198
+ "loss": 0.5709,
199
+ "step": 260
200
+ },
201
+ {
202
+ "epoch": 0.22110758521854848,
203
+ "grad_norm": 0.7408131957054138,
204
+ "learning_rate": 0.0001,
205
+ "loss": 0.5753,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 0.22929675504145766,
210
+ "grad_norm": 0.858842134475708,
211
+ "learning_rate": 0.0001,
212
+ "loss": 0.5649,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 0.23748592486436687,
217
+ "grad_norm": 0.9077485799789429,
218
+ "learning_rate": 0.0001,
219
+ "loss": 0.5769,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 0.24567509468727608,
224
+ "grad_norm": 1.1604504585266113,
225
+ "learning_rate": 0.0001,
226
+ "loss": 0.5558,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 0.2538642645101853,
231
+ "grad_norm": 0.7758939266204834,
232
+ "learning_rate": 0.0001,
233
+ "loss": 0.5711,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 0.26205343433309447,
238
+ "grad_norm": 1.2495347261428833,
239
+ "learning_rate": 0.0001,
240
+ "loss": 0.5845,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 0.2702426041560037,
245
+ "grad_norm": 0.8986139297485352,
246
+ "learning_rate": 0.0001,
247
+ "loss": 0.5483,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 0.2784317739789129,
252
+ "grad_norm": 0.7849992513656616,
253
+ "learning_rate": 0.0001,
254
+ "loss": 0.5682,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 0.28662094380182207,
259
+ "grad_norm": 0.8479835987091064,
260
+ "learning_rate": 0.0001,
261
+ "loss": 0.5381,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 0.2948101136247313,
266
+ "grad_norm": 0.9730711579322815,
267
+ "learning_rate": 0.0001,
268
+ "loss": 0.5572,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 0.3029992834476405,
273
+ "grad_norm": 0.8130871653556824,
274
+ "learning_rate": 0.0001,
275
+ "loss": 0.5285,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 0.3111884532705497,
280
+ "grad_norm": 0.7159671783447266,
281
+ "learning_rate": 0.0001,
282
+ "loss": 0.529,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 0.3193776230934589,
287
+ "grad_norm": 0.7021393775939941,
288
+ "learning_rate": 0.0001,
289
+ "loss": 0.5371,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 0.3275667929163681,
294
+ "grad_norm": 0.9046493172645569,
295
+ "learning_rate": 0.0001,
296
+ "loss": 0.5412,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 0.3275667929163681,
301
+ "eval_loss": 0.43820247054100037,
302
+ "eval_runtime": 1014.548,
303
+ "eval_samples_per_second": 35.484,
304
+ "eval_steps_per_second": 17.742,
305
+ "step": 400
306
+ },
307
+ {
308
+ "epoch": 0.3357559627392773,
309
+ "grad_norm": 0.9188250303268433,
310
+ "learning_rate": 0.0001,
311
+ "loss": 0.5567,
312
+ "step": 410
313
+ },
314
+ {
315
+ "epoch": 0.3439451325621865,
316
+ "grad_norm": 0.6707028150558472,
317
+ "learning_rate": 0.0001,
318
+ "loss": 0.5303,
319
+ "step": 420
320
+ },
321
+ {
322
+ "epoch": 0.3521343023850957,
323
+ "grad_norm": 1.1012392044067383,
324
+ "learning_rate": 0.0001,
325
+ "loss": 0.5356,
326
+ "step": 430
327
+ },
328
+ {
329
+ "epoch": 0.3603234722080049,
330
+ "grad_norm": 0.6614859104156494,
331
+ "learning_rate": 0.0001,
332
+ "loss": 0.5443,
333
+ "step": 440
334
+ },
335
+ {
336
+ "epoch": 0.3685126420309141,
337
+ "grad_norm": 0.8753280639648438,
338
+ "learning_rate": 0.0001,
339
+ "loss": 0.5278,
340
+ "step": 450
341
+ },
342
+ {
343
+ "epoch": 0.37670181185382334,
344
+ "grad_norm": 0.713115394115448,
345
+ "learning_rate": 0.0001,
346
+ "loss": 0.5344,
347
+ "step": 460
348
+ },
349
+ {
350
+ "epoch": 0.3848909816767325,
351
+ "grad_norm": 1.034822940826416,
352
+ "learning_rate": 0.0001,
353
+ "loss": 0.511,
354
+ "step": 470
355
+ },
356
+ {
357
+ "epoch": 0.3930801514996417,
358
+ "grad_norm": 0.7497478723526001,
359
+ "learning_rate": 0.0001,
360
+ "loss": 0.5143,
361
+ "step": 480
362
+ },
363
+ {
364
+ "epoch": 0.40126932132255094,
365
+ "grad_norm": 0.9680531024932861,
366
+ "learning_rate": 0.0001,
367
+ "loss": 0.5372,
368
+ "step": 490
369
+ },
370
+ {
371
+ "epoch": 0.4094584911454601,
372
+ "grad_norm": 0.6382943391799927,
373
+ "learning_rate": 0.0001,
374
+ "loss": 0.5242,
375
+ "step": 500
376
+ },
377
+ {
378
+ "epoch": 0.4176476609683693,
379
+ "grad_norm": 0.7657376527786255,
380
+ "learning_rate": 0.0001,
381
+ "loss": 0.5125,
382
+ "step": 510
383
+ },
384
+ {
385
+ "epoch": 0.42583683079127854,
386
+ "grad_norm": 0.9952341914176941,
387
+ "learning_rate": 0.0001,
388
+ "loss": 0.507,
389
+ "step": 520
390
+ },
391
+ {
392
+ "epoch": 0.4340260006141877,
393
+ "grad_norm": 0.8375737071037292,
394
+ "learning_rate": 0.0001,
395
+ "loss": 0.5142,
396
+ "step": 530
397
+ },
398
+ {
399
+ "epoch": 0.44221517043709696,
400
+ "grad_norm": 0.7849007844924927,
401
+ "learning_rate": 0.0001,
402
+ "loss": 0.5049,
403
+ "step": 540
404
+ },
405
+ {
406
+ "epoch": 0.45040434026000614,
407
+ "grad_norm": 0.7818809151649475,
408
+ "learning_rate": 0.0001,
409
+ "loss": 0.4921,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 0.4585935100829153,
414
+ "grad_norm": 0.6086965203285217,
415
+ "learning_rate": 0.0001,
416
+ "loss": 0.5254,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 0.46678267990582456,
421
+ "grad_norm": 0.6038303971290588,
422
+ "learning_rate": 0.0001,
423
+ "loss": 0.5044,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 0.47497184972873374,
428
+ "grad_norm": 0.7107850313186646,
429
+ "learning_rate": 0.0001,
430
+ "loss": 0.5189,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 0.483161019551643,
435
+ "grad_norm": 0.7399956583976746,
436
+ "learning_rate": 0.0001,
437
+ "loss": 0.4814,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 0.49135018937455216,
442
+ "grad_norm": 0.7447919249534607,
443
+ "learning_rate": 0.0001,
444
+ "loss": 0.5273,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 0.49135018937455216,
449
+ "eval_loss": 0.41115716099739075,
450
+ "eval_runtime": 974.1489,
451
+ "eval_samples_per_second": 36.955,
452
+ "eval_steps_per_second": 18.478,
453
+ "step": 600
454
+ },
455
+ {
456
+ "epoch": 0.49953935919746134,
457
+ "grad_norm": 0.7186319231987,
458
+ "learning_rate": 0.0001,
459
+ "loss": 0.4964,
460
+ "step": 610
461
+ },
462
+ {
463
+ "epoch": 0.5077285290203706,
464
+ "grad_norm": 0.6659027338027954,
465
+ "learning_rate": 0.0001,
466
+ "loss": 0.4813,
467
+ "step": 620
468
+ },
469
+ {
470
+ "epoch": 0.5159176988432798,
471
+ "grad_norm": 0.8509200811386108,
472
+ "learning_rate": 0.0001,
473
+ "loss": 0.5007,
474
+ "step": 630
475
+ },
476
+ {
477
+ "epoch": 0.5241068686661889,
478
+ "grad_norm": 0.7163340449333191,
479
+ "learning_rate": 0.0001,
480
+ "loss": 0.4918,
481
+ "step": 640
482
+ },
483
+ {
484
+ "epoch": 0.5322960384890981,
485
+ "grad_norm": 0.6762372851371765,
486
+ "learning_rate": 0.0001,
487
+ "loss": 0.4721,
488
+ "step": 650
489
+ },
490
+ {
491
+ "epoch": 0.5404852083120074,
492
+ "grad_norm": 0.741247832775116,
493
+ "learning_rate": 0.0001,
494
+ "loss": 0.5035,
495
+ "step": 660
496
+ },
497
+ {
498
+ "epoch": 0.5486743781349166,
499
+ "grad_norm": 0.6757375001907349,
500
+ "learning_rate": 0.0001,
501
+ "loss": 0.5044,
502
+ "step": 670
503
+ },
504
+ {
505
+ "epoch": 0.5568635479578258,
506
+ "grad_norm": 0.6605280637741089,
507
+ "learning_rate": 0.0001,
508
+ "loss": 0.5036,
509
+ "step": 680
510
+ },
511
+ {
512
+ "epoch": 0.565052717780735,
513
+ "grad_norm": 0.7928522825241089,
514
+ "learning_rate": 0.0001,
515
+ "loss": 0.4884,
516
+ "step": 690
517
+ },
518
+ {
519
+ "epoch": 0.5732418876036441,
520
+ "grad_norm": 0.7482662796974182,
521
+ "learning_rate": 0.0001,
522
+ "loss": 0.4831,
523
+ "step": 700
524
+ },
525
+ {
526
+ "epoch": 0.5814310574265534,
527
+ "grad_norm": 0.7094814777374268,
528
+ "learning_rate": 0.0001,
529
+ "loss": 0.493,
530
+ "step": 710
531
+ },
532
+ {
533
+ "epoch": 0.5896202272494626,
534
+ "grad_norm": 0.708988606929779,
535
+ "learning_rate": 0.0001,
536
+ "loss": 0.4878,
537
+ "step": 720
538
+ },
539
+ {
540
+ "epoch": 0.5978093970723718,
541
+ "grad_norm": 0.7677808403968811,
542
+ "learning_rate": 0.0001,
543
+ "loss": 0.4819,
544
+ "step": 730
545
+ },
546
+ {
547
+ "epoch": 0.605998566895281,
548
+ "grad_norm": 0.6716774702072144,
549
+ "learning_rate": 0.0001,
550
+ "loss": 0.505,
551
+ "step": 740
552
+ },
553
+ {
554
+ "epoch": 0.6141877367181902,
555
+ "grad_norm": 0.6802059412002563,
556
+ "learning_rate": 0.0001,
557
+ "loss": 0.4612,
558
+ "step": 750
559
+ },
560
+ {
561
+ "epoch": 0.6223769065410995,
562
+ "grad_norm": 0.7577608227729797,
563
+ "learning_rate": 0.0001,
564
+ "loss": 0.4814,
565
+ "step": 760
566
+ },
567
+ {
568
+ "epoch": 0.6305660763640086,
569
+ "grad_norm": 0.6441067457199097,
570
+ "learning_rate": 0.0001,
571
+ "loss": 0.4838,
572
+ "step": 770
573
+ },
574
+ {
575
+ "epoch": 0.6387552461869178,
576
+ "grad_norm": 0.666208028793335,
577
+ "learning_rate": 0.0001,
578
+ "loss": 0.4908,
579
+ "step": 780
580
+ },
581
+ {
582
+ "epoch": 0.646944416009827,
583
+ "grad_norm": 0.7665196657180786,
584
+ "learning_rate": 0.0001,
585
+ "loss": 0.4716,
586
+ "step": 790
587
+ },
588
+ {
589
+ "epoch": 0.6551335858327362,
590
+ "grad_norm": 0.8056005239486694,
591
+ "learning_rate": 0.0001,
592
+ "loss": 0.4717,
593
+ "step": 800
594
+ },
595
+ {
596
+ "epoch": 0.6551335858327362,
597
+ "eval_loss": 0.41053226590156555,
598
+ "eval_runtime": 952.7571,
599
+ "eval_samples_per_second": 37.785,
600
+ "eval_steps_per_second": 18.893,
601
+ "step": 800
602
+ },
603
+ {
604
+ "epoch": 0.6633227556556454,
605
+ "grad_norm": 1.5036696195602417,
606
+ "learning_rate": 0.0001,
607
+ "loss": 0.4711,
608
+ "step": 810
609
+ },
610
+ {
611
+ "epoch": 0.6715119254785546,
612
+ "grad_norm": 0.7547106146812439,
613
+ "learning_rate": 0.0001,
614
+ "loss": 0.476,
615
+ "step": 820
616
+ },
617
+ {
618
+ "epoch": 0.6797010953014638,
619
+ "grad_norm": 0.7936639785766602,
620
+ "learning_rate": 0.0001,
621
+ "loss": 0.4762,
622
+ "step": 830
623
+ },
624
+ {
625
+ "epoch": 0.687890265124373,
626
+ "grad_norm": 0.7227616310119629,
627
+ "learning_rate": 0.0001,
628
+ "loss": 0.4798,
629
+ "step": 840
630
+ },
631
+ {
632
+ "epoch": 0.6960794349472822,
633
+ "grad_norm": 0.7741641402244568,
634
+ "learning_rate": 0.0001,
635
+ "loss": 0.4992,
636
+ "step": 850
637
+ },
638
+ {
639
+ "epoch": 0.7042686047701914,
640
+ "grad_norm": 0.6723213791847229,
641
+ "learning_rate": 0.0001,
642
+ "loss": 0.4818,
643
+ "step": 860
644
+ },
645
+ {
646
+ "epoch": 0.7124577745931007,
647
+ "grad_norm": 0.5631268620491028,
648
+ "learning_rate": 0.0001,
649
+ "loss": 0.481,
650
+ "step": 870
651
+ },
652
+ {
653
+ "epoch": 0.7206469444160098,
654
+ "grad_norm": 0.7071460485458374,
655
+ "learning_rate": 0.0001,
656
+ "loss": 0.4744,
657
+ "step": 880
658
+ },
659
+ {
660
+ "epoch": 0.728836114238919,
661
+ "grad_norm": 0.6503288745880127,
662
+ "learning_rate": 0.0001,
663
+ "loss": 0.4466,
664
+ "step": 890
665
+ },
666
+ {
667
+ "epoch": 0.7370252840618282,
668
+ "grad_norm": 0.6489100456237793,
669
+ "learning_rate": 0.0001,
670
+ "loss": 0.4708,
671
+ "step": 900
672
+ },
673
+ {
674
+ "epoch": 0.7452144538847374,
675
+ "grad_norm": 0.7342277765274048,
676
+ "learning_rate": 0.0001,
677
+ "loss": 0.4687,
678
+ "step": 910
679
+ },
680
+ {
681
+ "epoch": 0.7534036237076467,
682
+ "grad_norm": 0.6502553224563599,
683
+ "learning_rate": 0.0001,
684
+ "loss": 0.4649,
685
+ "step": 920
686
+ },
687
+ {
688
+ "epoch": 0.7615927935305559,
689
+ "grad_norm": 0.6611005663871765,
690
+ "learning_rate": 0.0001,
691
+ "loss": 0.4771,
692
+ "step": 930
693
+ },
694
+ {
695
+ "epoch": 0.769781963353465,
696
+ "grad_norm": 0.5838377475738525,
697
+ "learning_rate": 0.0001,
698
+ "loss": 0.4671,
699
+ "step": 940
700
+ },
701
+ {
702
+ "epoch": 0.7779711331763742,
703
+ "grad_norm": 0.6084617972373962,
704
+ "learning_rate": 0.0001,
705
+ "loss": 0.4701,
706
+ "step": 950
707
+ },
708
+ {
709
+ "epoch": 0.7861603029992834,
710
+ "grad_norm": 0.6489084959030151,
711
+ "learning_rate": 0.0001,
712
+ "loss": 0.4586,
713
+ "step": 960
714
+ },
715
+ {
716
+ "epoch": 0.7943494728221927,
717
+ "grad_norm": 0.6316090226173401,
718
+ "learning_rate": 0.0001,
719
+ "loss": 0.451,
720
+ "step": 970
721
+ },
722
+ {
723
+ "epoch": 0.8025386426451019,
724
+ "grad_norm": 0.6724498271942139,
725
+ "learning_rate": 0.0001,
726
+ "loss": 0.4776,
727
+ "step": 980
728
+ },
729
+ {
730
+ "epoch": 0.8107278124680111,
731
+ "grad_norm": 0.6327974796295166,
732
+ "learning_rate": 0.0001,
733
+ "loss": 0.4708,
734
+ "step": 990
735
+ },
736
+ {
737
+ "epoch": 0.8189169822909202,
738
+ "grad_norm": 0.8041887879371643,
739
+ "learning_rate": 0.0001,
740
+ "loss": 0.4835,
741
+ "step": 1000
742
+ },
743
+ {
744
+ "epoch": 0.8189169822909202,
745
+ "eval_loss": 0.39249786734580994,
746
+ "eval_runtime": 953.0333,
747
+ "eval_samples_per_second": 37.774,
748
+ "eval_steps_per_second": 18.887,
749
+ "step": 1000
750
+ },
751
+ {
752
+ "epoch": 0.8271061521138294,
753
+ "grad_norm": 0.7333071827888489,
754
+ "learning_rate": 0.0001,
755
+ "loss": 0.4662,
756
+ "step": 1010
757
+ },
758
+ {
759
+ "epoch": 0.8352953219367386,
760
+ "grad_norm": 0.6036032438278198,
761
+ "learning_rate": 0.0001,
762
+ "loss": 0.449,
763
+ "step": 1020
764
+ },
765
+ {
766
+ "epoch": 0.8434844917596479,
767
+ "grad_norm": 0.6087955236434937,
768
+ "learning_rate": 0.0001,
769
+ "loss": 0.4651,
770
+ "step": 1030
771
+ },
772
+ {
773
+ "epoch": 0.8516736615825571,
774
+ "grad_norm": 0.8231128454208374,
775
+ "learning_rate": 0.0001,
776
+ "loss": 0.4672,
777
+ "step": 1040
778
+ },
779
+ {
780
+ "epoch": 0.8598628314054663,
781
+ "grad_norm": 0.6176358461380005,
782
+ "learning_rate": 0.0001,
783
+ "loss": 0.4616,
784
+ "step": 1050
785
+ },
786
+ {
787
+ "epoch": 0.8680520012283754,
788
+ "grad_norm": 0.5654678344726562,
789
+ "learning_rate": 0.0001,
790
+ "loss": 0.437,
791
+ "step": 1060
792
+ },
793
+ {
794
+ "epoch": 0.8762411710512846,
795
+ "grad_norm": 0.6934413909912109,
796
+ "learning_rate": 0.0001,
797
+ "loss": 0.4302,
798
+ "step": 1070
799
+ },
800
+ {
801
+ "epoch": 0.8844303408741939,
802
+ "grad_norm": 0.6048303842544556,
803
+ "learning_rate": 0.0001,
804
+ "loss": 0.4584,
805
+ "step": 1080
806
+ },
807
+ {
808
+ "epoch": 0.8926195106971031,
809
+ "grad_norm": 0.6487530469894409,
810
+ "learning_rate": 0.0001,
811
+ "loss": 0.4647,
812
+ "step": 1090
813
+ },
814
+ {
815
+ "epoch": 0.9008086805200123,
816
+ "grad_norm": 0.6674748659133911,
817
+ "learning_rate": 0.0001,
818
+ "loss": 0.467,
819
+ "step": 1100
820
+ },
821
+ {
822
+ "epoch": 0.9089978503429215,
823
+ "grad_norm": 0.6509521007537842,
824
+ "learning_rate": 0.0001,
825
+ "loss": 0.4525,
826
+ "step": 1110
827
+ },
828
+ {
829
+ "epoch": 0.9171870201658306,
830
+ "grad_norm": 0.6949372291564941,
831
+ "learning_rate": 0.0001,
832
+ "loss": 0.4663,
833
+ "step": 1120
834
+ },
835
+ {
836
+ "epoch": 0.9253761899887399,
837
+ "grad_norm": 0.7340756058692932,
838
+ "learning_rate": 0.0001,
839
+ "loss": 0.4297,
840
+ "step": 1130
841
+ },
842
+ {
843
+ "epoch": 0.9335653598116491,
844
+ "grad_norm": 0.5543187856674194,
845
+ "learning_rate": 0.0001,
846
+ "loss": 0.4606,
847
+ "step": 1140
848
+ },
849
+ {
850
+ "epoch": 0.9417545296345583,
851
+ "grad_norm": 0.6061782836914062,
852
+ "learning_rate": 0.0001,
853
+ "loss": 0.4589,
854
+ "step": 1150
855
+ },
856
+ {
857
+ "epoch": 0.9499436994574675,
858
+ "grad_norm": 0.6638914942741394,
859
+ "learning_rate": 0.0001,
860
+ "loss": 0.4252,
861
+ "step": 1160
862
+ },
863
+ {
864
+ "epoch": 0.9581328692803767,
865
+ "grad_norm": 0.5913025736808777,
866
+ "learning_rate": 0.0001,
867
+ "loss": 0.44,
868
+ "step": 1170
869
+ },
870
+ {
871
+ "epoch": 0.966322039103286,
872
+ "grad_norm": 0.5672889947891235,
873
+ "learning_rate": 0.0001,
874
+ "loss": 0.4659,
875
+ "step": 1180
876
+ },
877
+ {
878
+ "epoch": 0.9745112089261951,
879
+ "grad_norm": 0.5614264607429504,
880
+ "learning_rate": 0.0001,
881
+ "loss": 0.4471,
882
+ "step": 1190
883
+ },
884
+ {
885
+ "epoch": 0.9827003787491043,
886
+ "grad_norm": 0.5809562802314758,
887
+ "learning_rate": 0.0001,
888
+ "loss": 0.4288,
889
+ "step": 1200
890
+ },
891
+ {
892
+ "epoch": 0.9827003787491043,
893
+ "eval_loss": 0.37333595752716064,
894
+ "eval_runtime": 961.0219,
895
+ "eval_samples_per_second": 37.46,
896
+ "eval_steps_per_second": 18.73,
897
+ "step": 1200
898
+ }
899
+ ],
900
+ "logging_steps": 10,
901
+ "max_steps": 1221,
902
+ "num_input_tokens_seen": 0,
903
+ "num_train_epochs": 1,
904
+ "save_steps": 400,
905
+ "stateful_callbacks": {
906
+ "TrainerControl": {
907
+ "args": {
908
+ "should_epoch_stop": false,
909
+ "should_evaluate": false,
910
+ "should_log": false,
911
+ "should_save": true,
912
+ "should_training_stop": false
913
+ },
914
+ "attributes": {}
915
+ }
916
+ },
917
+ "total_flos": 7.304264713469952e+17,
918
+ "train_batch_size": 2,
919
+ "trial_name": null,
920
+ "trial_params": null
921
+ }