rshrott commited on
Commit
5f39d17
1 Parent(s): 06d4901

Training in progress, step 100

Browse files
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.01,
3
+ "train_loss": 0.21891093194946762,
4
+ "train_runtime": 6427.7582,
5
+ "train_samples_per_second": 8.027,
6
+ "train_steps_per_second": 0.502
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:169e32c03c2abee3829664c1b7ee5c2c12b1f5e260d6331e47a990343a363c81
3
  size 343236280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc909d8e38381547222c5a804da1f96a22ad0511f4e9b65417fbd85da5064cc2
3
  size 343236280
runs/Apr15_16-57-14_ryanserver/events.out.tfevents.1713214639.ryanserver.25404.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04edb9b1cc2ae4983c9de9f1edc685b0cf078f83b823071f46a3ce37043d92f
3
+ size 5587
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.01,
3
+ "train_loss": 0.21891093194946762,
4
+ "train_runtime": 6427.7582,
5
+ "train_samples_per_second": 8.027,
6
+ "train_steps_per_second": 0.502
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,933 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0100219229564673,
5
+ "eval_steps": 100,
6
+ "global_step": 3225,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 0.6999576091766357,
14
+ "learning_rate": 4.96124031007752e-05,
15
+ "loss": 0.533,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.02,
20
+ "grad_norm": 0.682187020778656,
21
+ "learning_rate": 4.922480620155039e-05,
22
+ "loss": 0.3801,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "grad_norm": 0.6211907267570496,
28
+ "learning_rate": 4.883720930232558e-05,
29
+ "loss": 0.3996,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.03,
34
+ "grad_norm": 2.131941080093384,
35
+ "learning_rate": 4.8449612403100775e-05,
36
+ "loss": 0.3272,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.04,
41
+ "grad_norm": 0.6068922877311707,
42
+ "learning_rate": 4.8062015503875976e-05,
43
+ "loss": 0.3431,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.05,
48
+ "grad_norm": 2.6034927368164062,
49
+ "learning_rate": 4.7674418604651164e-05,
50
+ "loss": 0.3298,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "grad_norm": 2.252187490463257,
56
+ "learning_rate": 4.728682170542636e-05,
57
+ "loss": 0.3048,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.06,
62
+ "grad_norm": 0.42226940393447876,
63
+ "learning_rate": 4.6899224806201553e-05,
64
+ "loss": 0.2993,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.07,
69
+ "grad_norm": 0.5101619958877563,
70
+ "learning_rate": 4.651162790697675e-05,
71
+ "loss": 0.3291,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.08,
76
+ "grad_norm": 0.44378426671028137,
77
+ "learning_rate": 4.6124031007751936e-05,
78
+ "loss": 0.3254,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.09,
83
+ "grad_norm": 0.39292019605636597,
84
+ "learning_rate": 4.573643410852713e-05,
85
+ "loss": 0.2908,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.09,
90
+ "grad_norm": 0.3389347791671753,
91
+ "learning_rate": 4.5348837209302326e-05,
92
+ "loss": 0.3058,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.1,
97
+ "grad_norm": 0.3901497423648834,
98
+ "learning_rate": 4.496124031007753e-05,
99
+ "loss": 0.343,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.11,
104
+ "grad_norm": 2.7542033195495605,
105
+ "learning_rate": 4.4573643410852715e-05,
106
+ "loss": 0.2969,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.12,
111
+ "grad_norm": 0.3395516872406006,
112
+ "learning_rate": 4.418604651162791e-05,
113
+ "loss": 0.2907,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.13,
118
+ "grad_norm": 0.3581525385379791,
119
+ "learning_rate": 4.3813953488372095e-05,
120
+ "loss": 0.2783,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.13,
125
+ "grad_norm": 0.6102267503738403,
126
+ "learning_rate": 4.342635658914729e-05,
127
+ "loss": 0.266,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.14,
132
+ "grad_norm": 1.409443974494934,
133
+ "learning_rate": 4.3038759689922484e-05,
134
+ "loss": 0.2898,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.15,
139
+ "grad_norm": 2.3266422748565674,
140
+ "learning_rate": 4.265116279069767e-05,
141
+ "loss": 0.2967,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.16,
146
+ "grad_norm": 1.4810105562210083,
147
+ "learning_rate": 4.2263565891472874e-05,
148
+ "loss": 0.2621,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.16,
153
+ "grad_norm": 3.7368390560150146,
154
+ "learning_rate": 4.187596899224807e-05,
155
+ "loss": 0.2766,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.17,
160
+ "grad_norm": 1.7454067468643188,
161
+ "learning_rate": 4.1488372093023256e-05,
162
+ "loss": 0.2435,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.18,
167
+ "grad_norm": 0.34005963802337646,
168
+ "learning_rate": 4.110077519379845e-05,
169
+ "loss": 0.2407,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.19,
174
+ "grad_norm": 1.942692518234253,
175
+ "learning_rate": 4.0713178294573646e-05,
176
+ "loss": 0.2556,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.2,
181
+ "grad_norm": 1.3751680850982666,
182
+ "learning_rate": 4.032558139534884e-05,
183
+ "loss": 0.2352,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.2,
188
+ "grad_norm": 1.911611795425415,
189
+ "learning_rate": 3.993798449612403e-05,
190
+ "loss": 0.2635,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.21,
195
+ "grad_norm": 2.1268646717071533,
196
+ "learning_rate": 3.955038759689922e-05,
197
+ "loss": 0.2473,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.22,
202
+ "grad_norm": 1.866083025932312,
203
+ "learning_rate": 3.9162790697674425e-05,
204
+ "loss": 0.238,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.23,
209
+ "grad_norm": 0.8285239338874817,
210
+ "learning_rate": 3.877519379844962e-05,
211
+ "loss": 0.2666,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.23,
216
+ "grad_norm": 0.8000108003616333,
217
+ "learning_rate": 3.838759689922481e-05,
218
+ "loss": 0.2343,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.24,
223
+ "grad_norm": 0.6987760066986084,
224
+ "learning_rate": 3.8e-05,
225
+ "loss": 0.207,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.25,
230
+ "grad_norm": 1.039829134941101,
231
+ "learning_rate": 3.76124031007752e-05,
232
+ "loss": 0.2469,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.26,
237
+ "grad_norm": 1.2499618530273438,
238
+ "learning_rate": 3.722480620155039e-05,
239
+ "loss": 0.2589,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.27,
244
+ "grad_norm": 2.926412582397461,
245
+ "learning_rate": 3.683720930232558e-05,
246
+ "loss": 0.1872,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.27,
251
+ "grad_norm": 5.37480354309082,
252
+ "learning_rate": 3.6449612403100774e-05,
253
+ "loss": 0.2797,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.28,
258
+ "grad_norm": 1.7981369495391846,
259
+ "learning_rate": 3.6077519379844966e-05,
260
+ "loss": 0.2423,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.29,
265
+ "grad_norm": 1.1063029766082764,
266
+ "learning_rate": 3.568992248062016e-05,
267
+ "loss": 0.2528,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.3,
272
+ "grad_norm": 0.5154077410697937,
273
+ "learning_rate": 3.530232558139535e-05,
274
+ "loss": 0.1966,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.31,
279
+ "grad_norm": 1.958801507949829,
280
+ "learning_rate": 3.4914728682170543e-05,
281
+ "loss": 0.2569,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.31,
286
+ "grad_norm": 0.43896540999412537,
287
+ "learning_rate": 3.452713178294574e-05,
288
+ "loss": 0.2294,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.32,
293
+ "grad_norm": 4.940056800842285,
294
+ "learning_rate": 3.413953488372093e-05,
295
+ "loss": 0.2138,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.33,
300
+ "grad_norm": 2.0871469974517822,
301
+ "learning_rate": 3.375193798449612e-05,
302
+ "loss": 0.2486,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.34,
307
+ "grad_norm": 0.4600803554058075,
308
+ "learning_rate": 3.3364341085271316e-05,
309
+ "loss": 0.1784,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.34,
314
+ "grad_norm": 1.7933701276779175,
315
+ "learning_rate": 3.297674418604652e-05,
316
+ "loss": 0.2486,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.35,
321
+ "grad_norm": 0.8704222440719604,
322
+ "learning_rate": 3.258914728682171e-05,
323
+ "loss": 0.1977,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.36,
328
+ "grad_norm": 2.517425775527954,
329
+ "learning_rate": 3.22015503875969e-05,
330
+ "loss": 0.2128,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.37,
335
+ "grad_norm": 1.5435869693756104,
336
+ "learning_rate": 3.1813953488372094e-05,
337
+ "loss": 0.1889,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.38,
342
+ "grad_norm": 0.8101773262023926,
343
+ "learning_rate": 3.142635658914729e-05,
344
+ "loss": 0.2274,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.38,
349
+ "grad_norm": 0.910406231880188,
350
+ "learning_rate": 3.1038759689922484e-05,
351
+ "loss": 0.1939,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 0.39,
356
+ "grad_norm": 1.1105294227600098,
357
+ "learning_rate": 3.065116279069767e-05,
358
+ "loss": 0.2712,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 0.4,
363
+ "grad_norm": 1.6309148073196411,
364
+ "learning_rate": 3.0263565891472867e-05,
365
+ "loss": 0.2098,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 0.41,
370
+ "grad_norm": 0.6428541541099548,
371
+ "learning_rate": 2.9875968992248065e-05,
372
+ "loss": 0.1944,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 0.41,
377
+ "grad_norm": 1.2899640798568726,
378
+ "learning_rate": 2.948837209302326e-05,
379
+ "loss": 0.232,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 0.42,
384
+ "grad_norm": 0.35119500756263733,
385
+ "learning_rate": 2.910077519379845e-05,
386
+ "loss": 0.2279,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 0.43,
391
+ "grad_norm": 0.7236185669898987,
392
+ "learning_rate": 2.8713178294573645e-05,
393
+ "loss": 0.1759,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 0.44,
398
+ "grad_norm": 0.7780153155326843,
399
+ "learning_rate": 2.8325581395348837e-05,
400
+ "loss": 0.2006,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 0.45,
405
+ "grad_norm": 2.4104530811309814,
406
+ "learning_rate": 2.793798449612403e-05,
407
+ "loss": 0.2128,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 0.45,
412
+ "grad_norm": 0.5463195443153381,
413
+ "learning_rate": 2.7550387596899223e-05,
414
+ "loss": 0.1777,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 0.46,
419
+ "grad_norm": 0.48027583956718445,
420
+ "learning_rate": 2.7162790697674418e-05,
421
+ "loss": 0.1887,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 0.47,
426
+ "grad_norm": 1.2007440328598022,
427
+ "learning_rate": 2.6775193798449616e-05,
428
+ "loss": 0.2016,
429
+ "step": 1500
430
+ },
431
+ {
432
+ "epoch": 0.48,
433
+ "grad_norm": 1.51267409324646,
434
+ "learning_rate": 2.638759689922481e-05,
435
+ "loss": 0.174,
436
+ "step": 1525
437
+ },
438
+ {
439
+ "epoch": 0.49,
440
+ "grad_norm": 2.8868677616119385,
441
+ "learning_rate": 2.6000000000000002e-05,
442
+ "loss": 0.2046,
443
+ "step": 1550
444
+ },
445
+ {
446
+ "epoch": 0.49,
447
+ "grad_norm": 2.025702476501465,
448
+ "learning_rate": 2.5612403100775197e-05,
449
+ "loss": 0.1859,
450
+ "step": 1575
451
+ },
452
+ {
453
+ "epoch": 0.5,
454
+ "grad_norm": 1.341884732246399,
455
+ "learning_rate": 2.5224806201550388e-05,
456
+ "loss": 0.2007,
457
+ "step": 1600
458
+ },
459
+ {
460
+ "epoch": 0.51,
461
+ "grad_norm": 0.914476752281189,
462
+ "learning_rate": 2.4837209302325583e-05,
463
+ "loss": 0.1863,
464
+ "step": 1625
465
+ },
466
+ {
467
+ "epoch": 0.52,
468
+ "grad_norm": 0.8603270649909973,
469
+ "learning_rate": 2.4465116279069768e-05,
470
+ "loss": 0.2002,
471
+ "step": 1650
472
+ },
473
+ {
474
+ "epoch": 0.52,
475
+ "grad_norm": 3.7743961811065674,
476
+ "learning_rate": 2.4077519379844962e-05,
477
+ "loss": 0.1991,
478
+ "step": 1675
479
+ },
480
+ {
481
+ "epoch": 0.53,
482
+ "grad_norm": 2.3465445041656494,
483
+ "learning_rate": 2.3689922480620154e-05,
484
+ "loss": 0.1901,
485
+ "step": 1700
486
+ },
487
+ {
488
+ "epoch": 0.54,
489
+ "grad_norm": 1.6707566976547241,
490
+ "learning_rate": 2.3302325581395352e-05,
491
+ "loss": 0.1805,
492
+ "step": 1725
493
+ },
494
+ {
495
+ "epoch": 0.55,
496
+ "grad_norm": 0.9617774486541748,
497
+ "learning_rate": 2.2914728682170543e-05,
498
+ "loss": 0.2044,
499
+ "step": 1750
500
+ },
501
+ {
502
+ "epoch": 0.56,
503
+ "grad_norm": 1.740809440612793,
504
+ "learning_rate": 2.2527131782945738e-05,
505
+ "loss": 0.2502,
506
+ "step": 1775
507
+ },
508
+ {
509
+ "epoch": 0.56,
510
+ "grad_norm": 1.6407257318496704,
511
+ "learning_rate": 2.213953488372093e-05,
512
+ "loss": 0.2071,
513
+ "step": 1800
514
+ },
515
+ {
516
+ "epoch": 0.57,
517
+ "grad_norm": 0.5815154314041138,
518
+ "learning_rate": 2.1751937984496127e-05,
519
+ "loss": 0.1962,
520
+ "step": 1825
521
+ },
522
+ {
523
+ "epoch": 0.58,
524
+ "grad_norm": 2.898057699203491,
525
+ "learning_rate": 2.136434108527132e-05,
526
+ "loss": 0.168,
527
+ "step": 1850
528
+ },
529
+ {
530
+ "epoch": 0.59,
531
+ "grad_norm": 0.7204940319061279,
532
+ "learning_rate": 2.0976744186046513e-05,
533
+ "loss": 0.1808,
534
+ "step": 1875
535
+ },
536
+ {
537
+ "epoch": 0.6,
538
+ "grad_norm": 1.5870317220687866,
539
+ "learning_rate": 2.0589147286821705e-05,
540
+ "loss": 0.1811,
541
+ "step": 1900
542
+ },
543
+ {
544
+ "epoch": 0.6,
545
+ "grad_norm": 0.8534879088401794,
546
+ "learning_rate": 2.0201550387596903e-05,
547
+ "loss": 0.2235,
548
+ "step": 1925
549
+ },
550
+ {
551
+ "epoch": 0.61,
552
+ "grad_norm": 1.5544407367706299,
553
+ "learning_rate": 1.9813953488372094e-05,
554
+ "loss": 0.192,
555
+ "step": 1950
556
+ },
557
+ {
558
+ "epoch": 0.62,
559
+ "grad_norm": 2.284710645675659,
560
+ "learning_rate": 1.942635658914729e-05,
561
+ "loss": 0.2307,
562
+ "step": 1975
563
+ },
564
+ {
565
+ "epoch": 0.63,
566
+ "grad_norm": 2.3412628173828125,
567
+ "learning_rate": 1.903875968992248e-05,
568
+ "loss": 0.1858,
569
+ "step": 2000
570
+ },
571
+ {
572
+ "epoch": 0.63,
573
+ "grad_norm": 0.5765611529350281,
574
+ "learning_rate": 1.8651162790697675e-05,
575
+ "loss": 0.1833,
576
+ "step": 2025
577
+ },
578
+ {
579
+ "epoch": 0.64,
580
+ "grad_norm": 1.0757735967636108,
581
+ "learning_rate": 1.826356589147287e-05,
582
+ "loss": 0.209,
583
+ "step": 2050
584
+ },
585
+ {
586
+ "epoch": 0.65,
587
+ "grad_norm": 1.0615739822387695,
588
+ "learning_rate": 1.7875968992248064e-05,
589
+ "loss": 0.1591,
590
+ "step": 2075
591
+ },
592
+ {
593
+ "epoch": 0.66,
594
+ "grad_norm": 0.5009509921073914,
595
+ "learning_rate": 1.7488372093023256e-05,
596
+ "loss": 0.1512,
597
+ "step": 2100
598
+ },
599
+ {
600
+ "epoch": 0.67,
601
+ "grad_norm": 2.7069976329803467,
602
+ "learning_rate": 1.710077519379845e-05,
603
+ "loss": 0.2202,
604
+ "step": 2125
605
+ },
606
+ {
607
+ "epoch": 0.67,
608
+ "grad_norm": 1.9919098615646362,
609
+ "learning_rate": 1.6713178294573645e-05,
610
+ "loss": 0.2132,
611
+ "step": 2150
612
+ },
613
+ {
614
+ "epoch": 0.68,
615
+ "grad_norm": 2.6684300899505615,
616
+ "learning_rate": 1.6325581395348837e-05,
617
+ "loss": 0.1887,
618
+ "step": 2175
619
+ },
620
+ {
621
+ "epoch": 0.69,
622
+ "grad_norm": 2.843564987182617,
623
+ "learning_rate": 1.593798449612403e-05,
624
+ "loss": 0.2035,
625
+ "step": 2200
626
+ },
627
+ {
628
+ "epoch": 0.7,
629
+ "grad_norm": 2.938154697418213,
630
+ "learning_rate": 1.5550387596899226e-05,
631
+ "loss": 0.1946,
632
+ "step": 2225
633
+ },
634
+ {
635
+ "epoch": 0.7,
636
+ "grad_norm": 2.365872859954834,
637
+ "learning_rate": 1.516279069767442e-05,
638
+ "loss": 0.159,
639
+ "step": 2250
640
+ },
641
+ {
642
+ "epoch": 0.71,
643
+ "grad_norm": 2.8501169681549072,
644
+ "learning_rate": 1.4775193798449614e-05,
645
+ "loss": 0.1569,
646
+ "step": 2275
647
+ },
648
+ {
649
+ "epoch": 0.72,
650
+ "grad_norm": 0.6475769877433777,
651
+ "learning_rate": 1.4387596899224807e-05,
652
+ "loss": 0.1626,
653
+ "step": 2300
654
+ },
655
+ {
656
+ "epoch": 0.73,
657
+ "grad_norm": 3.125209093093872,
658
+ "learning_rate": 1.4000000000000001e-05,
659
+ "loss": 0.2249,
660
+ "step": 2325
661
+ },
662
+ {
663
+ "epoch": 0.74,
664
+ "grad_norm": 0.6424142718315125,
665
+ "learning_rate": 1.3612403100775195e-05,
666
+ "loss": 0.1583,
667
+ "step": 2350
668
+ },
669
+ {
670
+ "epoch": 0.74,
671
+ "grad_norm": 1.333817481994629,
672
+ "learning_rate": 1.3224806201550388e-05,
673
+ "loss": 0.1505,
674
+ "step": 2375
675
+ },
676
+ {
677
+ "epoch": 0.75,
678
+ "grad_norm": 0.30924907326698303,
679
+ "learning_rate": 1.283720930232558e-05,
680
+ "loss": 0.211,
681
+ "step": 2400
682
+ },
683
+ {
684
+ "epoch": 0.76,
685
+ "grad_norm": 0.9411177039146423,
686
+ "learning_rate": 1.2449612403100775e-05,
687
+ "loss": 0.1582,
688
+ "step": 2425
689
+ },
690
+ {
691
+ "epoch": 0.77,
692
+ "grad_norm": 0.6235800981521606,
693
+ "learning_rate": 1.206201550387597e-05,
694
+ "loss": 0.1762,
695
+ "step": 2450
696
+ },
697
+ {
698
+ "epoch": 0.78,
699
+ "grad_norm": 1.076593279838562,
700
+ "learning_rate": 1.1674418604651163e-05,
701
+ "loss": 0.2124,
702
+ "step": 2475
703
+ },
704
+ {
705
+ "epoch": 0.78,
706
+ "grad_norm": 1.0768756866455078,
707
+ "learning_rate": 1.1286821705426358e-05,
708
+ "loss": 0.2067,
709
+ "step": 2500
710
+ },
711
+ {
712
+ "epoch": 0.79,
713
+ "grad_norm": 1.3747373819351196,
714
+ "learning_rate": 1.089922480620155e-05,
715
+ "loss": 0.1959,
716
+ "step": 2525
717
+ },
718
+ {
719
+ "epoch": 0.8,
720
+ "grad_norm": 3.307833194732666,
721
+ "learning_rate": 1.0511627906976746e-05,
722
+ "loss": 0.2249,
723
+ "step": 2550
724
+ },
725
+ {
726
+ "epoch": 0.81,
727
+ "grad_norm": 1.8046529293060303,
728
+ "learning_rate": 1.0124031007751939e-05,
729
+ "loss": 0.1566,
730
+ "step": 2575
731
+ },
732
+ {
733
+ "epoch": 0.81,
734
+ "grad_norm": 1.890415072441101,
735
+ "learning_rate": 9.736434108527132e-06,
736
+ "loss": 0.1621,
737
+ "step": 2600
738
+ },
739
+ {
740
+ "epoch": 0.82,
741
+ "grad_norm": 1.755682110786438,
742
+ "learning_rate": 9.348837209302326e-06,
743
+ "loss": 0.202,
744
+ "step": 2625
745
+ },
746
+ {
747
+ "epoch": 0.83,
748
+ "grad_norm": 0.6612691879272461,
749
+ "learning_rate": 8.96124031007752e-06,
750
+ "loss": 0.1863,
751
+ "step": 2650
752
+ },
753
+ {
754
+ "epoch": 0.84,
755
+ "grad_norm": 2.275036334991455,
756
+ "learning_rate": 8.573643410852714e-06,
757
+ "loss": 0.173,
758
+ "step": 2675
759
+ },
760
+ {
761
+ "epoch": 0.85,
762
+ "grad_norm": 0.7513935565948486,
763
+ "learning_rate": 8.186046511627907e-06,
764
+ "loss": 0.1884,
765
+ "step": 2700
766
+ },
767
+ {
768
+ "epoch": 0.85,
769
+ "grad_norm": 1.9435423612594604,
770
+ "learning_rate": 7.798449612403102e-06,
771
+ "loss": 0.1795,
772
+ "step": 2725
773
+ },
774
+ {
775
+ "epoch": 0.86,
776
+ "grad_norm": 0.5520192384719849,
777
+ "learning_rate": 7.410852713178294e-06,
778
+ "loss": 0.1908,
779
+ "step": 2750
780
+ },
781
+ {
782
+ "epoch": 0.87,
783
+ "grad_norm": 2.2986812591552734,
784
+ "learning_rate": 7.023255813953489e-06,
785
+ "loss": 0.1767,
786
+ "step": 2775
787
+ },
788
+ {
789
+ "epoch": 0.88,
790
+ "grad_norm": 2.4153175354003906,
791
+ "learning_rate": 6.635658914728682e-06,
792
+ "loss": 0.2202,
793
+ "step": 2800
794
+ },
795
+ {
796
+ "epoch": 0.88,
797
+ "grad_norm": 2.7443273067474365,
798
+ "learning_rate": 6.2480620155038765e-06,
799
+ "loss": 0.1961,
800
+ "step": 2825
801
+ },
802
+ {
803
+ "epoch": 0.89,
804
+ "grad_norm": 5.525525093078613,
805
+ "learning_rate": 5.86046511627907e-06,
806
+ "loss": 0.1827,
807
+ "step": 2850
808
+ },
809
+ {
810
+ "epoch": 0.9,
811
+ "grad_norm": 2.7762510776519775,
812
+ "learning_rate": 5.472868217054264e-06,
813
+ "loss": 0.1816,
814
+ "step": 2875
815
+ },
816
+ {
817
+ "epoch": 0.91,
818
+ "grad_norm": 2.3923604488372803,
819
+ "learning_rate": 5.085271317829457e-06,
820
+ "loss": 0.1482,
821
+ "step": 2900
822
+ },
823
+ {
824
+ "epoch": 0.92,
825
+ "grad_norm": 0.8370789289474487,
826
+ "learning_rate": 4.697674418604651e-06,
827
+ "loss": 0.148,
828
+ "step": 2925
829
+ },
830
+ {
831
+ "epoch": 0.92,
832
+ "grad_norm": 2.383211374282837,
833
+ "learning_rate": 4.310077519379845e-06,
834
+ "loss": 0.1772,
835
+ "step": 2950
836
+ },
837
+ {
838
+ "epoch": 0.93,
839
+ "grad_norm": 0.5339698195457458,
840
+ "learning_rate": 3.922480620155039e-06,
841
+ "loss": 0.1409,
842
+ "step": 2975
843
+ },
844
+ {
845
+ "epoch": 0.94,
846
+ "grad_norm": 0.5133029222488403,
847
+ "learning_rate": 3.534883720930233e-06,
848
+ "loss": 0.1532,
849
+ "step": 3000
850
+ },
851
+ {
852
+ "epoch": 0.95,
853
+ "grad_norm": 3.2108466625213623,
854
+ "learning_rate": 3.1472868217054267e-06,
855
+ "loss": 0.1999,
856
+ "step": 3025
857
+ },
858
+ {
859
+ "epoch": 0.96,
860
+ "grad_norm": 3.6793041229248047,
861
+ "learning_rate": 2.7596899224806206e-06,
862
+ "loss": 0.1732,
863
+ "step": 3050
864
+ },
865
+ {
866
+ "epoch": 0.96,
867
+ "grad_norm": 2.0069997310638428,
868
+ "learning_rate": 2.372093023255814e-06,
869
+ "loss": 0.1839,
870
+ "step": 3075
871
+ },
872
+ {
873
+ "epoch": 0.97,
874
+ "grad_norm": 0.663833737373352,
875
+ "learning_rate": 1.984496124031008e-06,
876
+ "loss": 0.1928,
877
+ "step": 3100
878
+ },
879
+ {
880
+ "epoch": 0.98,
881
+ "grad_norm": 3.452453851699829,
882
+ "learning_rate": 1.5968992248062018e-06,
883
+ "loss": 0.1304,
884
+ "step": 3125
885
+ },
886
+ {
887
+ "epoch": 0.99,
888
+ "grad_norm": 0.8049046397209167,
889
+ "learning_rate": 1.2093023255813954e-06,
890
+ "loss": 0.1972,
891
+ "step": 3150
892
+ },
893
+ {
894
+ "epoch": 0.99,
895
+ "grad_norm": 0.5933910608291626,
896
+ "learning_rate": 8.217054263565891e-07,
897
+ "loss": 0.159,
898
+ "step": 3175
899
+ },
900
+ {
901
+ "epoch": 1.0,
902
+ "grad_norm": 0.493872731924057,
903
+ "learning_rate": 4.3410852713178294e-07,
904
+ "loss": 0.1212,
905
+ "step": 3200
906
+ },
907
+ {
908
+ "epoch": 1.01,
909
+ "grad_norm": 1.8325016498565674,
910
+ "learning_rate": 4.651162790697675e-08,
911
+ "loss": 0.1036,
912
+ "step": 3225
913
+ },
914
+ {
915
+ "epoch": 1.01,
916
+ "step": 3225,
917
+ "total_flos": 3.9986525216152166e+18,
918
+ "train_loss": 0.21891093194946762,
919
+ "train_runtime": 6427.7582,
920
+ "train_samples_per_second": 8.027,
921
+ "train_steps_per_second": 0.502
922
+ }
923
+ ],
924
+ "logging_steps": 25,
925
+ "max_steps": 3225,
926
+ "num_input_tokens_seen": 0,
927
+ "num_train_epochs": 2,
928
+ "save_steps": 100,
929
+ "total_flos": 3.9986525216152166e+18,
930
+ "train_batch_size": 16,
931
+ "trial_name": null,
932
+ "trial_params": null
933
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1e0dfc814cfabd6127b9e88a1c721614e5c078dfe219b442943b1d96bfddaec
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd676b490639b1dca7e5b0ed857e8abf242bd22491897d3fe80c447a8a1684c7
3
  size 4920