RoyJoy commited on
Commit
c935cad
1 Parent(s): bc6ed93

Training in progress, step 25, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "up_proj",
24
- "v_proj",
25
- "k_proj",
26
- "q_proj",
27
  "o_proj",
 
28
  "gate_proj",
29
- "down_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "down_proj",
 
 
 
24
  "o_proj",
25
+ "q_proj",
26
  "gate_proj",
27
+ "v_proj",
28
+ "up_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8dcb9945fd2ecc339300d7eb65ec9e47082058be8e3ebbce1272014eafb2c77
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05871106d1407279ac63bb11790465a32c6d0268478077c7e91ad61e40311586
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be6915a12df2e73267355ab954d70640023a55c33da733775466ca551d1c6422
3
  size 313998650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97108cdeefa3bd949029354831c39337f3105a2a73344a8a8c6d3adf57d1ddc2
3
  size 313998650
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4112ee8a6422fdbd6e1694f9b1995795231aac521ab49e0d6779f6e817558ada
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e7ffd21d4ac6af84faa735bb708c7cb611bd3f93cd0963ac7beed9897ecc97f
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acef140ba4152eb4a38c728bc2fb1a2ed40c789ab0bf8a1e0470ff59ce722fcc
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c238ecc6a33c59cde9927d4ce224799f96613807ec9a758597d2e5dc16623158
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcc5806ca90feb608fbd18278e484c5701038240bb6d44841334b3f4595e0dd9
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c76d2e03cbf5f30ab39aea2c49a2984e40e38fc2a61b8cd5c5ec4f568d4395
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:568c36d169057949eae8d99f612d9d37d3a243fd3f5417e617ff85dd15be5121
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7f14e3f98f3816a16e008995b43b512c2474657e7430d5bf55b81358295398
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0478220dc1c61b501af7edfe8fa4a46b7ebe1a2bbd0ae4d7514712a0c8b72900
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "best_metric": 0.12861138582229614,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.7204301075268817,
5
  "eval_steps": 25,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.017204301075268817,
13
- "grad_norm": 4.458132266998291,
14
  "learning_rate": 2e-05,
15
  "loss": 0.4272,
16
  "step": 1
@@ -18,735 +18,186 @@
18
  {
19
  "epoch": 0.017204301075268817,
20
  "eval_loss": 1.4783204793930054,
21
- "eval_runtime": 5.145,
22
- "eval_samples_per_second": 76.19,
23
- "eval_steps_per_second": 9.524,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.034408602150537634,
28
- "grad_norm": 6.990025997161865,
29
  "learning_rate": 4e-05,
30
  "loss": 0.6626,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.05161290322580645,
35
- "grad_norm": 7.760075092315674,
36
  "learning_rate": 6e-05,
37
- "loss": 0.6972,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.06881720430107527,
42
- "grad_norm": 4.424337387084961,
43
  "learning_rate": 8e-05,
44
- "loss": 0.4081,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.08602150537634409,
49
- "grad_norm": 3.306837797164917,
50
  "learning_rate": 0.0001,
51
- "loss": 0.3062,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.1032258064516129,
56
- "grad_norm": 1.8788976669311523,
57
  "learning_rate": 9.997266286704631e-05,
58
- "loss": 0.2261,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.12043010752688173,
63
- "grad_norm": 1.6426763534545898,
64
  "learning_rate": 9.989068136093873e-05,
65
- "loss": 0.2242,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.13763440860215054,
70
- "grad_norm": 0.9566802978515625,
71
  "learning_rate": 9.975414512725057e-05,
72
- "loss": 0.155,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.15483870967741936,
77
- "grad_norm": 0.9555782675743103,
78
  "learning_rate": 9.956320346634876e-05,
79
- "loss": 0.1778,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 0.17204301075268819,
84
- "grad_norm": 0.8017747402191162,
85
  "learning_rate": 9.931806517013612e-05,
86
- "loss": 0.1825,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.18924731182795698,
91
- "grad_norm": 0.958012044429779,
92
  "learning_rate": 9.901899829374047e-05,
93
- "loss": 0.2193,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.2064516129032258,
98
- "grad_norm": 0.8382191061973572,
99
  "learning_rate": 9.86663298624003e-05,
100
- "loss": 0.2093,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.22365591397849463,
105
- "grad_norm": 0.3560003638267517,
106
  "learning_rate": 9.826044551386744e-05,
107
- "loss": 0.0776,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.24086021505376345,
112
- "grad_norm": 0.4326319396495819,
113
  "learning_rate": 9.780178907671789e-05,
114
- "loss": 0.0718,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.25806451612903225,
119
- "grad_norm": 0.37284064292907715,
120
  "learning_rate": 9.729086208503174e-05,
121
- "loss": 0.0865,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.2752688172043011,
126
- "grad_norm": 0.5674258470535278,
127
  "learning_rate": 9.672822322997305e-05,
128
- "loss": 0.1066,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.2924731182795699,
133
- "grad_norm": 0.4691183269023895,
134
  "learning_rate": 9.611448774886924e-05,
135
- "loss": 0.0984,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.3096774193548387,
140
- "grad_norm": 0.4190113842487335,
141
  "learning_rate": 9.545032675245813e-05,
142
- "loss": 0.1101,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.32688172043010755,
147
- "grad_norm": 0.4916987419128418,
148
  "learning_rate": 9.473646649103818e-05,
149
- "loss": 0.1126,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.34408602150537637,
154
- "grad_norm": 0.5751784443855286,
155
  "learning_rate": 9.397368756032445e-05,
156
- "loss": 0.1253,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.36129032258064514,
161
- "grad_norm": 0.5716490149497986,
162
  "learning_rate": 9.316282404787871e-05,
163
- "loss": 0.1295,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 0.37849462365591396,
168
- "grad_norm": 0.5874112248420715,
169
  "learning_rate": 9.230476262104677e-05,
170
- "loss": 0.1434,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 0.3956989247311828,
175
- "grad_norm": 0.5886926054954529,
176
  "learning_rate": 9.140044155740101e-05,
177
- "loss": 0.1337,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 0.4129032258064516,
182
- "grad_norm": 0.7976363301277161,
183
  "learning_rate": 9.045084971874738e-05,
184
- "loss": 0.1757,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 0.43010752688172044,
189
- "grad_norm": 0.8777889609336853,
190
  "learning_rate": 8.945702546981969e-05,
191
- "loss": 0.2267,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 0.43010752688172044,
196
- "eval_loss": 0.1384161114692688,
197
- "eval_runtime": 5.1574,
198
- "eval_samples_per_second": 76.007,
199
- "eval_steps_per_second": 9.501,
200
  "step": 25
201
- },
202
- {
203
- "epoch": 0.44731182795698926,
204
- "grad_norm": 0.1694585084915161,
205
- "learning_rate": 8.842005554284296e-05,
206
- "loss": 0.045,
207
- "step": 26
208
- },
209
- {
210
- "epoch": 0.4645161290322581,
211
- "grad_norm": 0.2662329375743866,
212
- "learning_rate": 8.73410738492077e-05,
213
- "loss": 0.0663,
214
- "step": 27
215
- },
216
- {
217
- "epoch": 0.4817204301075269,
218
- "grad_norm": 0.376115083694458,
219
- "learning_rate": 8.622126023955446e-05,
220
- "loss": 0.0903,
221
- "step": 28
222
- },
223
- {
224
- "epoch": 0.4989247311827957,
225
- "grad_norm": 0.3713178336620331,
226
- "learning_rate": 8.506183921362443e-05,
227
- "loss": 0.0913,
228
- "step": 29
229
- },
230
- {
231
- "epoch": 0.5161290322580645,
232
- "grad_norm": 0.35013172030448914,
233
- "learning_rate": 8.386407858128706e-05,
234
- "loss": 0.0937,
235
- "step": 30
236
- },
237
- {
238
- "epoch": 0.5333333333333333,
239
- "grad_norm": 0.43744900822639465,
240
- "learning_rate": 8.262928807620843e-05,
241
- "loss": 0.104,
242
- "step": 31
243
- },
244
- {
245
- "epoch": 0.5505376344086022,
246
- "grad_norm": 0.4328308403491974,
247
- "learning_rate": 8.135881792367686e-05,
248
- "loss": 0.1082,
249
- "step": 32
250
- },
251
- {
252
- "epoch": 0.567741935483871,
253
- "grad_norm": 0.4831233322620392,
254
- "learning_rate": 8.005405736415126e-05,
255
- "loss": 0.1199,
256
- "step": 33
257
- },
258
- {
259
- "epoch": 0.5849462365591398,
260
- "grad_norm": 0.5026971101760864,
261
- "learning_rate": 7.871643313414718e-05,
262
- "loss": 0.1211,
263
- "step": 34
264
- },
265
- {
266
- "epoch": 0.6021505376344086,
267
- "grad_norm": 0.5438146591186523,
268
- "learning_rate": 7.734740790612136e-05,
269
- "loss": 0.1419,
270
- "step": 35
271
- },
272
- {
273
- "epoch": 0.6193548387096774,
274
- "grad_norm": 0.5357680320739746,
275
- "learning_rate": 7.594847868906076e-05,
276
- "loss": 0.1607,
277
- "step": 36
278
- },
279
- {
280
- "epoch": 0.6365591397849463,
281
- "grad_norm": 0.756168007850647,
282
- "learning_rate": 7.452117519152542e-05,
283
- "loss": 0.1972,
284
- "step": 37
285
- },
286
- {
287
- "epoch": 0.6537634408602151,
288
- "grad_norm": 0.2554115355014801,
289
- "learning_rate": 7.30670581489344e-05,
290
- "loss": 0.0644,
291
- "step": 38
292
- },
293
- {
294
- "epoch": 0.6709677419354839,
295
- "grad_norm": 0.20917977392673492,
296
- "learning_rate": 7.158771761692464e-05,
297
- "loss": 0.0535,
298
- "step": 39
299
- },
300
- {
301
- "epoch": 0.6881720430107527,
302
- "grad_norm": 0.23978161811828613,
303
- "learning_rate": 7.008477123264848e-05,
304
- "loss": 0.0679,
305
- "step": 40
306
- },
307
- {
308
- "epoch": 0.7053763440860215,
309
- "grad_norm": 0.27051109075546265,
310
- "learning_rate": 6.855986244591104e-05,
311
- "loss": 0.0797,
312
- "step": 41
313
- },
314
- {
315
- "epoch": 0.7225806451612903,
316
- "grad_norm": 0.2598600387573242,
317
- "learning_rate": 6.701465872208216e-05,
318
- "loss": 0.0822,
319
- "step": 42
320
- },
321
- {
322
- "epoch": 0.7397849462365591,
323
- "grad_norm": 0.35222598910331726,
324
- "learning_rate": 6.545084971874738e-05,
325
- "loss": 0.0945,
326
- "step": 43
327
- },
328
- {
329
- "epoch": 0.7569892473118279,
330
- "grad_norm": 0.38500919938087463,
331
- "learning_rate": 6.387014543809223e-05,
332
- "loss": 0.1059,
333
- "step": 44
334
- },
335
- {
336
- "epoch": 0.7741935483870968,
337
- "grad_norm": 0.3825439512729645,
338
- "learning_rate": 6.227427435703997e-05,
339
- "loss": 0.1103,
340
- "step": 45
341
- },
342
- {
343
- "epoch": 0.7913978494623656,
344
- "grad_norm": 0.42811131477355957,
345
- "learning_rate": 6.066498153718735e-05,
346
- "loss": 0.1171,
347
- "step": 46
348
- },
349
- {
350
- "epoch": 0.8086021505376344,
351
- "grad_norm": 0.5827885270118713,
352
- "learning_rate": 5.90440267166055e-05,
353
- "loss": 0.1313,
354
- "step": 47
355
- },
356
- {
357
- "epoch": 0.8258064516129032,
358
- "grad_norm": 0.4837743937969208,
359
- "learning_rate": 5.74131823855921e-05,
360
- "loss": 0.1533,
361
- "step": 48
362
- },
363
- {
364
- "epoch": 0.843010752688172,
365
- "grad_norm": 0.6008716225624084,
366
- "learning_rate": 5.577423184847932e-05,
367
- "loss": 0.1616,
368
- "step": 49
369
- },
370
- {
371
- "epoch": 0.8602150537634409,
372
- "grad_norm": 0.940000057220459,
373
- "learning_rate": 5.4128967273616625e-05,
374
- "loss": 0.2398,
375
- "step": 50
376
- },
377
- {
378
- "epoch": 0.8602150537634409,
379
- "eval_loss": 0.13495324552059174,
380
- "eval_runtime": 5.1573,
381
- "eval_samples_per_second": 76.008,
382
- "eval_steps_per_second": 9.501,
383
- "step": 50
384
- },
385
- {
386
- "epoch": 0.8774193548387097,
387
- "grad_norm": 0.17139974236488342,
388
- "learning_rate": 5.247918773366112e-05,
389
- "loss": 0.0471,
390
- "step": 51
391
- },
392
- {
393
- "epoch": 0.8946236559139785,
394
- "grad_norm": 0.22964441776275635,
395
- "learning_rate": 5.0826697238317935e-05,
396
- "loss": 0.0711,
397
- "step": 52
398
- },
399
- {
400
- "epoch": 0.9118279569892473,
401
- "grad_norm": 0.2772515118122101,
402
- "learning_rate": 4.917330276168208e-05,
403
- "loss": 0.0881,
404
- "step": 53
405
- },
406
- {
407
- "epoch": 0.9290322580645162,
408
- "grad_norm": 0.3522781431674957,
409
- "learning_rate": 4.7520812266338885e-05,
410
- "loss": 0.0997,
411
- "step": 54
412
- },
413
- {
414
- "epoch": 0.946236559139785,
415
- "grad_norm": 0.39684680104255676,
416
- "learning_rate": 4.5871032726383386e-05,
417
- "loss": 0.1097,
418
- "step": 55
419
- },
420
- {
421
- "epoch": 0.9634408602150538,
422
- "grad_norm": 0.4268311560153961,
423
- "learning_rate": 4.4225768151520694e-05,
424
- "loss": 0.1237,
425
- "step": 56
426
- },
427
- {
428
- "epoch": 0.9806451612903225,
429
- "grad_norm": 0.4827687740325928,
430
- "learning_rate": 4.2586817614407895e-05,
431
- "loss": 0.1565,
432
- "step": 57
433
- },
434
- {
435
- "epoch": 0.9978494623655914,
436
- "grad_norm": 0.6742030382156372,
437
- "learning_rate": 4.095597328339452e-05,
438
- "loss": 0.1891,
439
- "step": 58
440
- },
441
- {
442
- "epoch": 1.0150537634408603,
443
- "grad_norm": 1.1234270334243774,
444
- "learning_rate": 3.933501846281267e-05,
445
- "loss": 0.1136,
446
- "step": 59
447
- },
448
- {
449
- "epoch": 1.032258064516129,
450
- "grad_norm": 0.18411989510059357,
451
- "learning_rate": 3.772572564296005e-05,
452
- "loss": 0.0529,
453
- "step": 60
454
- },
455
- {
456
- "epoch": 1.049462365591398,
457
- "grad_norm": 0.2407916635274887,
458
- "learning_rate": 3.612985456190778e-05,
459
- "loss": 0.0628,
460
- "step": 61
461
- },
462
- {
463
- "epoch": 1.0666666666666667,
464
- "grad_norm": 0.22990457713603973,
465
- "learning_rate": 3.4549150281252636e-05,
466
- "loss": 0.0707,
467
- "step": 62
468
- },
469
- {
470
- "epoch": 1.0838709677419356,
471
- "grad_norm": 0.2655136287212372,
472
- "learning_rate": 3.298534127791785e-05,
473
- "loss": 0.073,
474
- "step": 63
475
- },
476
- {
477
- "epoch": 1.1010752688172043,
478
- "grad_norm": 0.27105939388275146,
479
- "learning_rate": 3.144013755408895e-05,
480
- "loss": 0.0723,
481
- "step": 64
482
- },
483
- {
484
- "epoch": 1.118279569892473,
485
- "grad_norm": 0.3270939290523529,
486
- "learning_rate": 2.991522876735154e-05,
487
- "loss": 0.0787,
488
- "step": 65
489
- },
490
- {
491
- "epoch": 1.135483870967742,
492
- "grad_norm": 0.3238106369972229,
493
- "learning_rate": 2.8412282383075363e-05,
494
- "loss": 0.0795,
495
- "step": 66
496
- },
497
- {
498
- "epoch": 1.1526881720430107,
499
- "grad_norm": 0.3283810317516327,
500
- "learning_rate": 2.693294185106562e-05,
501
- "loss": 0.089,
502
- "step": 67
503
- },
504
- {
505
- "epoch": 1.1698924731182796,
506
- "grad_norm": 0.4149152636528015,
507
- "learning_rate": 2.547882480847461e-05,
508
- "loss": 0.1118,
509
- "step": 68
510
- },
511
- {
512
- "epoch": 1.1870967741935483,
513
- "grad_norm": 0.39082080125808716,
514
- "learning_rate": 2.405152131093926e-05,
515
- "loss": 0.1163,
516
- "step": 69
517
- },
518
- {
519
- "epoch": 1.2043010752688172,
520
- "grad_norm": 0.45351719856262207,
521
- "learning_rate": 2.2652592093878666e-05,
522
- "loss": 0.1187,
523
- "step": 70
524
- },
525
- {
526
- "epoch": 1.221505376344086,
527
- "grad_norm": 0.24564394354820251,
528
- "learning_rate": 2.128356686585282e-05,
529
- "loss": 0.0572,
530
- "step": 71
531
- },
532
- {
533
- "epoch": 1.238709677419355,
534
- "grad_norm": 0.1709287464618683,
535
- "learning_rate": 1.9945942635848748e-05,
536
- "loss": 0.0471,
537
- "step": 72
538
- },
539
- {
540
- "epoch": 1.2559139784946236,
541
- "grad_norm": 0.21685582399368286,
542
- "learning_rate": 1.8641182076323148e-05,
543
- "loss": 0.0593,
544
- "step": 73
545
- },
546
- {
547
- "epoch": 1.2731182795698925,
548
- "grad_norm": 0.2916705310344696,
549
- "learning_rate": 1.7370711923791567e-05,
550
- "loss": 0.0674,
551
- "step": 74
552
- },
553
- {
554
- "epoch": 1.2903225806451613,
555
- "grad_norm": 0.2436515837907791,
556
- "learning_rate": 1.6135921418712956e-05,
557
- "loss": 0.0669,
558
- "step": 75
559
- },
560
- {
561
- "epoch": 1.2903225806451613,
562
- "eval_loss": 0.12913550436496735,
563
- "eval_runtime": 5.1492,
564
- "eval_samples_per_second": 76.128,
565
- "eval_steps_per_second": 9.516,
566
- "step": 75
567
- },
568
- {
569
- "epoch": 1.3075268817204302,
570
- "grad_norm": 0.28724661469459534,
571
- "learning_rate": 1.4938160786375572e-05,
572
- "loss": 0.0693,
573
- "step": 76
574
- },
575
- {
576
- "epoch": 1.324731182795699,
577
- "grad_norm": 0.30966466665267944,
578
- "learning_rate": 1.3778739760445552e-05,
579
- "loss": 0.0818,
580
- "step": 77
581
- },
582
- {
583
- "epoch": 1.3419354838709676,
584
- "grad_norm": 0.30045086145401,
585
- "learning_rate": 1.2658926150792322e-05,
586
- "loss": 0.0787,
587
- "step": 78
588
- },
589
- {
590
- "epoch": 1.3591397849462366,
591
- "grad_norm": 0.32244807481765747,
592
- "learning_rate": 1.157994445715706e-05,
593
- "loss": 0.0848,
594
- "step": 79
595
- },
596
- {
597
- "epoch": 1.3763440860215055,
598
- "grad_norm": 0.314584881067276,
599
- "learning_rate": 1.0542974530180327e-05,
600
- "loss": 0.0883,
601
- "step": 80
602
- },
603
- {
604
- "epoch": 1.3935483870967742,
605
- "grad_norm": 0.34502357244491577,
606
- "learning_rate": 9.549150281252633e-06,
607
- "loss": 0.0882,
608
- "step": 81
609
- },
610
- {
611
- "epoch": 1.410752688172043,
612
- "grad_norm": 0.43789923191070557,
613
- "learning_rate": 8.599558442598998e-06,
614
- "loss": 0.1093,
615
- "step": 82
616
- },
617
- {
618
- "epoch": 1.4279569892473118,
619
- "grad_norm": 0.5525321364402771,
620
- "learning_rate": 7.695237378953223e-06,
621
- "loss": 0.1309,
622
- "step": 83
623
- },
624
- {
625
- "epoch": 1.4451612903225808,
626
- "grad_norm": 0.28792673349380493,
627
- "learning_rate": 6.837175952121306e-06,
628
- "loss": 0.0488,
629
- "step": 84
630
- },
631
- {
632
- "epoch": 1.4623655913978495,
633
- "grad_norm": 0.20269066095352173,
634
- "learning_rate": 6.026312439675552e-06,
635
- "loss": 0.0516,
636
- "step": 85
637
- },
638
- {
639
- "epoch": 1.4795698924731182,
640
- "grad_norm": 0.2444780319929123,
641
- "learning_rate": 5.263533508961827e-06,
642
- "loss": 0.0632,
643
- "step": 86
644
- },
645
- {
646
- "epoch": 1.4967741935483871,
647
- "grad_norm": 0.27078327536582947,
648
- "learning_rate": 4.549673247541875e-06,
649
- "loss": 0.0694,
650
- "step": 87
651
- },
652
- {
653
- "epoch": 1.513978494623656,
654
- "grad_norm": 0.2688973844051361,
655
- "learning_rate": 3.885512251130763e-06,
656
- "loss": 0.0732,
657
- "step": 88
658
- },
659
- {
660
- "epoch": 1.5311827956989248,
661
- "grad_norm": 0.29662248492240906,
662
- "learning_rate": 3.271776770026963e-06,
663
- "loss": 0.0768,
664
- "step": 89
665
- },
666
- {
667
- "epoch": 1.5483870967741935,
668
- "grad_norm": 0.34857553243637085,
669
- "learning_rate": 2.7091379149682685e-06,
670
- "loss": 0.0868,
671
- "step": 90
672
- },
673
- {
674
- "epoch": 1.5655913978494622,
675
- "grad_norm": 0.3253614008426666,
676
- "learning_rate": 2.1982109232821178e-06,
677
- "loss": 0.0789,
678
- "step": 91
679
- },
680
- {
681
- "epoch": 1.5827956989247312,
682
- "grad_norm": 0.3459737002849579,
683
- "learning_rate": 1.7395544861325718e-06,
684
- "loss": 0.085,
685
- "step": 92
686
- },
687
- {
688
- "epoch": 1.6,
689
- "grad_norm": 0.3518889248371124,
690
- "learning_rate": 1.333670137599713e-06,
691
- "loss": 0.095,
692
- "step": 93
693
- },
694
- {
695
- "epoch": 1.6172043010752688,
696
- "grad_norm": 0.44837722182273865,
697
- "learning_rate": 9.810017062595322e-07,
698
- "loss": 0.1058,
699
- "step": 94
700
- },
701
- {
702
- "epoch": 1.6344086021505375,
703
- "grad_norm": 0.4785314202308655,
704
- "learning_rate": 6.819348298638839e-07,
705
- "loss": 0.113,
706
- "step": 95
707
- },
708
- {
709
- "epoch": 1.6516129032258065,
710
- "grad_norm": 0.21725249290466309,
711
- "learning_rate": 4.367965336512403e-07,
712
- "loss": 0.0481,
713
- "step": 96
714
- },
715
- {
716
- "epoch": 1.6688172043010754,
717
- "grad_norm": 0.16432440280914307,
718
- "learning_rate": 2.458548727494292e-07,
719
- "loss": 0.0433,
720
- "step": 97
721
- },
722
- {
723
- "epoch": 1.686021505376344,
724
- "grad_norm": 0.21126870810985565,
725
- "learning_rate": 1.0931863906127327e-07,
726
- "loss": 0.0511,
727
- "step": 98
728
- },
729
- {
730
- "epoch": 1.7032258064516128,
731
- "grad_norm": 0.2568517327308655,
732
- "learning_rate": 2.7337132953697554e-08,
733
- "loss": 0.069,
734
- "step": 99
735
- },
736
- {
737
- "epoch": 1.7204301075268817,
738
- "grad_norm": 0.3253111243247986,
739
- "learning_rate": 0.0,
740
- "loss": 0.0793,
741
- "step": 100
742
- },
743
- {
744
- "epoch": 1.7204301075268817,
745
- "eval_loss": 0.12861138582229614,
746
- "eval_runtime": 5.1532,
747
- "eval_samples_per_second": 76.069,
748
- "eval_steps_per_second": 9.509,
749
- "step": 100
750
  }
751
  ],
752
  "logging_steps": 1,
@@ -770,12 +221,12 @@
770
  "should_evaluate": false,
771
  "should_log": false,
772
  "should_save": true,
773
- "should_training_stop": true
774
  },
775
  "attributes": {}
776
  }
777
  },
778
- "total_flos": 3.178927560327168e+17,
779
  "train_batch_size": 2,
780
  "trial_name": null,
781
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.1376180797815323,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.43010752688172044,
5
  "eval_steps": 25,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.017204301075268817,
13
+ "grad_norm": 4.601269245147705,
14
  "learning_rate": 2e-05,
15
  "loss": 0.4272,
16
  "step": 1
 
18
  {
19
  "epoch": 0.017204301075268817,
20
  "eval_loss": 1.4783204793930054,
21
+ "eval_runtime": 5.1438,
22
+ "eval_samples_per_second": 76.208,
23
+ "eval_steps_per_second": 9.526,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.034408602150537634,
28
+ "grad_norm": 7.236650466918945,
29
  "learning_rate": 4e-05,
30
  "loss": 0.6626,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.05161290322580645,
35
+ "grad_norm": 7.9963555335998535,
36
  "learning_rate": 6e-05,
37
+ "loss": 0.6886,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.06881720430107527,
42
+ "grad_norm": 4.405614376068115,
43
  "learning_rate": 8e-05,
44
+ "loss": 0.4014,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.08602150537634409,
49
+ "grad_norm": 3.2208263874053955,
50
  "learning_rate": 0.0001,
51
+ "loss": 0.3021,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.1032258064516129,
56
+ "grad_norm": 1.8561677932739258,
57
  "learning_rate": 9.997266286704631e-05,
58
+ "loss": 0.2245,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.12043010752688173,
63
+ "grad_norm": 1.6137471199035645,
64
  "learning_rate": 9.989068136093873e-05,
65
+ "loss": 0.2223,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.13763440860215054,
70
+ "grad_norm": 0.9222277998924255,
71
  "learning_rate": 9.975414512725057e-05,
72
+ "loss": 0.1546,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.15483870967741936,
77
+ "grad_norm": 0.9431182146072388,
78
  "learning_rate": 9.956320346634876e-05,
79
+ "loss": 0.1754,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 0.17204301075268819,
84
+ "grad_norm": 0.7953192591667175,
85
  "learning_rate": 9.931806517013612e-05,
86
+ "loss": 0.1822,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.18924731182795698,
91
+ "grad_norm": 0.9455572366714478,
92
  "learning_rate": 9.901899829374047e-05,
93
+ "loss": 0.2185,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.2064516129032258,
98
+ "grad_norm": 0.8408288359642029,
99
  "learning_rate": 9.86663298624003e-05,
100
+ "loss": 0.2108,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.22365591397849463,
105
+ "grad_norm": 0.35438165068626404,
106
  "learning_rate": 9.826044551386744e-05,
107
+ "loss": 0.0773,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.24086021505376345,
112
+ "grad_norm": 0.42859965562820435,
113
  "learning_rate": 9.780178907671789e-05,
114
+ "loss": 0.0717,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.25806451612903225,
119
+ "grad_norm": 0.36290422081947327,
120
  "learning_rate": 9.729086208503174e-05,
121
+ "loss": 0.0868,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.2752688172043011,
126
+ "grad_norm": 0.5616369247436523,
127
  "learning_rate": 9.672822322997305e-05,
128
+ "loss": 0.1069,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.2924731182795699,
133
+ "grad_norm": 0.47484615445137024,
134
  "learning_rate": 9.611448774886924e-05,
135
+ "loss": 0.0989,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.3096774193548387,
140
+ "grad_norm": 0.4143848121166229,
141
  "learning_rate": 9.545032675245813e-05,
142
+ "loss": 0.11,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.32688172043010755,
147
+ "grad_norm": 0.49859318137168884,
148
  "learning_rate": 9.473646649103818e-05,
149
+ "loss": 0.114,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.34408602150537637,
154
+ "grad_norm": 0.5608797073364258,
155
  "learning_rate": 9.397368756032445e-05,
156
+ "loss": 0.1247,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.36129032258064514,
161
+ "grad_norm": 0.5681672096252441,
162
  "learning_rate": 9.316282404787871e-05,
163
+ "loss": 0.1305,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 0.37849462365591396,
168
+ "grad_norm": 0.5968943238258362,
169
  "learning_rate": 9.230476262104677e-05,
170
+ "loss": 0.1441,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 0.3956989247311828,
175
+ "grad_norm": 0.5786952376365662,
176
  "learning_rate": 9.140044155740101e-05,
177
+ "loss": 0.135,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 0.4129032258064516,
182
+ "grad_norm": 0.7746197581291199,
183
  "learning_rate": 9.045084971874738e-05,
184
+ "loss": 0.1746,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 0.43010752688172044,
189
+ "grad_norm": 0.9171465039253235,
190
  "learning_rate": 8.945702546981969e-05,
191
+ "loss": 0.2272,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 0.43010752688172044,
196
+ "eval_loss": 0.1376180797815323,
197
+ "eval_runtime": 5.1567,
198
+ "eval_samples_per_second": 76.018,
199
+ "eval_steps_per_second": 9.502,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
 
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
+ "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
+ "total_flos": 7.94731890081792e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1430955dec2173fb51d1a0e1a428a749a2c198d9ccb43582e217453a077583c4
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0fe48adcabb1d6f94577ee90c3fdba8a86bbc49d5aed11c616af37b904c1661
3
  size 6776