Namronaldo2004
commited on
Commit
·
9da66cf
1
Parent(s):
cbb0219
Update fine-tuned model
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +580 -405
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -23,13 +23,13 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"gate_proj",
|
27 |
"down_proj",
|
|
|
|
|
28 |
"v_proj",
|
29 |
-
"up_proj",
|
30 |
-
"o_proj",
|
31 |
"q_proj",
|
32 |
-
"
|
|
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
|
|
26 |
"down_proj",
|
27 |
+
"k_proj",
|
28 |
+
"gate_proj",
|
29 |
"v_proj",
|
|
|
|
|
30 |
"q_proj",
|
31 |
+
"up_proj",
|
32 |
+
"o_proj"
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 159967880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7590911661892e3c9392347ebda1de5380f253ffac55e85329e8a73e50b15cf
|
3 |
size 159967880
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 852876198
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36f202410c6d81593d68b1f21d20796871070444fabd294bacb88f27ee680fbe
|
3 |
size 852876198
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:809f3a6e13b93e710ea3d5ab2176d5175aca70d252bdab23bcb3fb5dd85b6047
|
3 |
size 14244
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25c0243da09e051ffbb600413baac079966a139cd6939cbef7eb321283bd0767
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -1,718 +1,893 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
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.
|
13 |
-
"grad_norm": 0.
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate":
|
22 |
-
"loss": 0.
|
23 |
"step": 2
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm": 0.
|
28 |
-
"learning_rate":
|
29 |
-
"loss": 0.
|
30 |
"step": 3
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 0.
|
34 |
-
"grad_norm": 0.
|
35 |
-
"learning_rate": 0.
|
36 |
-
"loss": 0.
|
37 |
"step": 4
|
38 |
},
|
39 |
{
|
40 |
-
"epoch": 0.
|
41 |
-
"grad_norm": 0.
|
42 |
-
"learning_rate": 0.
|
43 |
-
"loss": 0.
|
44 |
"step": 5
|
45 |
},
|
46 |
{
|
47 |
-
"epoch": 0.
|
48 |
-
"grad_norm": 0.
|
49 |
-
"learning_rate": 0.
|
50 |
-
"loss": 0.
|
51 |
"step": 6
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 0.
|
55 |
-
"grad_norm": 0.
|
56 |
-
"learning_rate": 0.
|
57 |
-
"loss": 0.
|
58 |
"step": 7
|
59 |
},
|
60 |
{
|
61 |
-
"epoch": 0.
|
62 |
-
"grad_norm": 0.
|
63 |
-
"learning_rate": 0.
|
64 |
-
"loss": 0.
|
65 |
"step": 8
|
66 |
},
|
67 |
{
|
68 |
-
"epoch": 0.
|
69 |
-
"grad_norm": 0.
|
70 |
-
"learning_rate": 0.
|
71 |
-
"loss": 0.
|
72 |
"step": 9
|
73 |
},
|
74 |
{
|
75 |
-
"epoch": 0.
|
76 |
-
"grad_norm": 0.
|
77 |
-
"learning_rate": 0.
|
78 |
-
"loss": 0.
|
79 |
"step": 10
|
80 |
},
|
81 |
{
|
82 |
-
"epoch": 0.
|
83 |
-
"grad_norm": 0.
|
84 |
-
"learning_rate": 0.
|
85 |
-
"loss": 0.
|
86 |
"step": 11
|
87 |
},
|
88 |
{
|
89 |
-
"epoch": 0.
|
90 |
-
"grad_norm": 0.
|
91 |
-
"learning_rate": 0.
|
92 |
-
"loss": 0.
|
93 |
"step": 12
|
94 |
},
|
95 |
{
|
96 |
-
"epoch": 0.
|
97 |
-
"grad_norm": 0.
|
98 |
-
"learning_rate": 0.
|
99 |
-
"loss": 0.
|
100 |
"step": 13
|
101 |
},
|
102 |
{
|
103 |
-
"epoch": 0.
|
104 |
-
"grad_norm": 0.
|
105 |
-
"learning_rate": 0.
|
106 |
-
"loss": 0.
|
107 |
"step": 14
|
108 |
},
|
109 |
{
|
110 |
-
"epoch": 0.
|
111 |
-
"grad_norm": 0.
|
112 |
-
"learning_rate": 0.
|
113 |
-
"loss": 0.
|
114 |
"step": 15
|
115 |
},
|
116 |
{
|
117 |
-
"epoch": 0.
|
118 |
-
"grad_norm": 0.
|
119 |
-
"learning_rate": 0.
|
120 |
-
"loss": 0.
|
121 |
"step": 16
|
122 |
},
|
123 |
{
|
124 |
-
"epoch": 0.
|
125 |
-
"grad_norm": 0.
|
126 |
-
"learning_rate": 0.
|
127 |
-
"loss": 0.
|
128 |
"step": 17
|
129 |
},
|
130 |
{
|
131 |
-
"epoch": 0.
|
132 |
-
"grad_norm": 0.
|
133 |
-
"learning_rate": 0.
|
134 |
-
"loss": 0.
|
135 |
"step": 18
|
136 |
},
|
137 |
{
|
138 |
-
"epoch": 0.
|
139 |
-
"grad_norm": 0.
|
140 |
-
"learning_rate": 0.
|
141 |
-
"loss": 0.
|
142 |
"step": 19
|
143 |
},
|
144 |
{
|
145 |
-
"epoch": 0.
|
146 |
-
"grad_norm": 0.
|
147 |
-
"learning_rate": 0.
|
148 |
-
"loss": 0.
|
149 |
"step": 20
|
150 |
},
|
151 |
{
|
152 |
-
"epoch": 0.
|
153 |
-
"grad_norm": 0.
|
154 |
-
"learning_rate": 0.
|
155 |
-
"loss": 0.
|
156 |
"step": 21
|
157 |
},
|
158 |
{
|
159 |
-
"epoch": 0.
|
160 |
-
"grad_norm": 0.
|
161 |
-
"learning_rate": 0.
|
162 |
-
"loss": 0.
|
163 |
"step": 22
|
164 |
},
|
165 |
{
|
166 |
-
"epoch": 0.
|
167 |
-
"grad_norm": 0.
|
168 |
-
"learning_rate": 0.
|
169 |
-
"loss": 0.
|
170 |
"step": 23
|
171 |
},
|
172 |
{
|
173 |
-
"epoch": 0.
|
174 |
-
"grad_norm": 0.
|
175 |
-
"learning_rate": 0.
|
176 |
-
"loss": 0.
|
177 |
"step": 24
|
178 |
},
|
179 |
{
|
180 |
-
"epoch": 0
|
181 |
-
"grad_norm": 0.
|
182 |
-
"learning_rate": 0.
|
183 |
-
"loss": 0.
|
184 |
"step": 25
|
185 |
},
|
186 |
{
|
187 |
-
"epoch":
|
188 |
-
"grad_norm": 0.
|
189 |
-
"learning_rate": 0.
|
190 |
-
"loss": 0.
|
191 |
"step": 26
|
192 |
},
|
193 |
{
|
194 |
-
"epoch":
|
195 |
-
"grad_norm": 0.
|
196 |
-
"learning_rate": 0.
|
197 |
-
"loss": 0.
|
198 |
"step": 27
|
199 |
},
|
200 |
{
|
201 |
-
"epoch":
|
202 |
-
"grad_norm": 0.
|
203 |
-
"learning_rate": 0.
|
204 |
-
"loss": 0.
|
205 |
"step": 28
|
206 |
},
|
207 |
{
|
208 |
-
"epoch":
|
209 |
-
"grad_norm": 0.
|
210 |
-
"learning_rate": 0.
|
211 |
-
"loss": 0.
|
212 |
"step": 29
|
213 |
},
|
214 |
{
|
215 |
-
"epoch":
|
216 |
-
"grad_norm": 0.
|
217 |
-
"learning_rate": 0.
|
218 |
-
"loss": 0.
|
219 |
"step": 30
|
220 |
},
|
221 |
{
|
222 |
-
"epoch":
|
223 |
-
"grad_norm": 0.
|
224 |
-
"learning_rate": 0.
|
225 |
-
"loss": 0.
|
226 |
"step": 31
|
227 |
},
|
228 |
{
|
229 |
-
"epoch":
|
230 |
-
"grad_norm": 0.
|
231 |
-
"learning_rate": 0.
|
232 |
-
"loss": 0.
|
233 |
"step": 32
|
234 |
},
|
235 |
{
|
236 |
-
"epoch":
|
237 |
-
"grad_norm": 0.
|
238 |
-
"learning_rate": 0.
|
239 |
-
"loss": 0.
|
240 |
"step": 33
|
241 |
},
|
242 |
{
|
243 |
-
"epoch":
|
244 |
-
"grad_norm": 0.
|
245 |
-
"learning_rate": 0.
|
246 |
-
"loss": 0.
|
247 |
"step": 34
|
248 |
},
|
249 |
{
|
250 |
-
"epoch":
|
251 |
-
"grad_norm": 0.
|
252 |
-
"learning_rate": 0.
|
253 |
-
"loss": 0.
|
254 |
"step": 35
|
255 |
},
|
256 |
{
|
257 |
-
"epoch":
|
258 |
-
"grad_norm": 0.
|
259 |
-
"learning_rate": 0.
|
260 |
-
"loss": 0.
|
261 |
"step": 36
|
262 |
},
|
263 |
{
|
264 |
-
"epoch":
|
265 |
-
"grad_norm": 0.
|
266 |
-
"learning_rate": 0.
|
267 |
-
"loss": 0.
|
268 |
"step": 37
|
269 |
},
|
270 |
{
|
271 |
-
"epoch":
|
272 |
-
"grad_norm": 0.
|
273 |
-
"learning_rate": 0.
|
274 |
-
"loss": 0.
|
275 |
"step": 38
|
276 |
},
|
277 |
{
|
278 |
-
"epoch":
|
279 |
-
"grad_norm": 0.
|
280 |
-
"learning_rate": 0.
|
281 |
-
"loss": 0.
|
282 |
"step": 39
|
283 |
},
|
284 |
{
|
285 |
-
"epoch":
|
286 |
-
"grad_norm": 0.
|
287 |
-
"learning_rate": 0.
|
288 |
-
"loss": 0.
|
289 |
"step": 40
|
290 |
},
|
291 |
{
|
292 |
-
"epoch":
|
293 |
-
"grad_norm": 0.
|
294 |
-
"learning_rate": 0.
|
295 |
-
"loss": 0.
|
296 |
"step": 41
|
297 |
},
|
298 |
{
|
299 |
-
"epoch":
|
300 |
-
"grad_norm": 0.
|
301 |
-
"learning_rate": 0.
|
302 |
-
"loss": 0.
|
303 |
"step": 42
|
304 |
},
|
305 |
{
|
306 |
-
"epoch":
|
307 |
-
"grad_norm": 0.
|
308 |
-
"learning_rate": 0.
|
309 |
-
"loss": 0.
|
310 |
"step": 43
|
311 |
},
|
312 |
{
|
313 |
-
"epoch":
|
314 |
-
"grad_norm": 0.
|
315 |
-
"learning_rate": 0.
|
316 |
-
"loss": 0.
|
317 |
"step": 44
|
318 |
},
|
319 |
{
|
320 |
-
"epoch":
|
321 |
-
"grad_norm": 0.
|
322 |
-
"learning_rate": 0.
|
323 |
-
"loss": 0.
|
324 |
"step": 45
|
325 |
},
|
326 |
{
|
327 |
-
"epoch":
|
328 |
-
"grad_norm": 0.
|
329 |
-
"learning_rate": 0.
|
330 |
-
"loss": 0.
|
331 |
"step": 46
|
332 |
},
|
333 |
{
|
334 |
-
"epoch":
|
335 |
-
"grad_norm": 0.
|
336 |
-
"learning_rate": 0.
|
337 |
-
"loss": 0.
|
338 |
"step": 47
|
339 |
},
|
340 |
{
|
341 |
-
"epoch":
|
342 |
-
"grad_norm": 0.
|
343 |
-
"learning_rate": 0.
|
344 |
-
"loss": 0.
|
345 |
"step": 48
|
346 |
},
|
347 |
{
|
348 |
-
"epoch":
|
349 |
-
"grad_norm": 0.
|
350 |
-
"learning_rate": 0.
|
351 |
-
"loss": 0.
|
352 |
"step": 49
|
353 |
},
|
354 |
{
|
355 |
-
"epoch": 0
|
356 |
-
"grad_norm": 0.
|
357 |
-
"learning_rate": 0.
|
358 |
-
"loss": 0.
|
359 |
"step": 50
|
360 |
},
|
361 |
{
|
362 |
-
"epoch":
|
363 |
-
"grad_norm": 0.
|
364 |
-
"learning_rate": 0.
|
365 |
-
"loss": 0.
|
366 |
"step": 51
|
367 |
},
|
368 |
{
|
369 |
-
"epoch":
|
370 |
-
"grad_norm": 0.
|
371 |
-
"learning_rate": 0.
|
372 |
-
"loss": 0.
|
373 |
"step": 52
|
374 |
},
|
375 |
{
|
376 |
-
"epoch":
|
377 |
-
"grad_norm": 0.
|
378 |
-
"learning_rate":
|
379 |
-
"loss": 0.
|
380 |
"step": 53
|
381 |
},
|
382 |
{
|
383 |
-
"epoch":
|
384 |
-
"grad_norm": 0.
|
385 |
-
"learning_rate":
|
386 |
-
"loss": 0.
|
387 |
"step": 54
|
388 |
},
|
389 |
{
|
390 |
-
"epoch":
|
391 |
-
"grad_norm": 0.
|
392 |
-
"learning_rate":
|
393 |
-
"loss": 0.
|
394 |
"step": 55
|
395 |
},
|
396 |
{
|
397 |
-
"epoch":
|
398 |
-
"grad_norm": 0.
|
399 |
-
"learning_rate":
|
400 |
-
"loss": 0.
|
401 |
"step": 56
|
402 |
},
|
403 |
{
|
404 |
-
"epoch":
|
405 |
-
"grad_norm": 0.
|
406 |
-
"learning_rate":
|
407 |
-
"loss": 0.
|
408 |
"step": 57
|
409 |
},
|
410 |
{
|
411 |
-
"epoch":
|
412 |
-
"grad_norm": 0.
|
413 |
-
"learning_rate":
|
414 |
-
"loss": 0.
|
415 |
"step": 58
|
416 |
},
|
417 |
{
|
418 |
-
"epoch":
|
419 |
-
"grad_norm": 0.
|
420 |
-
"learning_rate":
|
421 |
-
"loss": 0.
|
422 |
"step": 59
|
423 |
},
|
424 |
{
|
425 |
-
"epoch":
|
426 |
-
"grad_norm": 0.
|
427 |
-
"learning_rate":
|
428 |
-
"loss": 0.
|
429 |
"step": 60
|
430 |
},
|
431 |
{
|
432 |
-
"epoch":
|
433 |
-
"grad_norm": 0.
|
434 |
-
"learning_rate":
|
435 |
-
"loss": 0.
|
436 |
"step": 61
|
437 |
},
|
438 |
{
|
439 |
-
"epoch":
|
440 |
-
"grad_norm": 0.
|
441 |
-
"learning_rate":
|
442 |
-
"loss": 0.
|
443 |
"step": 62
|
444 |
},
|
445 |
{
|
446 |
-
"epoch":
|
447 |
-
"grad_norm": 0.
|
448 |
-
"learning_rate":
|
449 |
-
"loss": 0.
|
450 |
"step": 63
|
451 |
},
|
452 |
{
|
453 |
-
"epoch":
|
454 |
-
"grad_norm": 0.
|
455 |
-
"learning_rate":
|
456 |
-
"loss": 0.
|
457 |
"step": 64
|
458 |
},
|
459 |
{
|
460 |
-
"epoch":
|
461 |
-
"grad_norm": 0.
|
462 |
-
"learning_rate":
|
463 |
-
"loss": 0.
|
464 |
"step": 65
|
465 |
},
|
466 |
{
|
467 |
-
"epoch":
|
468 |
-
"grad_norm": 0.
|
469 |
-
"learning_rate":
|
470 |
-
"loss": 0.
|
471 |
"step": 66
|
472 |
},
|
473 |
{
|
474 |
-
"epoch":
|
475 |
-
"grad_norm": 0.
|
476 |
-
"learning_rate":
|
477 |
-
"loss": 0.
|
478 |
"step": 67
|
479 |
},
|
480 |
{
|
481 |
-
"epoch":
|
482 |
-
"grad_norm": 0.
|
483 |
-
"learning_rate":
|
484 |
-
"loss": 0.
|
485 |
"step": 68
|
486 |
},
|
487 |
{
|
488 |
-
"epoch":
|
489 |
-
"grad_norm": 0.
|
490 |
-
"learning_rate":
|
491 |
-
"loss": 0.
|
492 |
"step": 69
|
493 |
},
|
494 |
{
|
495 |
-
"epoch":
|
496 |
-
"grad_norm": 0.
|
497 |
-
"learning_rate":
|
498 |
-
"loss": 0.
|
499 |
"step": 70
|
500 |
},
|
501 |
{
|
502 |
-
"epoch":
|
503 |
-
"grad_norm": 0.
|
504 |
-
"learning_rate":
|
505 |
-
"loss": 0.
|
506 |
"step": 71
|
507 |
},
|
508 |
{
|
509 |
-
"epoch":
|
510 |
-
"grad_norm": 0.
|
511 |
-
"learning_rate":
|
512 |
-
"loss": 0.
|
513 |
"step": 72
|
514 |
},
|
515 |
{
|
516 |
-
"epoch":
|
517 |
-
"grad_norm": 0.
|
518 |
-
"learning_rate":
|
519 |
-
"loss": 0.
|
520 |
"step": 73
|
521 |
},
|
522 |
{
|
523 |
-
"epoch":
|
524 |
-
"grad_norm": 0.
|
525 |
-
"learning_rate":
|
526 |
-
"loss": 0.
|
527 |
"step": 74
|
528 |
},
|
529 |
{
|
530 |
-
"epoch": 0
|
531 |
-
"grad_norm": 0.
|
532 |
-
"learning_rate":
|
533 |
-
"loss": 0.
|
534 |
"step": 75
|
535 |
},
|
536 |
{
|
537 |
-
"epoch":
|
538 |
-
"grad_norm": 0.
|
539 |
-
"learning_rate":
|
540 |
-
"loss": 0.
|
541 |
"step": 76
|
542 |
},
|
543 |
{
|
544 |
-
"epoch":
|
545 |
-
"grad_norm": 0.
|
546 |
-
"learning_rate":
|
547 |
-
"loss": 0.
|
548 |
"step": 77
|
549 |
},
|
550 |
{
|
551 |
-
"epoch":
|
552 |
-
"grad_norm": 0.
|
553 |
-
"learning_rate":
|
554 |
-
"loss": 0.
|
555 |
"step": 78
|
556 |
},
|
557 |
{
|
558 |
-
"epoch":
|
559 |
-
"grad_norm": 0.
|
560 |
-
"learning_rate":
|
561 |
-
"loss": 0.
|
562 |
"step": 79
|
563 |
},
|
564 |
{
|
565 |
-
"epoch":
|
566 |
-
"grad_norm": 0.
|
567 |
-
"learning_rate":
|
568 |
-
"loss": 0.
|
569 |
"step": 80
|
570 |
},
|
571 |
{
|
572 |
-
"epoch":
|
573 |
-
"grad_norm": 0.
|
574 |
-
"learning_rate":
|
575 |
-
"loss": 0.
|
576 |
"step": 81
|
577 |
},
|
578 |
{
|
579 |
-
"epoch":
|
580 |
-
"grad_norm": 0.
|
581 |
-
"learning_rate":
|
582 |
-
"loss": 0.
|
583 |
"step": 82
|
584 |
},
|
585 |
{
|
586 |
-
"epoch":
|
587 |
-
"grad_norm": 0.
|
588 |
-
"learning_rate":
|
589 |
-
"loss": 0.
|
590 |
"step": 83
|
591 |
},
|
592 |
{
|
593 |
-
"epoch":
|
594 |
-
"grad_norm": 0.
|
595 |
-
"learning_rate":
|
596 |
-
"loss": 0.
|
597 |
"step": 84
|
598 |
},
|
599 |
{
|
600 |
-
"epoch":
|
601 |
-
"grad_norm": 0.
|
602 |
-
"learning_rate":
|
603 |
-
"loss": 0.
|
604 |
"step": 85
|
605 |
},
|
606 |
{
|
607 |
-
"epoch":
|
608 |
-
"grad_norm": 0.
|
609 |
-
"learning_rate":
|
610 |
-
"loss": 0.
|
611 |
"step": 86
|
612 |
},
|
613 |
{
|
614 |
-
"epoch":
|
615 |
-
"grad_norm": 0.
|
616 |
-
"learning_rate":
|
617 |
-
"loss": 0.
|
618 |
"step": 87
|
619 |
},
|
620 |
{
|
621 |
-
"epoch":
|
622 |
-
"grad_norm": 0.
|
623 |
-
"learning_rate":
|
624 |
-
"loss": 0.
|
625 |
"step": 88
|
626 |
},
|
627 |
{
|
628 |
-
"epoch":
|
629 |
-
"grad_norm": 0.
|
630 |
-
"learning_rate":
|
631 |
-
"loss": 0.
|
632 |
"step": 89
|
633 |
},
|
634 |
{
|
635 |
-
"epoch":
|
636 |
-
"grad_norm": 0.
|
637 |
-
"learning_rate":
|
638 |
-
"loss": 0.
|
639 |
"step": 90
|
640 |
},
|
641 |
{
|
642 |
-
"epoch":
|
643 |
-
"grad_norm": 0.
|
644 |
-
"learning_rate":
|
645 |
-
"loss": 0.
|
646 |
"step": 91
|
647 |
},
|
648 |
{
|
649 |
-
"epoch":
|
650 |
-
"grad_norm": 0.
|
651 |
-
"learning_rate": 3.
|
652 |
-
"loss": 0.
|
653 |
"step": 92
|
654 |
},
|
655 |
{
|
656 |
-
"epoch":
|
657 |
-
"grad_norm": 0.
|
658 |
-
"learning_rate":
|
659 |
-
"loss": 0.
|
660 |
"step": 93
|
661 |
},
|
662 |
{
|
663 |
-
"epoch":
|
664 |
-
"grad_norm": 0.
|
665 |
-
"learning_rate":
|
666 |
-
"loss": 0.
|
667 |
"step": 94
|
668 |
},
|
669 |
{
|
670 |
-
"epoch":
|
671 |
-
"grad_norm": 0.
|
672 |
-
"learning_rate":
|
673 |
-
"loss": 0.
|
674 |
"step": 95
|
675 |
},
|
676 |
{
|
677 |
-
"epoch":
|
678 |
-
"grad_norm": 0.
|
679 |
-
"learning_rate":
|
680 |
-
"loss": 0.
|
681 |
"step": 96
|
682 |
},
|
683 |
{
|
684 |
-
"epoch":
|
685 |
-
"grad_norm": 0.
|
686 |
-
"learning_rate":
|
687 |
-
"loss": 0.
|
688 |
"step": 97
|
689 |
},
|
690 |
{
|
691 |
-
"epoch":
|
692 |
-
"grad_norm": 0.
|
693 |
-
"learning_rate": 2.
|
694 |
-
"loss": 0.
|
695 |
"step": 98
|
696 |
},
|
697 |
{
|
698 |
-
"epoch":
|
699 |
-
"grad_norm": 0.
|
700 |
-
"learning_rate":
|
701 |
-
"loss": 0.
|
702 |
"step": 99
|
703 |
},
|
704 |
{
|
705 |
-
"epoch":
|
706 |
-
"grad_norm": 0.
|
707 |
-
"learning_rate":
|
708 |
-
"loss": 0.
|
709 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
710 |
}
|
711 |
],
|
712 |
"logging_steps": 1,
|
713 |
-
"max_steps":
|
714 |
"num_input_tokens_seen": 0,
|
715 |
-
"num_train_epochs":
|
716 |
"save_steps": 500,
|
717 |
"stateful_callbacks": {
|
718 |
"TrainerControl": {
|
@@ -726,7 +901,7 @@
|
|
726 |
"attributes": {}
|
727 |
}
|
728 |
},
|
729 |
-
"total_flos": 1.
|
730 |
"train_batch_size": 1,
|
731 |
"trial_name": null,
|
732 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 125,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"grad_norm": 0.5675837397575378,
|
14 |
+
"learning_rate": 2.857142857142857e-05,
|
15 |
+
"loss": 0.6417,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.08,
|
20 |
+
"grad_norm": 0.5383580923080444,
|
21 |
+
"learning_rate": 5.714285714285714e-05,
|
22 |
+
"loss": 0.6334,
|
23 |
"step": 2
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.12,
|
27 |
+
"grad_norm": 0.523246705532074,
|
28 |
+
"learning_rate": 8.571428571428571e-05,
|
29 |
+
"loss": 0.6413,
|
30 |
"step": 3
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.16,
|
34 |
+
"grad_norm": 0.4905203580856323,
|
35 |
+
"learning_rate": 0.00011428571428571428,
|
36 |
+
"loss": 0.665,
|
37 |
"step": 4
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 0.2,
|
41 |
+
"grad_norm": 0.5177513957023621,
|
42 |
+
"learning_rate": 0.00014285714285714287,
|
43 |
+
"loss": 0.6041,
|
44 |
"step": 5
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"grad_norm": 0.482448011636734,
|
49 |
+
"learning_rate": 0.00017142857142857143,
|
50 |
+
"loss": 0.6078,
|
51 |
"step": 6
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.28,
|
55 |
+
"grad_norm": 0.49536892771720886,
|
56 |
+
"learning_rate": 0.0002,
|
57 |
+
"loss": 0.6412,
|
58 |
"step": 7
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 0.32,
|
62 |
+
"grad_norm": 0.5152004361152649,
|
63 |
+
"learning_rate": 0.00019996456111234527,
|
64 |
+
"loss": 0.607,
|
65 |
"step": 8
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 0.36,
|
69 |
+
"grad_norm": 0.496277391910553,
|
70 |
+
"learning_rate": 0.0001998582695676762,
|
71 |
+
"loss": 0.6227,
|
72 |
"step": 9
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 0.4,
|
76 |
+
"grad_norm": 0.5162248611450195,
|
77 |
+
"learning_rate": 0.000199681200703075,
|
78 |
+
"loss": 0.6012,
|
79 |
"step": 10
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 0.44,
|
83 |
+
"grad_norm": 0.5029735565185547,
|
84 |
+
"learning_rate": 0.00019943348002101371,
|
85 |
+
"loss": 0.5842,
|
86 |
"step": 11
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 0.48,
|
90 |
+
"grad_norm": 0.5039064884185791,
|
91 |
+
"learning_rate": 0.00019911528310040074,
|
92 |
+
"loss": 0.5833,
|
93 |
"step": 12
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 0.52,
|
97 |
+
"grad_norm": 0.486408531665802,
|
98 |
+
"learning_rate": 0.00019872683547213446,
|
99 |
+
"loss": 0.57,
|
100 |
"step": 13
|
101 |
},
|
102 |
{
|
103 |
+
"epoch": 0.56,
|
104 |
+
"grad_norm": 0.48064252734184265,
|
105 |
+
"learning_rate": 0.00019826841245925212,
|
106 |
+
"loss": 0.5857,
|
107 |
"step": 14
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 0.6,
|
111 |
+
"grad_norm": 0.4762842655181885,
|
112 |
+
"learning_rate": 0.00019774033898178667,
|
113 |
+
"loss": 0.5434,
|
114 |
"step": 15
|
115 |
},
|
116 |
{
|
117 |
+
"epoch": 0.64,
|
118 |
+
"grad_norm": 0.4918793737888336,
|
119 |
+
"learning_rate": 0.00019714298932647098,
|
120 |
+
"loss": 0.5295,
|
121 |
"step": 16
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 0.68,
|
125 |
+
"grad_norm": 0.4949023425579071,
|
126 |
+
"learning_rate": 0.0001964767868814516,
|
127 |
+
"loss": 0.5382,
|
128 |
"step": 17
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 0.72,
|
132 |
+
"grad_norm": 0.4618944227695465,
|
133 |
+
"learning_rate": 0.00019574220383620055,
|
134 |
+
"loss": 0.517,
|
135 |
"step": 18
|
136 |
},
|
137 |
{
|
138 |
+
"epoch": 0.76,
|
139 |
+
"grad_norm": 0.4404259920120239,
|
140 |
+
"learning_rate": 0.00019493976084683813,
|
141 |
+
"loss": 0.5089,
|
142 |
"step": 19
|
143 |
},
|
144 |
{
|
145 |
+
"epoch": 0.8,
|
146 |
+
"grad_norm": 0.47014883160591125,
|
147 |
+
"learning_rate": 0.00019407002666710336,
|
148 |
+
"loss": 0.5412,
|
149 |
"step": 20
|
150 |
},
|
151 |
{
|
152 |
+
"epoch": 0.84,
|
153 |
+
"grad_norm": 0.49193090200424194,
|
154 |
+
"learning_rate": 0.00019313361774523385,
|
155 |
+
"loss": 0.5533,
|
156 |
"step": 21
|
157 |
},
|
158 |
{
|
159 |
+
"epoch": 0.88,
|
160 |
+
"grad_norm": 0.47287049889564514,
|
161 |
+
"learning_rate": 0.00019213119778704128,
|
162 |
+
"loss": 0.486,
|
163 |
"step": 22
|
164 |
},
|
165 |
{
|
166 |
+
"epoch": 0.92,
|
167 |
+
"grad_norm": 0.4395417273044586,
|
168 |
+
"learning_rate": 0.00019106347728549135,
|
169 |
+
"loss": 0.4964,
|
170 |
"step": 23
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 0.96,
|
174 |
+
"grad_norm": 0.4677005708217621,
|
175 |
+
"learning_rate": 0.00018993121301712193,
|
176 |
+
"loss": 0.5101,
|
177 |
"step": 24
|
178 |
},
|
179 |
{
|
180 |
+
"epoch": 1.0,
|
181 |
+
"grad_norm": 0.4530835449695587,
|
182 |
+
"learning_rate": 0.00018873520750565718,
|
183 |
+
"loss": 0.4903,
|
184 |
"step": 25
|
185 |
},
|
186 |
{
|
187 |
+
"epoch": 1.04,
|
188 |
+
"grad_norm": 0.41354307532310486,
|
189 |
+
"learning_rate": 0.00018747630845319612,
|
190 |
+
"loss": 0.3837,
|
191 |
"step": 26
|
192 |
},
|
193 |
{
|
194 |
+
"epoch": 1.08,
|
195 |
+
"grad_norm": 0.4053184986114502,
|
196 |
+
"learning_rate": 0.0001861554081393806,
|
197 |
+
"loss": 0.3586,
|
198 |
"step": 27
|
199 |
},
|
200 |
{
|
201 |
+
"epoch": 1.12,
|
202 |
+
"grad_norm": 0.39625370502471924,
|
203 |
+
"learning_rate": 0.0001847734427889671,
|
204 |
+
"loss": 0.3408,
|
205 |
"step": 28
|
206 |
},
|
207 |
{
|
208 |
+
"epoch": 1.16,
|
209 |
+
"grad_norm": 0.3945152759552002,
|
210 |
+
"learning_rate": 0.0001833313919082515,
|
211 |
+
"loss": 0.3329,
|
212 |
"step": 29
|
213 |
},
|
214 |
{
|
215 |
+
"epoch": 1.2,
|
216 |
+
"grad_norm": 0.45374399423599243,
|
217 |
+
"learning_rate": 0.0001818302775908169,
|
218 |
+
"loss": 0.3273,
|
219 |
"step": 30
|
220 |
},
|
221 |
{
|
222 |
+
"epoch": 1.24,
|
223 |
+
"grad_norm": 0.44107717275619507,
|
224 |
+
"learning_rate": 0.00018027116379309638,
|
225 |
+
"loss": 0.3397,
|
226 |
"step": 31
|
227 |
},
|
228 |
{
|
229 |
+
"epoch": 1.28,
|
230 |
+
"grad_norm": 0.46182313561439514,
|
231 |
+
"learning_rate": 0.00017865515558026428,
|
232 |
+
"loss": 0.3439,
|
233 |
"step": 32
|
234 |
},
|
235 |
{
|
236 |
+
"epoch": 1.32,
|
237 |
+
"grad_norm": 0.4914720356464386,
|
238 |
+
"learning_rate": 0.00017698339834299061,
|
239 |
+
"loss": 0.3415,
|
240 |
"step": 33
|
241 |
},
|
242 |
{
|
243 |
+
"epoch": 1.3599999999999999,
|
244 |
+
"grad_norm": 0.46283280849456787,
|
245 |
+
"learning_rate": 0.00017525707698561385,
|
246 |
+
"loss": 0.3309,
|
247 |
"step": 34
|
248 |
},
|
249 |
{
|
250 |
+
"epoch": 1.4,
|
251 |
+
"grad_norm": 0.47037574648857117,
|
252 |
+
"learning_rate": 0.00017347741508630672,
|
253 |
+
"loss": 0.3311,
|
254 |
"step": 35
|
255 |
},
|
256 |
{
|
257 |
+
"epoch": 1.44,
|
258 |
+
"grad_norm": 0.4362049102783203,
|
259 |
+
"learning_rate": 0.00017164567402983152,
|
260 |
+
"loss": 0.3185,
|
261 |
"step": 36
|
262 |
},
|
263 |
{
|
264 |
+
"epoch": 1.48,
|
265 |
+
"grad_norm": 0.4418430030345917,
|
266 |
+
"learning_rate": 0.0001697631521134985,
|
267 |
+
"loss": 0.3189,
|
268 |
"step": 37
|
269 |
},
|
270 |
{
|
271 |
+
"epoch": 1.52,
|
272 |
+
"grad_norm": 0.4334975779056549,
|
273 |
+
"learning_rate": 0.00016783118362696163,
|
274 |
+
"loss": 0.3152,
|
275 |
"step": 38
|
276 |
},
|
277 |
{
|
278 |
+
"epoch": 1.56,
|
279 |
+
"grad_norm": 0.42978766560554504,
|
280 |
+
"learning_rate": 0.00016585113790650388,
|
281 |
+
"loss": 0.3302,
|
282 |
"step": 39
|
283 |
},
|
284 |
{
|
285 |
+
"epoch": 1.6,
|
286 |
+
"grad_norm": 0.4448607563972473,
|
287 |
+
"learning_rate": 0.00016382441836448202,
|
288 |
+
"loss": 0.3311,
|
289 |
"step": 40
|
290 |
},
|
291 |
{
|
292 |
+
"epoch": 1.6400000000000001,
|
293 |
+
"grad_norm": 0.40594780445098877,
|
294 |
+
"learning_rate": 0.0001617524614946192,
|
295 |
+
"loss": 0.326,
|
296 |
"step": 41
|
297 |
},
|
298 |
{
|
299 |
+
"epoch": 1.6800000000000002,
|
300 |
+
"grad_norm": 0.4091069996356964,
|
301 |
+
"learning_rate": 0.00015963673585385016,
|
302 |
+
"loss": 0.3374,
|
303 |
"step": 42
|
304 |
},
|
305 |
{
|
306 |
+
"epoch": 1.72,
|
307 |
+
"grad_norm": 0.42589232325553894,
|
308 |
+
"learning_rate": 0.0001574787410214407,
|
309 |
+
"loss": 0.3228,
|
310 |
"step": 43
|
311 |
},
|
312 |
{
|
313 |
+
"epoch": 1.76,
|
314 |
+
"grad_norm": 0.413335919380188,
|
315 |
+
"learning_rate": 0.00015528000653611935,
|
316 |
+
"loss": 0.3234,
|
317 |
"step": 44
|
318 |
},
|
319 |
{
|
320 |
+
"epoch": 1.8,
|
321 |
+
"grad_norm": 0.44703832268714905,
|
322 |
+
"learning_rate": 0.00015304209081197425,
|
323 |
+
"loss": 0.3352,
|
324 |
"step": 45
|
325 |
},
|
326 |
{
|
327 |
+
"epoch": 1.8399999999999999,
|
328 |
+
"grad_norm": 0.42445358633995056,
|
329 |
+
"learning_rate": 0.000150766580033884,
|
330 |
+
"loss": 0.3429,
|
331 |
"step": 46
|
332 |
},
|
333 |
{
|
334 |
+
"epoch": 1.88,
|
335 |
+
"grad_norm": 0.39593955874443054,
|
336 |
+
"learning_rate": 0.00014845508703326504,
|
337 |
+
"loss": 0.3247,
|
338 |
"step": 47
|
339 |
},
|
340 |
{
|
341 |
+
"epoch": 1.92,
|
342 |
+
"grad_norm": 0.40969106554985046,
|
343 |
+
"learning_rate": 0.0001461092501449326,
|
344 |
+
"loss": 0.3126,
|
345 |
"step": 48
|
346 |
},
|
347 |
{
|
348 |
+
"epoch": 1.96,
|
349 |
+
"grad_norm": 0.4226933717727661,
|
350 |
+
"learning_rate": 0.00014373073204588556,
|
351 |
+
"loss": 0.3184,
|
352 |
"step": 49
|
353 |
},
|
354 |
{
|
355 |
+
"epoch": 2.0,
|
356 |
+
"grad_norm": 0.4182460308074951,
|
357 |
+
"learning_rate": 0.00014132121857683783,
|
358 |
+
"loss": 0.3263,
|
359 |
"step": 50
|
360 |
},
|
361 |
{
|
362 |
+
"epoch": 2.04,
|
363 |
+
"grad_norm": 0.3583109676837921,
|
364 |
+
"learning_rate": 0.00013888241754733208,
|
365 |
+
"loss": 0.2484,
|
366 |
"step": 51
|
367 |
},
|
368 |
{
|
369 |
+
"epoch": 2.08,
|
370 |
+
"grad_norm": 0.3850906491279602,
|
371 |
+
"learning_rate": 0.00013641605752528224,
|
372 |
+
"loss": 0.24,
|
373 |
"step": 52
|
374 |
},
|
375 |
{
|
376 |
+
"epoch": 2.12,
|
377 |
+
"grad_norm": 0.3770233392715454,
|
378 |
+
"learning_rate": 0.00013392388661180303,
|
379 |
+
"loss": 0.2334,
|
380 |
"step": 53
|
381 |
},
|
382 |
{
|
383 |
+
"epoch": 2.16,
|
384 |
+
"grad_norm": 0.374737024307251,
|
385 |
+
"learning_rate": 0.0001314076712021949,
|
386 |
+
"loss": 0.244,
|
387 |
"step": 54
|
388 |
},
|
389 |
{
|
390 |
+
"epoch": 2.2,
|
391 |
+
"grad_norm": 0.37868672609329224,
|
392 |
+
"learning_rate": 0.0001288691947339621,
|
393 |
+
"loss": 0.2134,
|
394 |
"step": 55
|
395 |
},
|
396 |
{
|
397 |
+
"epoch": 2.24,
|
398 |
+
"grad_norm": 0.41098785400390625,
|
399 |
+
"learning_rate": 0.00012631025642275212,
|
400 |
+
"loss": 0.2373,
|
401 |
"step": 56
|
402 |
},
|
403 |
{
|
404 |
+
"epoch": 2.2800000000000002,
|
405 |
+
"grad_norm": 0.3870932161808014,
|
406 |
+
"learning_rate": 0.0001237326699871115,
|
407 |
+
"loss": 0.2238,
|
408 |
"step": 57
|
409 |
},
|
410 |
{
|
411 |
+
"epoch": 2.32,
|
412 |
+
"grad_norm": 0.4083153307437897,
|
413 |
+
"learning_rate": 0.00012113826236296244,
|
414 |
+
"loss": 0.2141,
|
415 |
"step": 58
|
416 |
},
|
417 |
{
|
418 |
+
"epoch": 2.36,
|
419 |
+
"grad_norm": 0.412580668926239,
|
420 |
+
"learning_rate": 0.00011852887240871145,
|
421 |
+
"loss": 0.2201,
|
422 |
"step": 59
|
423 |
},
|
424 |
{
|
425 |
+
"epoch": 2.4,
|
426 |
+
"grad_norm": 0.4499835968017578,
|
427 |
+
"learning_rate": 0.00011590634960190721,
|
428 |
+
"loss": 0.2215,
|
429 |
"step": 60
|
430 |
},
|
431 |
{
|
432 |
+
"epoch": 2.44,
|
433 |
+
"grad_norm": 0.48053982853889465,
|
434 |
+
"learning_rate": 0.00011327255272837221,
|
435 |
+
"loss": 0.217,
|
436 |
"step": 61
|
437 |
},
|
438 |
{
|
439 |
+
"epoch": 2.48,
|
440 |
+
"grad_norm": 0.44269296526908875,
|
441 |
+
"learning_rate": 0.00011062934856473655,
|
442 |
+
"loss": 0.2212,
|
443 |
"step": 62
|
444 |
},
|
445 |
{
|
446 |
+
"epoch": 2.52,
|
447 |
+
"grad_norm": 0.4232514202594757,
|
448 |
+
"learning_rate": 0.00010797861055530831,
|
449 |
+
"loss": 0.2289,
|
450 |
"step": 63
|
451 |
},
|
452 |
{
|
453 |
+
"epoch": 2.56,
|
454 |
+
"grad_norm": 0.41652482748031616,
|
455 |
+
"learning_rate": 0.00010532221748421787,
|
456 |
+
"loss": 0.2098,
|
457 |
"step": 64
|
458 |
},
|
459 |
{
|
460 |
+
"epoch": 2.6,
|
461 |
+
"grad_norm": 0.39650851488113403,
|
462 |
+
"learning_rate": 0.00010266205214377748,
|
463 |
+
"loss": 0.195,
|
464 |
"step": 65
|
465 |
},
|
466 |
{
|
467 |
+
"epoch": 2.64,
|
468 |
+
"grad_norm": 0.39610394835472107,
|
469 |
+
"learning_rate": 0.0001,
|
470 |
+
"loss": 0.1996,
|
471 |
"step": 66
|
472 |
},
|
473 |
{
|
474 |
+
"epoch": 2.68,
|
475 |
+
"grad_norm": 0.3933280110359192,
|
476 |
+
"learning_rate": 9.733794785622253e-05,
|
477 |
+
"loss": 0.2243,
|
478 |
"step": 67
|
479 |
},
|
480 |
{
|
481 |
+
"epoch": 2.7199999999999998,
|
482 |
+
"grad_norm": 0.3946898579597473,
|
483 |
+
"learning_rate": 9.467778251578217e-05,
|
484 |
+
"loss": 0.2216,
|
485 |
"step": 68
|
486 |
},
|
487 |
{
|
488 |
+
"epoch": 2.76,
|
489 |
+
"grad_norm": 0.4111415147781372,
|
490 |
+
"learning_rate": 9.202138944469168e-05,
|
491 |
+
"loss": 0.2261,
|
492 |
"step": 69
|
493 |
},
|
494 |
{
|
495 |
+
"epoch": 2.8,
|
496 |
+
"grad_norm": 0.4122645854949951,
|
497 |
+
"learning_rate": 8.937065143526347e-05,
|
498 |
+
"loss": 0.226,
|
499 |
"step": 70
|
500 |
},
|
501 |
{
|
502 |
+
"epoch": 2.84,
|
503 |
+
"grad_norm": 0.4040912091732025,
|
504 |
+
"learning_rate": 8.672744727162781e-05,
|
505 |
+
"loss": 0.2397,
|
506 |
"step": 71
|
507 |
},
|
508 |
{
|
509 |
+
"epoch": 2.88,
|
510 |
+
"grad_norm": 0.4039236605167389,
|
511 |
+
"learning_rate": 8.409365039809281e-05,
|
512 |
+
"loss": 0.214,
|
513 |
"step": 72
|
514 |
},
|
515 |
{
|
516 |
+
"epoch": 2.92,
|
517 |
+
"grad_norm": 0.39346644282341003,
|
518 |
+
"learning_rate": 8.147112759128859e-05,
|
519 |
+
"loss": 0.2211,
|
520 |
"step": 73
|
521 |
},
|
522 |
{
|
523 |
+
"epoch": 2.96,
|
524 |
+
"grad_norm": 0.4206030070781708,
|
525 |
+
"learning_rate": 7.886173763703757e-05,
|
526 |
+
"loss": 0.2193,
|
527 |
"step": 74
|
528 |
},
|
529 |
{
|
530 |
+
"epoch": 3.0,
|
531 |
+
"grad_norm": 0.3998810648918152,
|
532 |
+
"learning_rate": 7.626733001288851e-05,
|
533 |
+
"loss": 0.2129,
|
534 |
"step": 75
|
535 |
},
|
536 |
{
|
537 |
+
"epoch": 3.04,
|
538 |
+
"grad_norm": 0.3447999060153961,
|
539 |
+
"learning_rate": 7.368974357724789e-05,
|
540 |
+
"loss": 0.1809,
|
541 |
"step": 76
|
542 |
},
|
543 |
{
|
544 |
+
"epoch": 3.08,
|
545 |
+
"grad_norm": 0.3176288306713104,
|
546 |
+
"learning_rate": 7.113080526603792e-05,
|
547 |
+
"loss": 0.1648,
|
548 |
"step": 77
|
549 |
},
|
550 |
{
|
551 |
+
"epoch": 3.12,
|
552 |
+
"grad_norm": 0.32004985213279724,
|
553 |
+
"learning_rate": 6.859232879780515e-05,
|
554 |
+
"loss": 0.1582,
|
555 |
"step": 78
|
556 |
},
|
557 |
{
|
558 |
+
"epoch": 3.16,
|
559 |
+
"grad_norm": 0.31019288301467896,
|
560 |
+
"learning_rate": 6.607611338819697e-05,
|
561 |
+
"loss": 0.1502,
|
562 |
"step": 79
|
563 |
},
|
564 |
{
|
565 |
+
"epoch": 3.2,
|
566 |
+
"grad_norm": 0.31684502959251404,
|
567 |
+
"learning_rate": 6.358394247471778e-05,
|
568 |
+
"loss": 0.1514,
|
569 |
"step": 80
|
570 |
},
|
571 |
{
|
572 |
+
"epoch": 3.24,
|
573 |
+
"grad_norm": 0.3580498695373535,
|
574 |
+
"learning_rate": 6.111758245266794e-05,
|
575 |
+
"loss": 0.1533,
|
576 |
"step": 81
|
577 |
},
|
578 |
{
|
579 |
+
"epoch": 3.2800000000000002,
|
580 |
+
"grad_norm": 0.3377327024936676,
|
581 |
+
"learning_rate": 5.867878142316221e-05,
|
582 |
+
"loss": 0.1522,
|
583 |
"step": 82
|
584 |
},
|
585 |
{
|
586 |
+
"epoch": 3.32,
|
587 |
+
"grad_norm": 0.36469805240631104,
|
588 |
+
"learning_rate": 5.626926795411447e-05,
|
589 |
+
"loss": 0.1625,
|
590 |
"step": 83
|
591 |
},
|
592 |
{
|
593 |
+
"epoch": 3.36,
|
594 |
+
"grad_norm": 0.3576640486717224,
|
595 |
+
"learning_rate": 5.38907498550674e-05,
|
596 |
+
"loss": 0.1491,
|
597 |
"step": 84
|
598 |
},
|
599 |
{
|
600 |
+
"epoch": 3.4,
|
601 |
+
"grad_norm": 0.36043015122413635,
|
602 |
+
"learning_rate": 5.1544912966734994e-05,
|
603 |
+
"loss": 0.1561,
|
604 |
"step": 85
|
605 |
},
|
606 |
{
|
607 |
+
"epoch": 3.44,
|
608 |
+
"grad_norm": 0.3925049602985382,
|
609 |
+
"learning_rate": 4.9233419966116036e-05,
|
610 |
+
"loss": 0.1526,
|
611 |
"step": 86
|
612 |
},
|
613 |
{
|
614 |
+
"epoch": 3.48,
|
615 |
+
"grad_norm": 0.3896467685699463,
|
616 |
+
"learning_rate": 4.695790918802576e-05,
|
617 |
+
"loss": 0.1626,
|
618 |
"step": 87
|
619 |
},
|
620 |
{
|
621 |
+
"epoch": 3.52,
|
622 |
+
"grad_norm": 0.38003793358802795,
|
623 |
+
"learning_rate": 4.47199934638807e-05,
|
624 |
+
"loss": 0.1483,
|
625 |
"step": 88
|
626 |
},
|
627 |
{
|
628 |
+
"epoch": 3.56,
|
629 |
+
"grad_norm": 0.3852701187133789,
|
630 |
+
"learning_rate": 4.252125897855932e-05,
|
631 |
+
"loss": 0.1494,
|
632 |
"step": 89
|
633 |
},
|
634 |
{
|
635 |
+
"epoch": 3.6,
|
636 |
+
"grad_norm": 0.38289740681648254,
|
637 |
+
"learning_rate": 4.036326414614985e-05,
|
638 |
+
"loss": 0.1694,
|
639 |
"step": 90
|
640 |
},
|
641 |
{
|
642 |
+
"epoch": 3.64,
|
643 |
+
"grad_norm": 0.3584575057029724,
|
644 |
+
"learning_rate": 3.824753850538082e-05,
|
645 |
+
"loss": 0.1581,
|
646 |
"step": 91
|
647 |
},
|
648 |
{
|
649 |
+
"epoch": 3.68,
|
650 |
+
"grad_norm": 0.36479833722114563,
|
651 |
+
"learning_rate": 3.617558163551802e-05,
|
652 |
+
"loss": 0.1567,
|
653 |
"step": 92
|
654 |
},
|
655 |
{
|
656 |
+
"epoch": 3.7199999999999998,
|
657 |
+
"grad_norm": 0.3648757338523865,
|
658 |
+
"learning_rate": 3.414886209349615e-05,
|
659 |
+
"loss": 0.1539,
|
660 |
"step": 93
|
661 |
},
|
662 |
{
|
663 |
+
"epoch": 3.76,
|
664 |
+
"grad_norm": 0.3735385835170746,
|
665 |
+
"learning_rate": 3.216881637303839e-05,
|
666 |
+
"loss": 0.1455,
|
667 |
"step": 94
|
668 |
},
|
669 |
{
|
670 |
+
"epoch": 3.8,
|
671 |
+
"grad_norm": 0.3788692355155945,
|
672 |
+
"learning_rate": 3.0236847886501542e-05,
|
673 |
+
"loss": 0.1512,
|
674 |
"step": 95
|
675 |
},
|
676 |
{
|
677 |
+
"epoch": 3.84,
|
678 |
+
"grad_norm": 0.36534735560417175,
|
679 |
+
"learning_rate": 2.8354325970168484e-05,
|
680 |
+
"loss": 0.1539,
|
681 |
"step": 96
|
682 |
},
|
683 |
{
|
684 |
+
"epoch": 3.88,
|
685 |
+
"grad_norm": 0.3561382591724396,
|
686 |
+
"learning_rate": 2.6522584913693294e-05,
|
687 |
+
"loss": 0.1613,
|
688 |
"step": 97
|
689 |
},
|
690 |
{
|
691 |
+
"epoch": 3.92,
|
692 |
+
"grad_norm": 0.36043405532836914,
|
693 |
+
"learning_rate": 2.4742923014386156e-05,
|
694 |
+
"loss": 0.1399,
|
695 |
"step": 98
|
696 |
},
|
697 |
{
|
698 |
+
"epoch": 3.96,
|
699 |
+
"grad_norm": 0.3461771011352539,
|
700 |
+
"learning_rate": 2.301660165700936e-05,
|
701 |
+
"loss": 0.1446,
|
702 |
"step": 99
|
703 |
},
|
704 |
{
|
705 |
+
"epoch": 4.0,
|
706 |
+
"grad_norm": 0.3610660135746002,
|
707 |
+
"learning_rate": 2.1344844419735755e-05,
|
708 |
+
"loss": 0.1669,
|
709 |
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 4.04,
|
713 |
+
"grad_norm": 0.3192867636680603,
|
714 |
+
"learning_rate": 1.9728836206903656e-05,
|
715 |
+
"loss": 0.138,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 4.08,
|
720 |
+
"grad_norm": 0.2961142957210541,
|
721 |
+
"learning_rate": 1.8169722409183097e-05,
|
722 |
+
"loss": 0.1251,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 4.12,
|
727 |
+
"grad_norm": 0.33224716782569885,
|
728 |
+
"learning_rate": 1.6668608091748495e-05,
|
729 |
+
"loss": 0.1307,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 4.16,
|
734 |
+
"grad_norm": 0.30373403429985046,
|
735 |
+
"learning_rate": 1.522655721103291e-05,
|
736 |
+
"loss": 0.1259,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 4.2,
|
741 |
+
"grad_norm": 0.31472688913345337,
|
742 |
+
"learning_rate": 1.3844591860619383e-05,
|
743 |
+
"loss": 0.1267,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 4.24,
|
748 |
+
"grad_norm": 0.3078845739364624,
|
749 |
+
"learning_rate": 1.2523691546803873e-05,
|
750 |
+
"loss": 0.123,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 4.28,
|
755 |
+
"grad_norm": 0.31925857067108154,
|
756 |
+
"learning_rate": 1.1264792494342857e-05,
|
757 |
+
"loss": 0.1326,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 4.32,
|
762 |
+
"grad_norm": 0.29572564363479614,
|
763 |
+
"learning_rate": 1.0068786982878087e-05,
|
764 |
+
"loss": 0.1162,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 4.36,
|
769 |
+
"grad_norm": 0.29332664608955383,
|
770 |
+
"learning_rate": 8.936522714508678e-06,
|
771 |
+
"loss": 0.1153,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 4.4,
|
776 |
+
"grad_norm": 0.29813987016677856,
|
777 |
+
"learning_rate": 7.868802212958703e-06,
|
778 |
+
"loss": 0.1166,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 4.44,
|
783 |
+
"grad_norm": 0.2909725308418274,
|
784 |
+
"learning_rate": 6.866382254766157e-06,
|
785 |
+
"loss": 0.108,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 4.48,
|
790 |
+
"grad_norm": 0.31103241443634033,
|
791 |
+
"learning_rate": 5.929973332896677e-06,
|
792 |
+
"loss": 0.1228,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 4.52,
|
797 |
+
"grad_norm": 0.29073992371559143,
|
798 |
+
"learning_rate": 5.060239153161872e-06,
|
799 |
+
"loss": 0.118,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 4.5600000000000005,
|
804 |
+
"grad_norm": 0.288641095161438,
|
805 |
+
"learning_rate": 4.257796163799455e-06,
|
806 |
+
"loss": 0.1184,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 4.6,
|
811 |
+
"grad_norm": 0.3088034689426422,
|
812 |
+
"learning_rate": 3.5232131185484076e-06,
|
813 |
+
"loss": 0.1285,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 4.64,
|
818 |
+
"grad_norm": 0.30730554461479187,
|
819 |
+
"learning_rate": 2.857010673529015e-06,
|
820 |
+
"loss": 0.1263,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 4.68,
|
825 |
+
"grad_norm": 0.291875422000885,
|
826 |
+
"learning_rate": 2.259661018213333e-06,
|
827 |
+
"loss": 0.108,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 4.72,
|
832 |
+
"grad_norm": 0.31049686670303345,
|
833 |
+
"learning_rate": 1.7315875407479032e-06,
|
834 |
+
"loss": 0.1225,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 4.76,
|
839 |
+
"grad_norm": 0.32437863945961,
|
840 |
+
"learning_rate": 1.2731645278655445e-06,
|
841 |
+
"loss": 0.1431,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 4.8,
|
846 |
+
"grad_norm": 0.3190011978149414,
|
847 |
+
"learning_rate": 8.847168995992916e-07,
|
848 |
+
"loss": 0.1298,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 4.84,
|
853 |
+
"grad_norm": 0.3092647194862366,
|
854 |
+
"learning_rate": 5.665199789862907e-07,
|
855 |
+
"loss": 0.1333,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 4.88,
|
860 |
+
"grad_norm": 0.3259420096874237,
|
861 |
+
"learning_rate": 3.1879929692498757e-07,
|
862 |
+
"loss": 0.1312,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 4.92,
|
867 |
+
"grad_norm": 0.31257393956184387,
|
868 |
+
"learning_rate": 1.4173043232380557e-07,
|
869 |
+
"loss": 0.1255,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 4.96,
|
874 |
+
"grad_norm": 0.310062438249588,
|
875 |
+
"learning_rate": 3.5438887654737355e-08,
|
876 |
+
"loss": 0.1155,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 5.0,
|
881 |
+
"grad_norm": 0.3081853687763214,
|
882 |
+
"learning_rate": 0.0,
|
883 |
+
"loss": 0.1245,
|
884 |
+
"step": 125
|
885 |
}
|
886 |
],
|
887 |
"logging_steps": 1,
|
888 |
+
"max_steps": 125,
|
889 |
"num_input_tokens_seen": 0,
|
890 |
+
"num_train_epochs": 5,
|
891 |
"save_steps": 500,
|
892 |
"stateful_callbacks": {
|
893 |
"TrainerControl": {
|
|
|
901 |
"attributes": {}
|
902 |
}
|
903 |
},
|
904 |
+
"total_flos": 1.8813347440214016e+17,
|
905 |
"train_batch_size": 1,
|
906 |
"trial_name": null,
|
907 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e1d32de1ebecb4b037f065430ceae70509727e789a1fec0ab879aa962ea3fb
|
3 |
size 5240
|