Training in progress, epoch 0, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"k_proj",
|
24 |
-
"down_proj",
|
25 |
"up_proj",
|
26 |
-
"gate_proj",
|
27 |
-
"o_proj",
|
28 |
"v_proj",
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
"k_proj",
|
|
|
25 |
"up_proj",
|
|
|
|
|
26 |
"v_proj",
|
27 |
+
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"o_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:
|
3 |
size 80013120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f2c54b3cff7229bba3a337321576ca3fbedcde46f10b6c700245830c01cb495
|
3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41119636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79bc646c7471cb3943c0b5456f615d091883e21fcd695a7c0aa6311ff2dd361a
|
3 |
size 41119636
|
last-checkpoint/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:b5da8984c55f90689ec5dc6254808c095ed22f24233bafba7be5034f696b9c85
|
3 |
size 14244
|
last-checkpoint/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:a9299ec7d0989f843c66221f6a5f12c76f22cfda8e3a2897dd9a527db5b37854
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,727 +9,727 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm": 0.
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 2.
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"eval_loss": 3.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second": 4.
|
23 |
-
"eval_steps_per_second": 4.
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
-
"epoch": 0.
|
28 |
-
"grad_norm": 0.
|
29 |
-
"learning_rate":
|
30 |
-
"loss": 2.
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
-
"epoch": 0.
|
35 |
-
"grad_norm": 0.
|
36 |
-
"learning_rate":
|
37 |
-
"loss": 2.
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
-
"epoch": 0.
|
42 |
-
"grad_norm": 0.
|
43 |
-
"learning_rate":
|
44 |
-
"loss": 2.
|
45 |
"step": 4
|
46 |
},
|
47 |
{
|
48 |
-
"epoch": 0.
|
49 |
-
"grad_norm":
|
50 |
-
"learning_rate":
|
51 |
-
"loss": 2.
|
52 |
"step": 5
|
53 |
},
|
54 |
{
|
55 |
-
"epoch": 0.
|
56 |
-
"grad_norm":
|
57 |
-
"learning_rate":
|
58 |
-
"loss": 2.
|
59 |
"step": 6
|
60 |
},
|
61 |
{
|
62 |
-
"epoch": 0.
|
63 |
-
"grad_norm":
|
64 |
-
"learning_rate":
|
65 |
-
"loss": 2.
|
66 |
"step": 7
|
67 |
},
|
68 |
{
|
69 |
-
"epoch": 0.
|
70 |
-
"grad_norm": 0.
|
71 |
-
"learning_rate":
|
72 |
-
"loss": 2.
|
73 |
"step": 8
|
74 |
},
|
75 |
{
|
76 |
-
"epoch": 0.
|
77 |
-
"grad_norm":
|
78 |
-
"learning_rate":
|
79 |
-
"loss": 2.
|
80 |
"step": 9
|
81 |
},
|
82 |
{
|
83 |
-
"epoch": 0.
|
84 |
-
"grad_norm":
|
85 |
-
"learning_rate": 0.
|
86 |
-
"loss": 2.
|
87 |
"step": 10
|
88 |
},
|
89 |
{
|
90 |
-
"epoch": 0.
|
91 |
-
"grad_norm": 1.
|
92 |
-
"learning_rate":
|
93 |
-
"loss": 2.
|
94 |
"step": 11
|
95 |
},
|
96 |
{
|
97 |
-
"epoch": 0.
|
98 |
-
"grad_norm":
|
99 |
-
"learning_rate":
|
100 |
-
"loss": 2.
|
101 |
"step": 12
|
102 |
},
|
103 |
{
|
104 |
-
"epoch": 0.
|
105 |
-
"grad_norm":
|
106 |
-
"learning_rate":
|
107 |
-
"loss": 2.
|
108 |
"step": 13
|
109 |
},
|
110 |
{
|
111 |
-
"epoch": 0.
|
112 |
-
"grad_norm": 1.
|
113 |
-
"learning_rate":
|
114 |
-
"loss": 2.
|
115 |
"step": 14
|
116 |
},
|
117 |
{
|
118 |
-
"epoch": 0.
|
119 |
-
"grad_norm":
|
120 |
-
"learning_rate":
|
121 |
-
"loss": 2.
|
122 |
"step": 15
|
123 |
},
|
124 |
{
|
125 |
-
"epoch": 0.
|
126 |
-
"grad_norm":
|
127 |
-
"learning_rate":
|
128 |
-
"loss": 2.
|
129 |
"step": 16
|
130 |
},
|
131 |
{
|
132 |
-
"epoch": 0.
|
133 |
-
"grad_norm": 1.
|
134 |
-
"learning_rate":
|
135 |
-
"loss": 2.
|
136 |
"step": 17
|
137 |
},
|
138 |
{
|
139 |
-
"epoch": 0.
|
140 |
-
"grad_norm":
|
141 |
-
"learning_rate":
|
142 |
-
"loss": 2.
|
143 |
"step": 18
|
144 |
},
|
145 |
{
|
146 |
-
"epoch": 0.
|
147 |
-
"grad_norm":
|
148 |
-
"learning_rate":
|
149 |
-
"loss": 2.
|
150 |
"step": 19
|
151 |
},
|
152 |
{
|
153 |
-
"epoch": 0.
|
154 |
-
"grad_norm":
|
155 |
-
"learning_rate":
|
156 |
-
"loss": 2.
|
157 |
"step": 20
|
158 |
},
|
159 |
{
|
160 |
-
"epoch": 0.
|
161 |
-
"grad_norm":
|
162 |
-
"learning_rate":
|
163 |
-
"loss": 2.
|
164 |
"step": 21
|
165 |
},
|
166 |
{
|
167 |
-
"epoch": 0.
|
168 |
-
"grad_norm": 0.
|
169 |
-
"learning_rate":
|
170 |
-
"loss": 2.
|
171 |
"step": 22
|
172 |
},
|
173 |
{
|
174 |
-
"epoch": 0.
|
175 |
-
"grad_norm":
|
176 |
-
"learning_rate":
|
177 |
-
"loss": 2.
|
178 |
"step": 23
|
179 |
},
|
180 |
{
|
181 |
-
"epoch": 0.
|
182 |
-
"grad_norm": 0.
|
183 |
-
"learning_rate":
|
184 |
-
"loss": 2.
|
185 |
"step": 24
|
186 |
},
|
187 |
{
|
188 |
-
"epoch": 0.
|
189 |
-
"grad_norm": 1.
|
190 |
-
"learning_rate":
|
191 |
-
"loss": 2.
|
192 |
"step": 25
|
193 |
},
|
194 |
{
|
195 |
-
"epoch": 0.
|
196 |
-
"grad_norm":
|
197 |
-
"learning_rate":
|
198 |
-
"loss": 2.
|
199 |
"step": 26
|
200 |
},
|
201 |
{
|
202 |
-
"epoch": 0.
|
203 |
-
"grad_norm":
|
204 |
-
"learning_rate":
|
205 |
-
"loss": 2.
|
206 |
"step": 27
|
207 |
},
|
208 |
{
|
209 |
-
"epoch": 0.
|
210 |
-
"grad_norm":
|
211 |
-
"learning_rate":
|
212 |
-
"loss": 2.
|
213 |
"step": 28
|
214 |
},
|
215 |
{
|
216 |
-
"epoch": 0.
|
217 |
-
"grad_norm":
|
218 |
-
"learning_rate":
|
219 |
-
"loss": 2.
|
220 |
"step": 29
|
221 |
},
|
222 |
{
|
223 |
-
"epoch": 0.
|
224 |
-
"grad_norm":
|
225 |
-
"learning_rate":
|
226 |
-
"loss": 2.
|
227 |
"step": 30
|
228 |
},
|
229 |
{
|
230 |
-
"epoch": 0.
|
231 |
-
"grad_norm": 0.
|
232 |
-
"learning_rate":
|
233 |
-
"loss": 2.
|
234 |
"step": 31
|
235 |
},
|
236 |
{
|
237 |
-
"epoch": 0.
|
238 |
-
"grad_norm":
|
239 |
-
"learning_rate":
|
240 |
-
"loss": 2.
|
241 |
"step": 32
|
242 |
},
|
243 |
{
|
244 |
-
"epoch": 0.
|
245 |
-
"grad_norm": 0.
|
246 |
-
"learning_rate":
|
247 |
-
"loss": 2.
|
248 |
"step": 33
|
249 |
},
|
250 |
{
|
251 |
-
"epoch": 0.
|
252 |
-
"grad_norm": 0.
|
253 |
-
"learning_rate":
|
254 |
-
"loss": 2.
|
255 |
"step": 34
|
256 |
},
|
257 |
{
|
258 |
-
"epoch": 0.
|
259 |
-
"grad_norm": 0.
|
260 |
-
"learning_rate":
|
261 |
-
"loss": 2.
|
262 |
"step": 35
|
263 |
},
|
264 |
{
|
265 |
-
"epoch": 0.
|
266 |
-
"grad_norm":
|
267 |
-
"learning_rate":
|
268 |
-
"loss": 2.
|
269 |
"step": 36
|
270 |
},
|
271 |
{
|
272 |
-
"epoch": 0.
|
273 |
-
"grad_norm": 0.
|
274 |
-
"learning_rate":
|
275 |
-
"loss": 2.
|
276 |
"step": 37
|
277 |
},
|
278 |
{
|
279 |
-
"epoch": 0.
|
280 |
-
"grad_norm": 0.
|
281 |
-
"learning_rate":
|
282 |
-
"loss": 2.
|
283 |
"step": 38
|
284 |
},
|
285 |
{
|
286 |
-
"epoch": 0.
|
287 |
-
"grad_norm": 0.
|
288 |
-
"learning_rate":
|
289 |
-
"loss": 2.
|
290 |
"step": 39
|
291 |
},
|
292 |
{
|
293 |
-
"epoch": 0.
|
294 |
-
"grad_norm": 0.
|
295 |
-
"learning_rate":
|
296 |
-
"loss": 2.
|
297 |
"step": 40
|
298 |
},
|
299 |
{
|
300 |
-
"epoch": 0.
|
301 |
-
"grad_norm": 0.
|
302 |
-
"learning_rate":
|
303 |
-
"loss": 2.
|
304 |
"step": 41
|
305 |
},
|
306 |
{
|
307 |
-
"epoch": 0.
|
308 |
-
"grad_norm": 0.
|
309 |
-
"learning_rate":
|
310 |
-
"loss": 2.
|
311 |
"step": 42
|
312 |
},
|
313 |
{
|
314 |
-
"epoch": 0.
|
315 |
-
"grad_norm": 0.
|
316 |
-
"learning_rate":
|
317 |
-
"loss": 2.
|
318 |
"step": 43
|
319 |
},
|
320 |
{
|
321 |
-
"epoch": 0.
|
322 |
-
"grad_norm": 0.
|
323 |
-
"learning_rate":
|
324 |
-
"loss": 2.
|
325 |
"step": 44
|
326 |
},
|
327 |
{
|
328 |
-
"epoch": 0.
|
329 |
-
"grad_norm": 0.
|
330 |
-
"learning_rate":
|
331 |
-
"loss": 2.
|
332 |
"step": 45
|
333 |
},
|
334 |
{
|
335 |
-
"epoch": 0.
|
336 |
-
"grad_norm": 0.
|
337 |
-
"learning_rate":
|
338 |
-
"loss": 2.
|
339 |
"step": 46
|
340 |
},
|
341 |
{
|
342 |
-
"epoch": 0.
|
343 |
-
"grad_norm": 0.
|
344 |
-
"learning_rate":
|
345 |
-
"loss": 2.
|
346 |
"step": 47
|
347 |
},
|
348 |
{
|
349 |
-
"epoch": 0.
|
350 |
-
"grad_norm":
|
351 |
-
"learning_rate":
|
352 |
-
"loss": 2.
|
353 |
"step": 48
|
354 |
},
|
355 |
{
|
356 |
-
"epoch": 0.
|
357 |
-
"grad_norm": 0.
|
358 |
-
"learning_rate":
|
359 |
-
"loss": 2.
|
360 |
"step": 49
|
361 |
},
|
362 |
{
|
363 |
-
"epoch": 0.
|
364 |
-
"grad_norm":
|
365 |
-
"learning_rate":
|
366 |
-
"loss": 2.
|
367 |
"step": 50
|
368 |
},
|
369 |
{
|
370 |
-
"epoch": 0.
|
371 |
-
"eval_loss": 2.
|
372 |
-
"eval_runtime":
|
373 |
-
"eval_samples_per_second": 4.
|
374 |
-
"eval_steps_per_second": 4.
|
375 |
"step": 50
|
376 |
},
|
377 |
{
|
378 |
-
"epoch": 0.
|
379 |
-
"grad_norm": 0.
|
380 |
-
"learning_rate":
|
381 |
-
"loss": 2.
|
382 |
"step": 51
|
383 |
},
|
384 |
{
|
385 |
-
"epoch": 0.
|
386 |
-
"grad_norm":
|
387 |
-
"learning_rate":
|
388 |
-
"loss": 2.
|
389 |
"step": 52
|
390 |
},
|
391 |
{
|
392 |
-
"epoch": 0.
|
393 |
-
"grad_norm": 0.
|
394 |
-
"learning_rate":
|
395 |
-
"loss": 2.
|
396 |
"step": 53
|
397 |
},
|
398 |
{
|
399 |
-
"epoch": 0.
|
400 |
-
"grad_norm":
|
401 |
-
"learning_rate":
|
402 |
-
"loss": 2.
|
403 |
"step": 54
|
404 |
},
|
405 |
{
|
406 |
-
"epoch": 0.
|
407 |
-
"grad_norm":
|
408 |
-
"learning_rate":
|
409 |
-
"loss": 2.
|
410 |
"step": 55
|
411 |
},
|
412 |
{
|
413 |
-
"epoch": 0.
|
414 |
-
"grad_norm":
|
415 |
-
"learning_rate":
|
416 |
-
"loss": 2.
|
417 |
"step": 56
|
418 |
},
|
419 |
{
|
420 |
-
"epoch": 0.
|
421 |
-
"grad_norm": 0.
|
422 |
-
"learning_rate":
|
423 |
-
"loss": 2.
|
424 |
"step": 57
|
425 |
},
|
426 |
{
|
427 |
-
"epoch": 0.
|
428 |
-
"grad_norm":
|
429 |
-
"learning_rate":
|
430 |
-
"loss": 2.
|
431 |
"step": 58
|
432 |
},
|
433 |
{
|
434 |
-
"epoch": 0.
|
435 |
-
"grad_norm":
|
436 |
-
"learning_rate":
|
437 |
-
"loss": 2.
|
438 |
"step": 59
|
439 |
},
|
440 |
{
|
441 |
-
"epoch": 0.
|
442 |
-
"grad_norm":
|
443 |
-
"learning_rate":
|
444 |
-
"loss": 2.
|
445 |
"step": 60
|
446 |
},
|
447 |
{
|
448 |
-
"epoch": 0.
|
449 |
-
"grad_norm":
|
450 |
-
"learning_rate":
|
451 |
-
"loss": 2.
|
452 |
"step": 61
|
453 |
},
|
454 |
{
|
455 |
-
"epoch": 0.
|
456 |
-
"grad_norm":
|
457 |
-
"learning_rate":
|
458 |
-
"loss": 2.
|
459 |
"step": 62
|
460 |
},
|
461 |
{
|
462 |
-
"epoch": 0.
|
463 |
-
"grad_norm":
|
464 |
-
"learning_rate":
|
465 |
-
"loss": 2.
|
466 |
"step": 63
|
467 |
},
|
468 |
{
|
469 |
-
"epoch": 0.
|
470 |
-
"grad_norm": 0.
|
471 |
-
"learning_rate":
|
472 |
-
"loss": 2.
|
473 |
"step": 64
|
474 |
},
|
475 |
{
|
476 |
-
"epoch": 0.
|
477 |
-
"grad_norm":
|
478 |
-
"learning_rate":
|
479 |
-
"loss": 2.
|
480 |
"step": 65
|
481 |
},
|
482 |
{
|
483 |
-
"epoch": 0.
|
484 |
-
"grad_norm": 0.
|
485 |
-
"learning_rate":
|
486 |
-
"loss": 2.
|
487 |
"step": 66
|
488 |
},
|
489 |
{
|
490 |
-
"epoch": 0.
|
491 |
-
"grad_norm": 0.
|
492 |
-
"learning_rate":
|
493 |
-
"loss": 2.
|
494 |
"step": 67
|
495 |
},
|
496 |
{
|
497 |
-
"epoch": 0.
|
498 |
-
"grad_norm":
|
499 |
-
"learning_rate":
|
500 |
-
"loss": 2.
|
501 |
"step": 68
|
502 |
},
|
503 |
{
|
504 |
-
"epoch": 0.
|
505 |
-
"grad_norm": 0.
|
506 |
-
"learning_rate":
|
507 |
-
"loss": 2.
|
508 |
"step": 69
|
509 |
},
|
510 |
{
|
511 |
-
"epoch": 0.
|
512 |
-
"grad_norm": 0.
|
513 |
-
"learning_rate":
|
514 |
-
"loss": 2.
|
515 |
"step": 70
|
516 |
},
|
517 |
{
|
518 |
-
"epoch": 0.
|
519 |
-
"grad_norm":
|
520 |
-
"learning_rate":
|
521 |
-
"loss": 2.
|
522 |
"step": 71
|
523 |
},
|
524 |
{
|
525 |
-
"epoch": 0.
|
526 |
-
"grad_norm":
|
527 |
-
"learning_rate":
|
528 |
-
"loss": 2.
|
529 |
"step": 72
|
530 |
},
|
531 |
{
|
532 |
-
"epoch": 0.
|
533 |
-
"grad_norm": 0.
|
534 |
-
"learning_rate":
|
535 |
-
"loss": 2.
|
536 |
"step": 73
|
537 |
},
|
538 |
{
|
539 |
-
"epoch": 0.
|
540 |
-
"grad_norm": 0.
|
541 |
-
"learning_rate":
|
542 |
-
"loss": 2.
|
543 |
"step": 74
|
544 |
},
|
545 |
{
|
546 |
-
"epoch": 0.
|
547 |
-
"grad_norm": 0.
|
548 |
-
"learning_rate":
|
549 |
-
"loss": 2.
|
550 |
"step": 75
|
551 |
},
|
552 |
{
|
553 |
-
"epoch": 0.
|
554 |
-
"grad_norm":
|
555 |
-
"learning_rate":
|
556 |
-
"loss": 2.
|
557 |
"step": 76
|
558 |
},
|
559 |
{
|
560 |
-
"epoch": 0.
|
561 |
-
"grad_norm":
|
562 |
-
"learning_rate":
|
563 |
-
"loss": 2.
|
564 |
"step": 77
|
565 |
},
|
566 |
{
|
567 |
-
"epoch": 0.
|
568 |
-
"grad_norm": 0.
|
569 |
-
"learning_rate":
|
570 |
-
"loss": 2.
|
571 |
"step": 78
|
572 |
},
|
573 |
{
|
574 |
-
"epoch": 0.
|
575 |
-
"grad_norm": 0.
|
576 |
-
"learning_rate":
|
577 |
-
"loss": 2.
|
578 |
"step": 79
|
579 |
},
|
580 |
{
|
581 |
-
"epoch": 0.
|
582 |
-
"grad_norm":
|
583 |
-
"learning_rate":
|
584 |
-
"loss": 2.
|
585 |
"step": 80
|
586 |
},
|
587 |
{
|
588 |
-
"epoch": 0.
|
589 |
-
"grad_norm": 0.
|
590 |
-
"learning_rate":
|
591 |
-
"loss": 2.
|
592 |
"step": 81
|
593 |
},
|
594 |
{
|
595 |
-
"epoch": 0.
|
596 |
-
"grad_norm": 0.
|
597 |
-
"learning_rate": 9.549150281252633e-
|
598 |
-
"loss": 2.
|
599 |
"step": 82
|
600 |
},
|
601 |
{
|
602 |
-
"epoch": 0.
|
603 |
-
"grad_norm":
|
604 |
-
"learning_rate": 8.548121372247918e-
|
605 |
-
"loss": 2.
|
606 |
"step": 83
|
607 |
},
|
608 |
{
|
609 |
-
"epoch": 0.
|
610 |
-
"grad_norm": 0.
|
611 |
-
"learning_rate": 7.597595192178702e-
|
612 |
-
"loss": 2.
|
613 |
"step": 84
|
614 |
},
|
615 |
{
|
616 |
-
"epoch": 0.
|
617 |
-
"grad_norm": 0.
|
618 |
-
"learning_rate": 6.698729810778065e-
|
619 |
-
"loss": 2.
|
620 |
"step": 85
|
621 |
},
|
622 |
{
|
623 |
-
"epoch": 0.
|
624 |
-
"grad_norm": 0.
|
625 |
-
"learning_rate": 5.852620357053651e-
|
626 |
-
"loss": 2.
|
627 |
"step": 86
|
628 |
},
|
629 |
{
|
630 |
-
"epoch": 0.
|
631 |
-
"grad_norm": 0.
|
632 |
-
"learning_rate": 5.060297685041659e-
|
633 |
-
"loss": 2.
|
634 |
"step": 87
|
635 |
},
|
636 |
{
|
637 |
-
"epoch": 0.
|
638 |
-
"grad_norm":
|
639 |
-
"learning_rate": 4.322727117869951e-
|
640 |
-
"loss": 2.
|
641 |
"step": 88
|
642 |
},
|
643 |
{
|
644 |
-
"epoch": 0.
|
645 |
-
"grad_norm": 0.
|
646 |
-
"learning_rate": 3.
|
647 |
-
"loss": 2.
|
648 |
"step": 89
|
649 |
},
|
650 |
{
|
651 |
-
"epoch": 0.
|
652 |
-
"grad_norm": 0.
|
653 |
-
"learning_rate": 3.
|
654 |
-
"loss": 2.
|
655 |
"step": 90
|
656 |
},
|
657 |
{
|
658 |
-
"epoch": 0.
|
659 |
-
"grad_norm": 0.
|
660 |
-
"learning_rate": 2.
|
661 |
-
"loss": 2.
|
662 |
"step": 91
|
663 |
},
|
664 |
{
|
665 |
-
"epoch": 0.
|
666 |
-
"grad_norm": 0.
|
667 |
-
"learning_rate": 1.
|
668 |
-
"loss": 2.
|
669 |
"step": 92
|
670 |
},
|
671 |
{
|
672 |
-
"epoch": 0.
|
673 |
-
"grad_norm":
|
674 |
-
"learning_rate": 1.4852136862001764e-
|
675 |
-
"loss": 2.
|
676 |
"step": 93
|
677 |
},
|
678 |
{
|
679 |
-
"epoch": 0.
|
680 |
-
"grad_norm":
|
681 |
-
"learning_rate": 1.
|
682 |
-
"loss": 2.
|
683 |
"step": 94
|
684 |
},
|
685 |
{
|
686 |
-
"epoch": 0.
|
687 |
-
"grad_norm": 0.
|
688 |
-
"learning_rate": 7.
|
689 |
-
"loss": 2.
|
690 |
"step": 95
|
691 |
},
|
692 |
{
|
693 |
-
"epoch": 0.
|
694 |
-
"grad_norm": 0.
|
695 |
-
"learning_rate": 4.865965629214819e-
|
696 |
-
"loss": 2.
|
697 |
"step": 96
|
698 |
},
|
699 |
{
|
700 |
-
"epoch": 0.
|
701 |
-
"grad_norm": 0.
|
702 |
-
"learning_rate": 2.
|
703 |
-
"loss": 2.
|
704 |
"step": 97
|
705 |
},
|
706 |
{
|
707 |
-
"epoch": 0.
|
708 |
-
"grad_norm": 0.
|
709 |
-
"learning_rate": 1.2179748700879012e-
|
710 |
-
"loss": 2.
|
711 |
"step": 98
|
712 |
},
|
713 |
{
|
714 |
-
"epoch": 0.
|
715 |
-
"grad_norm": 0.
|
716 |
-
"learning_rate": 3.
|
717 |
-
"loss": 2.
|
718 |
"step": 99
|
719 |
},
|
720 |
{
|
721 |
-
"epoch": 0.
|
722 |
-
"grad_norm": 0.
|
723 |
"learning_rate": 0.0,
|
724 |
-
"loss": 2.
|
725 |
"step": 100
|
726 |
},
|
727 |
{
|
728 |
-
"epoch": 0.
|
729 |
-
"eval_loss": 2.
|
730 |
-
"eval_runtime":
|
731 |
-
"eval_samples_per_second": 4.
|
732 |
-
"eval_steps_per_second": 4.
|
733 |
"step": 100
|
734 |
}
|
735 |
],
|
@@ -737,7 +737,7 @@
|
|
737 |
"max_steps": 100,
|
738 |
"num_input_tokens_seen": 0,
|
739 |
"num_train_epochs": 1,
|
740 |
-
"save_steps":
|
741 |
"stateful_callbacks": {
|
742 |
"TrainerControl": {
|
743 |
"args": {
|
@@ -750,7 +750,7 @@
|
|
750 |
"attributes": {}
|
751 |
}
|
752 |
},
|
753 |
-
"total_flos":
|
754 |
"train_batch_size": 1,
|
755 |
"trial_name": null,
|
756 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2,
|
5 |
"eval_steps": 50,
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.002,
|
13 |
+
"grad_norm": 0.3986969590187073,
|
14 |
+
"learning_rate": 0.0001,
|
15 |
+
"loss": 2.7769,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.002,
|
20 |
+
"eval_loss": 3.0125324726104736,
|
21 |
+
"eval_runtime": 4.8013,
|
22 |
+
"eval_samples_per_second": 4.374,
|
23 |
+
"eval_steps_per_second": 4.374,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
+
"epoch": 0.004,
|
28 |
+
"grad_norm": 0.5986809730529785,
|
29 |
+
"learning_rate": 0.0002,
|
30 |
+
"loss": 2.9521,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
+
"epoch": 0.006,
|
35 |
+
"grad_norm": 0.595142662525177,
|
36 |
+
"learning_rate": 0.0003,
|
37 |
+
"loss": 2.955,
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
+
"epoch": 0.008,
|
42 |
+
"grad_norm": 0.7013932466506958,
|
43 |
+
"learning_rate": 0.0004,
|
44 |
+
"loss": 2.9037,
|
45 |
"step": 4
|
46 |
},
|
47 |
{
|
48 |
+
"epoch": 0.01,
|
49 |
+
"grad_norm": 1.5847638845443726,
|
50 |
+
"learning_rate": 0.0005,
|
51 |
+
"loss": 2.9706,
|
52 |
"step": 5
|
53 |
},
|
54 |
{
|
55 |
+
"epoch": 0.012,
|
56 |
+
"grad_norm": 1.6309813261032104,
|
57 |
+
"learning_rate": 0.0006,
|
58 |
+
"loss": 2.75,
|
59 |
"step": 6
|
60 |
},
|
61 |
{
|
62 |
+
"epoch": 0.014,
|
63 |
+
"grad_norm": 1.3442208766937256,
|
64 |
+
"learning_rate": 0.0007,
|
65 |
+
"loss": 2.5161,
|
66 |
"step": 7
|
67 |
},
|
68 |
{
|
69 |
+
"epoch": 0.016,
|
70 |
+
"grad_norm": 0.900488018989563,
|
71 |
+
"learning_rate": 0.0008,
|
72 |
+
"loss": 2.2906,
|
73 |
"step": 8
|
74 |
},
|
75 |
{
|
76 |
+
"epoch": 0.018,
|
77 |
+
"grad_norm": 2.340869903564453,
|
78 |
+
"learning_rate": 0.0009000000000000001,
|
79 |
+
"loss": 2.6079,
|
80 |
"step": 9
|
81 |
},
|
82 |
{
|
83 |
+
"epoch": 0.02,
|
84 |
+
"grad_norm": 2.987302303314209,
|
85 |
+
"learning_rate": 0.001,
|
86 |
+
"loss": 2.5506,
|
87 |
"step": 10
|
88 |
},
|
89 |
{
|
90 |
+
"epoch": 0.022,
|
91 |
+
"grad_norm": 1.844685673713684,
|
92 |
+
"learning_rate": 0.0009996954135095479,
|
93 |
+
"loss": 2.7146,
|
94 |
"step": 11
|
95 |
},
|
96 |
{
|
97 |
+
"epoch": 0.024,
|
98 |
+
"grad_norm": 0.9662850499153137,
|
99 |
+
"learning_rate": 0.0009987820251299122,
|
100 |
+
"loss": 2.6323,
|
101 |
"step": 12
|
102 |
},
|
103 |
{
|
104 |
+
"epoch": 0.026,
|
105 |
+
"grad_norm": 3.0721042156219482,
|
106 |
+
"learning_rate": 0.0009972609476841367,
|
107 |
+
"loss": 2.1718,
|
108 |
"step": 13
|
109 |
},
|
110 |
{
|
111 |
+
"epoch": 0.028,
|
112 |
+
"grad_norm": 1.0009405612945557,
|
113 |
+
"learning_rate": 0.0009951340343707852,
|
114 |
+
"loss": 2.6348,
|
115 |
"step": 14
|
116 |
},
|
117 |
{
|
118 |
+
"epoch": 0.03,
|
119 |
+
"grad_norm": 14.435264587402344,
|
120 |
+
"learning_rate": 0.000992403876506104,
|
121 |
+
"loss": 2.5352,
|
122 |
"step": 15
|
123 |
},
|
124 |
{
|
125 |
+
"epoch": 0.032,
|
126 |
+
"grad_norm": 5.060039520263672,
|
127 |
+
"learning_rate": 0.0009890738003669028,
|
128 |
+
"loss": 2.708,
|
129 |
"step": 16
|
130 |
},
|
131 |
{
|
132 |
+
"epoch": 0.034,
|
133 |
+
"grad_norm": 1.6351608037948608,
|
134 |
+
"learning_rate": 0.0009851478631379982,
|
135 |
+
"loss": 2.3905,
|
136 |
"step": 17
|
137 |
},
|
138 |
{
|
139 |
+
"epoch": 0.036,
|
140 |
+
"grad_norm": 2.9582386016845703,
|
141 |
+
"learning_rate": 0.0009806308479691594,
|
142 |
+
"loss": 2.5147,
|
143 |
"step": 18
|
144 |
},
|
145 |
{
|
146 |
+
"epoch": 0.038,
|
147 |
+
"grad_norm": 1.8205921649932861,
|
148 |
+
"learning_rate": 0.0009755282581475768,
|
149 |
+
"loss": 2.766,
|
150 |
"step": 19
|
151 |
},
|
152 |
{
|
153 |
+
"epoch": 0.04,
|
154 |
+
"grad_norm": 1.1158825159072876,
|
155 |
+
"learning_rate": 0.0009698463103929542,
|
156 |
+
"loss": 2.7895,
|
157 |
"step": 20
|
158 |
},
|
159 |
{
|
160 |
+
"epoch": 0.042,
|
161 |
+
"grad_norm": 1.1689060926437378,
|
162 |
+
"learning_rate": 0.0009635919272833937,
|
163 |
+
"loss": 2.6373,
|
164 |
"step": 21
|
165 |
},
|
166 |
{
|
167 |
+
"epoch": 0.044,
|
168 |
+
"grad_norm": 0.8205438256263733,
|
169 |
+
"learning_rate": 0.0009567727288213005,
|
170 |
+
"loss": 2.4038,
|
171 |
"step": 22
|
172 |
},
|
173 |
{
|
174 |
+
"epoch": 0.046,
|
175 |
+
"grad_norm": 1.2794568538665771,
|
176 |
+
"learning_rate": 0.0009493970231495835,
|
177 |
+
"loss": 2.3676,
|
178 |
"step": 23
|
179 |
},
|
180 |
{
|
181 |
+
"epoch": 0.048,
|
182 |
+
"grad_norm": 0.822256863117218,
|
183 |
+
"learning_rate": 0.0009414737964294635,
|
184 |
+
"loss": 2.327,
|
185 |
"step": 24
|
186 |
},
|
187 |
{
|
188 |
+
"epoch": 0.05,
|
189 |
+
"grad_norm": 1.986864447593689,
|
190 |
+
"learning_rate": 0.0009330127018922195,
|
191 |
+
"loss": 2.4431,
|
192 |
"step": 25
|
193 |
},
|
194 |
{
|
195 |
+
"epoch": 0.052,
|
196 |
+
"grad_norm": 3.7959301471710205,
|
197 |
+
"learning_rate": 0.0009240240480782129,
|
198 |
+
"loss": 2.6657,
|
199 |
"step": 26
|
200 |
},
|
201 |
{
|
202 |
+
"epoch": 0.054,
|
203 |
+
"grad_norm": 2.489267587661743,
|
204 |
+
"learning_rate": 0.0009145187862775209,
|
205 |
+
"loss": 2.5005,
|
206 |
"step": 27
|
207 |
},
|
208 |
{
|
209 |
+
"epoch": 0.056,
|
210 |
+
"grad_norm": 2.1583516597747803,
|
211 |
+
"learning_rate": 0.0009045084971874737,
|
212 |
+
"loss": 2.5402,
|
213 |
"step": 28
|
214 |
},
|
215 |
{
|
216 |
+
"epoch": 0.058,
|
217 |
+
"grad_norm": 4.524465084075928,
|
218 |
+
"learning_rate": 0.0008940053768033609,
|
219 |
+
"loss": 2.2461,
|
220 |
"step": 29
|
221 |
},
|
222 |
{
|
223 |
+
"epoch": 0.06,
|
224 |
+
"grad_norm": 1.3595800399780273,
|
225 |
+
"learning_rate": 0.000883022221559489,
|
226 |
+
"loss": 2.331,
|
227 |
"step": 30
|
228 |
},
|
229 |
{
|
230 |
+
"epoch": 0.062,
|
231 |
+
"grad_norm": 0.9844056367874146,
|
232 |
+
"learning_rate": 0.0008715724127386971,
|
233 |
+
"loss": 2.3781,
|
234 |
"step": 31
|
235 |
},
|
236 |
{
|
237 |
+
"epoch": 0.064,
|
238 |
+
"grad_norm": 1.117148518562317,
|
239 |
+
"learning_rate": 0.0008596699001693256,
|
240 |
+
"loss": 2.4258,
|
241 |
"step": 32
|
242 |
},
|
243 |
{
|
244 |
+
"epoch": 0.066,
|
245 |
+
"grad_norm": 0.7900739312171936,
|
246 |
+
"learning_rate": 0.0008473291852294987,
|
247 |
+
"loss": 2.437,
|
248 |
"step": 33
|
249 |
},
|
250 |
{
|
251 |
+
"epoch": 0.068,
|
252 |
+
"grad_norm": 0.8672456741333008,
|
253 |
+
"learning_rate": 0.0008345653031794292,
|
254 |
+
"loss": 2.8025,
|
255 |
"step": 34
|
256 |
},
|
257 |
{
|
258 |
+
"epoch": 0.07,
|
259 |
+
"grad_norm": 0.816504716873169,
|
260 |
+
"learning_rate": 0.0008213938048432696,
|
261 |
+
"loss": 2.5078,
|
262 |
"step": 35
|
263 |
},
|
264 |
{
|
265 |
+
"epoch": 0.072,
|
266 |
+
"grad_norm": 1.0574641227722168,
|
267 |
+
"learning_rate": 0.0008078307376628291,
|
268 |
+
"loss": 2.6408,
|
269 |
"step": 36
|
270 |
},
|
271 |
{
|
272 |
+
"epoch": 0.074,
|
273 |
+
"grad_norm": 0.6753240823745728,
|
274 |
+
"learning_rate": 0.0007938926261462366,
|
275 |
+
"loss": 2.2858,
|
276 |
"step": 37
|
277 |
},
|
278 |
{
|
279 |
+
"epoch": 0.076,
|
280 |
+
"grad_norm": 0.9166250824928284,
|
281 |
+
"learning_rate": 0.0007795964517353734,
|
282 |
+
"loss": 2.7091,
|
283 |
"step": 38
|
284 |
},
|
285 |
{
|
286 |
+
"epoch": 0.078,
|
287 |
+
"grad_norm": 0.9022424221038818,
|
288 |
+
"learning_rate": 0.0007649596321166025,
|
289 |
+
"loss": 2.6459,
|
290 |
"step": 39
|
291 |
},
|
292 |
{
|
293 |
+
"epoch": 0.08,
|
294 |
+
"grad_norm": 0.7723848223686218,
|
295 |
+
"learning_rate": 0.00075,
|
296 |
+
"loss": 2.4329,
|
297 |
"step": 40
|
298 |
},
|
299 |
{
|
300 |
+
"epoch": 0.082,
|
301 |
+
"grad_norm": 0.8669672012329102,
|
302 |
+
"learning_rate": 0.0007347357813929454,
|
303 |
+
"loss": 2.3661,
|
304 |
"step": 41
|
305 |
},
|
306 |
{
|
307 |
+
"epoch": 0.084,
|
308 |
+
"grad_norm": 0.9701873660087585,
|
309 |
+
"learning_rate": 0.0007191855733945387,
|
310 |
+
"loss": 2.6723,
|
311 |
"step": 42
|
312 |
},
|
313 |
{
|
314 |
+
"epoch": 0.086,
|
315 |
+
"grad_norm": 0.8038893342018127,
|
316 |
+
"learning_rate": 0.0007033683215379002,
|
317 |
+
"loss": 2.7652,
|
318 |
"step": 43
|
319 |
},
|
320 |
{
|
321 |
+
"epoch": 0.088,
|
322 |
+
"grad_norm": 0.6812747716903687,
|
323 |
+
"learning_rate": 0.0006873032967079561,
|
324 |
+
"loss": 2.4019,
|
325 |
"step": 44
|
326 |
},
|
327 |
{
|
328 |
+
"epoch": 0.09,
|
329 |
+
"grad_norm": 0.8909493088722229,
|
330 |
+
"learning_rate": 0.0006710100716628344,
|
331 |
+
"loss": 2.349,
|
332 |
"step": 45
|
333 |
},
|
334 |
{
|
335 |
+
"epoch": 0.092,
|
336 |
+
"grad_norm": 0.9887206554412842,
|
337 |
+
"learning_rate": 0.0006545084971874737,
|
338 |
+
"loss": 2.5577,
|
339 |
"step": 46
|
340 |
},
|
341 |
{
|
342 |
+
"epoch": 0.094,
|
343 |
+
"grad_norm": 0.7749077081680298,
|
344 |
+
"learning_rate": 0.0006378186779084996,
|
345 |
+
"loss": 2.2903,
|
346 |
"step": 47
|
347 |
},
|
348 |
{
|
349 |
+
"epoch": 0.096,
|
350 |
+
"grad_norm": 1.0913500785827637,
|
351 |
+
"learning_rate": 0.0006209609477998338,
|
352 |
+
"loss": 2.3697,
|
353 |
"step": 48
|
354 |
},
|
355 |
{
|
356 |
+
"epoch": 0.098,
|
357 |
+
"grad_norm": 0.894119381904602,
|
358 |
+
"learning_rate": 0.0006039558454088796,
|
359 |
+
"loss": 2.5167,
|
360 |
"step": 49
|
361 |
},
|
362 |
{
|
363 |
+
"epoch": 0.1,
|
364 |
+
"grad_norm": 1.159035325050354,
|
365 |
+
"learning_rate": 0.0005868240888334653,
|
366 |
+
"loss": 2.4637,
|
367 |
"step": 50
|
368 |
},
|
369 |
{
|
370 |
+
"epoch": 0.1,
|
371 |
+
"eval_loss": 2.5838444232940674,
|
372 |
+
"eval_runtime": 4.8707,
|
373 |
+
"eval_samples_per_second": 4.311,
|
374 |
+
"eval_steps_per_second": 4.311,
|
375 |
"step": 50
|
376 |
},
|
377 |
{
|
378 |
+
"epoch": 0.102,
|
379 |
+
"grad_norm": 0.6844251751899719,
|
380 |
+
"learning_rate": 0.0005695865504800327,
|
381 |
+
"loss": 2.4118,
|
382 |
"step": 51
|
383 |
},
|
384 |
{
|
385 |
+
"epoch": 0.104,
|
386 |
+
"grad_norm": 1.1709848642349243,
|
387 |
+
"learning_rate": 0.0005522642316338268,
|
388 |
+
"loss": 2.444,
|
389 |
"step": 52
|
390 |
},
|
391 |
{
|
392 |
+
"epoch": 0.106,
|
393 |
+
"grad_norm": 0.9435467720031738,
|
394 |
+
"learning_rate": 0.0005348782368720626,
|
395 |
+
"loss": 2.5568,
|
396 |
"step": 53
|
397 |
},
|
398 |
{
|
399 |
+
"epoch": 0.108,
|
400 |
+
"grad_norm": 1.0800719261169434,
|
401 |
+
"learning_rate": 0.0005174497483512506,
|
402 |
+
"loss": 2.5766,
|
403 |
"step": 54
|
404 |
},
|
405 |
{
|
406 |
+
"epoch": 0.11,
|
407 |
+
"grad_norm": 1.001356840133667,
|
408 |
+
"learning_rate": 0.0005,
|
409 |
+
"loss": 2.2205,
|
410 |
"step": 55
|
411 |
},
|
412 |
{
|
413 |
+
"epoch": 0.112,
|
414 |
+
"grad_norm": 1.4582829475402832,
|
415 |
+
"learning_rate": 0.0004825502516487497,
|
416 |
+
"loss": 2.7271,
|
417 |
"step": 56
|
418 |
},
|
419 |
{
|
420 |
+
"epoch": 0.114,
|
421 |
+
"grad_norm": 0.8312236666679382,
|
422 |
+
"learning_rate": 0.00046512176312793734,
|
423 |
+
"loss": 2.3204,
|
424 |
"step": 57
|
425 |
},
|
426 |
{
|
427 |
+
"epoch": 0.116,
|
428 |
+
"grad_norm": 1.2127161026000977,
|
429 |
+
"learning_rate": 0.00044773576836617336,
|
430 |
+
"loss": 2.0169,
|
431 |
"step": 58
|
432 |
},
|
433 |
{
|
434 |
+
"epoch": 0.118,
|
435 |
+
"grad_norm": 1.6428215503692627,
|
436 |
+
"learning_rate": 0.0004304134495199674,
|
437 |
+
"loss": 2.4521,
|
438 |
"step": 59
|
439 |
},
|
440 |
{
|
441 |
+
"epoch": 0.12,
|
442 |
+
"grad_norm": 1.7682443857192993,
|
443 |
+
"learning_rate": 0.00041317591116653486,
|
444 |
+
"loss": 2.6753,
|
445 |
"step": 60
|
446 |
},
|
447 |
{
|
448 |
+
"epoch": 0.122,
|
449 |
+
"grad_norm": 1.0919681787490845,
|
450 |
+
"learning_rate": 0.0003960441545911204,
|
451 |
+
"loss": 2.4022,
|
452 |
"step": 61
|
453 |
},
|
454 |
{
|
455 |
+
"epoch": 0.124,
|
456 |
+
"grad_norm": 2.5304136276245117,
|
457 |
+
"learning_rate": 0.0003790390522001662,
|
458 |
+
"loss": 2.4325,
|
459 |
"step": 62
|
460 |
},
|
461 |
{
|
462 |
+
"epoch": 0.126,
|
463 |
+
"grad_norm": 1.1737953424453735,
|
464 |
+
"learning_rate": 0.00036218132209150044,
|
465 |
+
"loss": 2.2653,
|
466 |
"step": 63
|
467 |
},
|
468 |
{
|
469 |
+
"epoch": 0.128,
|
470 |
+
"grad_norm": 0.7943472862243652,
|
471 |
+
"learning_rate": 0.00034549150281252633,
|
472 |
+
"loss": 2.6079,
|
473 |
"step": 64
|
474 |
},
|
475 |
{
|
476 |
+
"epoch": 0.13,
|
477 |
+
"grad_norm": 1.3269349336624146,
|
478 |
+
"learning_rate": 0.0003289899283371657,
|
479 |
+
"loss": 2.3745,
|
480 |
"step": 65
|
481 |
},
|
482 |
{
|
483 |
+
"epoch": 0.132,
|
484 |
+
"grad_norm": 0.8898394107818604,
|
485 |
+
"learning_rate": 0.00031269670329204396,
|
486 |
+
"loss": 2.3862,
|
487 |
"step": 66
|
488 |
},
|
489 |
{
|
490 |
+
"epoch": 0.134,
|
491 |
+
"grad_norm": 0.8309778571128845,
|
492 |
+
"learning_rate": 0.0002966316784621,
|
493 |
+
"loss": 2.5131,
|
494 |
"step": 67
|
495 |
},
|
496 |
{
|
497 |
+
"epoch": 0.136,
|
498 |
+
"grad_norm": 1.2103646993637085,
|
499 |
+
"learning_rate": 0.00028081442660546124,
|
500 |
+
"loss": 2.5138,
|
501 |
"step": 68
|
502 |
},
|
503 |
{
|
504 |
+
"epoch": 0.138,
|
505 |
+
"grad_norm": 0.9281813502311707,
|
506 |
+
"learning_rate": 0.00026526421860705474,
|
507 |
+
"loss": 2.5798,
|
508 |
"step": 69
|
509 |
},
|
510 |
{
|
511 |
+
"epoch": 0.14,
|
512 |
+
"grad_norm": 0.8275775909423828,
|
513 |
+
"learning_rate": 0.0002500000000000001,
|
514 |
+
"loss": 2.5348,
|
515 |
"step": 70
|
516 |
},
|
517 |
{
|
518 |
+
"epoch": 0.142,
|
519 |
+
"grad_norm": 1.5009329319000244,
|
520 |
+
"learning_rate": 0.0002350403678833976,
|
521 |
+
"loss": 2.5156,
|
522 |
"step": 71
|
523 |
},
|
524 |
{
|
525 |
+
"epoch": 0.144,
|
526 |
+
"grad_norm": 1.4796998500823975,
|
527 |
+
"learning_rate": 0.00022040354826462666,
|
528 |
+
"loss": 2.3567,
|
529 |
"step": 72
|
530 |
},
|
531 |
{
|
532 |
+
"epoch": 0.146,
|
533 |
+
"grad_norm": 0.7437081933021545,
|
534 |
+
"learning_rate": 0.00020610737385376348,
|
535 |
+
"loss": 2.4399,
|
536 |
"step": 73
|
537 |
},
|
538 |
{
|
539 |
+
"epoch": 0.148,
|
540 |
+
"grad_norm": 0.7033576369285583,
|
541 |
+
"learning_rate": 0.00019216926233717085,
|
542 |
+
"loss": 2.3149,
|
543 |
"step": 74
|
544 |
},
|
545 |
{
|
546 |
+
"epoch": 0.15,
|
547 |
+
"grad_norm": 0.9651651978492737,
|
548 |
+
"learning_rate": 0.0001786061951567303,
|
549 |
+
"loss": 2.5816,
|
550 |
"step": 75
|
551 |
},
|
552 |
{
|
553 |
+
"epoch": 0.152,
|
554 |
+
"grad_norm": 1.0059478282928467,
|
555 |
+
"learning_rate": 0.00016543469682057105,
|
556 |
+
"loss": 2.6395,
|
557 |
"step": 76
|
558 |
},
|
559 |
{
|
560 |
+
"epoch": 0.154,
|
561 |
+
"grad_norm": 1.6795697212219238,
|
562 |
+
"learning_rate": 0.00015267081477050133,
|
563 |
+
"loss": 2.3551,
|
564 |
"step": 77
|
565 |
},
|
566 |
{
|
567 |
+
"epoch": 0.156,
|
568 |
+
"grad_norm": 0.7962441444396973,
|
569 |
+
"learning_rate": 0.00014033009983067452,
|
570 |
+
"loss": 2.2151,
|
571 |
"step": 78
|
572 |
},
|
573 |
{
|
574 |
+
"epoch": 0.158,
|
575 |
+
"grad_norm": 0.880089282989502,
|
576 |
+
"learning_rate": 0.00012842758726130281,
|
577 |
+
"loss": 2.4376,
|
578 |
"step": 79
|
579 |
},
|
580 |
{
|
581 |
+
"epoch": 0.16,
|
582 |
+
"grad_norm": 1.0629572868347168,
|
583 |
+
"learning_rate": 0.00011697777844051105,
|
584 |
+
"loss": 2.6063,
|
585 |
"step": 80
|
586 |
},
|
587 |
{
|
588 |
+
"epoch": 0.162,
|
589 |
+
"grad_norm": 0.8691402077674866,
|
590 |
+
"learning_rate": 0.00010599462319663906,
|
591 |
+
"loss": 2.4764,
|
592 |
"step": 81
|
593 |
},
|
594 |
{
|
595 |
+
"epoch": 0.164,
|
596 |
+
"grad_norm": 0.8258126378059387,
|
597 |
+
"learning_rate": 9.549150281252633e-05,
|
598 |
+
"loss": 2.3996,
|
599 |
"step": 82
|
600 |
},
|
601 |
{
|
602 |
+
"epoch": 0.166,
|
603 |
+
"grad_norm": 2.253006935119629,
|
604 |
+
"learning_rate": 8.548121372247918e-05,
|
605 |
+
"loss": 2.7106,
|
606 |
"step": 83
|
607 |
},
|
608 |
{
|
609 |
+
"epoch": 0.168,
|
610 |
+
"grad_norm": 0.9351361393928528,
|
611 |
+
"learning_rate": 7.597595192178702e-05,
|
612 |
+
"loss": 2.3613,
|
613 |
"step": 84
|
614 |
},
|
615 |
{
|
616 |
+
"epoch": 0.17,
|
617 |
+
"grad_norm": 0.8624694347381592,
|
618 |
+
"learning_rate": 6.698729810778065e-05,
|
619 |
+
"loss": 2.4328,
|
620 |
"step": 85
|
621 |
},
|
622 |
{
|
623 |
+
"epoch": 0.172,
|
624 |
+
"grad_norm": 0.6949071884155273,
|
625 |
+
"learning_rate": 5.852620357053651e-05,
|
626 |
+
"loss": 2.4157,
|
627 |
"step": 86
|
628 |
},
|
629 |
{
|
630 |
+
"epoch": 0.174,
|
631 |
+
"grad_norm": 0.7830259203910828,
|
632 |
+
"learning_rate": 5.060297685041659e-05,
|
633 |
+
"loss": 2.2797,
|
634 |
"step": 87
|
635 |
},
|
636 |
{
|
637 |
+
"epoch": 0.176,
|
638 |
+
"grad_norm": 1.3727121353149414,
|
639 |
+
"learning_rate": 4.322727117869951e-05,
|
640 |
+
"loss": 2.6155,
|
641 |
"step": 88
|
642 |
},
|
643 |
{
|
644 |
+
"epoch": 0.178,
|
645 |
+
"grad_norm": 0.6731472611427307,
|
646 |
+
"learning_rate": 3.6408072716606344e-05,
|
647 |
+
"loss": 2.4149,
|
648 |
"step": 89
|
649 |
},
|
650 |
{
|
651 |
+
"epoch": 0.18,
|
652 |
+
"grad_norm": 0.846976101398468,
|
653 |
+
"learning_rate": 3.0153689607045842e-05,
|
654 |
+
"loss": 2.3137,
|
655 |
"step": 90
|
656 |
},
|
657 |
{
|
658 |
+
"epoch": 0.182,
|
659 |
+
"grad_norm": 0.9294453859329224,
|
660 |
+
"learning_rate": 2.4471741852423235e-05,
|
661 |
+
"loss": 2.5798,
|
662 |
"step": 91
|
663 |
},
|
664 |
{
|
665 |
+
"epoch": 0.184,
|
666 |
+
"grad_norm": 0.766918957233429,
|
667 |
+
"learning_rate": 1.9369152030840554e-05,
|
668 |
+
"loss": 2.6766,
|
669 |
"step": 92
|
670 |
},
|
671 |
{
|
672 |
+
"epoch": 0.186,
|
673 |
+
"grad_norm": 1.3079534769058228,
|
674 |
+
"learning_rate": 1.4852136862001764e-05,
|
675 |
+
"loss": 2.6047,
|
676 |
"step": 93
|
677 |
},
|
678 |
{
|
679 |
+
"epoch": 0.188,
|
680 |
+
"grad_norm": 1.1351994276046753,
|
681 |
+
"learning_rate": 1.0926199633097156e-05,
|
682 |
+
"loss": 2.6034,
|
683 |
"step": 94
|
684 |
},
|
685 |
{
|
686 |
+
"epoch": 0.19,
|
687 |
+
"grad_norm": 0.8010856509208679,
|
688 |
+
"learning_rate": 7.59612349389599e-06,
|
689 |
+
"loss": 2.2994,
|
690 |
"step": 95
|
691 |
},
|
692 |
{
|
693 |
+
"epoch": 0.192,
|
694 |
+
"grad_norm": 0.9184717535972595,
|
695 |
+
"learning_rate": 4.865965629214819e-06,
|
696 |
+
"loss": 2.5489,
|
697 |
"step": 96
|
698 |
},
|
699 |
{
|
700 |
+
"epoch": 0.194,
|
701 |
+
"grad_norm": 0.9543655514717102,
|
702 |
+
"learning_rate": 2.739052315863355e-06,
|
703 |
+
"loss": 2.5186,
|
704 |
"step": 97
|
705 |
},
|
706 |
{
|
707 |
+
"epoch": 0.196,
|
708 |
+
"grad_norm": 0.9216803908348083,
|
709 |
+
"learning_rate": 1.2179748700879012e-06,
|
710 |
+
"loss": 2.5627,
|
711 |
"step": 98
|
712 |
},
|
713 |
{
|
714 |
+
"epoch": 0.198,
|
715 |
+
"grad_norm": 0.8810911178588867,
|
716 |
+
"learning_rate": 3.0458649045211895e-07,
|
717 |
+
"loss": 2.6527,
|
718 |
"step": 99
|
719 |
},
|
720 |
{
|
721 |
+
"epoch": 0.2,
|
722 |
+
"grad_norm": 0.7426478266716003,
|
723 |
"learning_rate": 0.0,
|
724 |
+
"loss": 2.1737,
|
725 |
"step": 100
|
726 |
},
|
727 |
{
|
728 |
+
"epoch": 0.2,
|
729 |
+
"eval_loss": 2.527949094772339,
|
730 |
+
"eval_runtime": 4.9855,
|
731 |
+
"eval_samples_per_second": 4.212,
|
732 |
+
"eval_steps_per_second": 4.212,
|
733 |
"step": 100
|
734 |
}
|
735 |
],
|
|
|
737 |
"max_steps": 100,
|
738 |
"num_input_tokens_seen": 0,
|
739 |
"num_train_epochs": 1,
|
740 |
+
"save_steps": 500,
|
741 |
"stateful_callbacks": {
|
742 |
"TrainerControl": {
|
743 |
"args": {
|
|
|
750 |
"attributes": {}
|
751 |
}
|
752 |
},
|
753 |
+
"total_flos": 1.62874924204032e+16,
|
754 |
"train_batch_size": 1,
|
755 |
"trial_name": null,
|
756 |
"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:
|
3 |
size 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8d9124138abd44af04b2c60a935bcab4ff5cdb3ea64e57559b87dc3f7e79065
|
3 |
size 6776
|