Uploaded checkpoint-1000
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- trainer_state.json +315 -315
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2836579040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0196c5ce80fd43262001640fe072b0ec28cd75bb43c932fcc335164a687a423
|
3 |
size 2836579040
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5673376169
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:836935c1112f5445cc74e15ee8ae5be94d2417e38d4506acd0b8491b620484e4
|
3 |
size 5673376169
|
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 sha256:51ec34ea8aede6091de0519b617851419190260c027c065a3f39a7503df0ada3
|
3 |
size 14244
|
trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 250,
|
6 |
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
@@ -10,734 +10,734 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 1.98e-05,
|
15 |
-
"loss":
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm":
|
21 |
"learning_rate": 1.9600000000000002e-05,
|
22 |
-
"loss": 1.
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.01,
|
27 |
-
"grad_norm":
|
28 |
"learning_rate": 1.94e-05,
|
29 |
-
"loss":
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.01,
|
34 |
-
"grad_norm":
|
35 |
"learning_rate": 1.9200000000000003e-05,
|
36 |
-
"loss":
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.01,
|
41 |
-
"grad_norm":
|
42 |
"learning_rate": 1.9e-05,
|
43 |
-
"loss": 1.
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.01,
|
48 |
-
"grad_norm":
|
49 |
"learning_rate": 1.88e-05,
|
50 |
-
"loss": 1.
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 0.
|
55 |
-
"grad_norm":
|
56 |
"learning_rate": 1.86e-05,
|
57 |
-
"loss": 1.
|
58 |
"step": 70
|
59 |
},
|
60 |
{
|
61 |
-
"epoch": 0.
|
62 |
-
"grad_norm":
|
63 |
"learning_rate": 1.8400000000000003e-05,
|
64 |
-
"loss":
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
-
"epoch": 0.
|
69 |
-
"grad_norm":
|
70 |
"learning_rate": 1.8200000000000002e-05,
|
71 |
-
"loss":
|
72 |
"step": 90
|
73 |
},
|
74 |
{
|
75 |
-
"epoch": 0.
|
76 |
-
"grad_norm":
|
77 |
"learning_rate": 1.8e-05,
|
78 |
-
"loss": 1.
|
79 |
"step": 100
|
80 |
},
|
81 |
{
|
82 |
-
"epoch": 0.
|
83 |
-
"grad_norm":
|
84 |
"learning_rate": 1.7800000000000002e-05,
|
85 |
-
"loss": 1.
|
86 |
"step": 110
|
87 |
},
|
88 |
{
|
89 |
-
"epoch": 0.
|
90 |
-
"grad_norm":
|
91 |
"learning_rate": 1.76e-05,
|
92 |
-
"loss": 1.
|
93 |
"step": 120
|
94 |
},
|
95 |
{
|
96 |
-
"epoch": 0.
|
97 |
-
"grad_norm":
|
98 |
"learning_rate": 1.7400000000000003e-05,
|
99 |
-
"loss":
|
100 |
"step": 130
|
101 |
},
|
102 |
{
|
103 |
-
"epoch": 0.
|
104 |
-
"grad_norm":
|
105 |
"learning_rate": 1.72e-05,
|
106 |
-
"loss": 1.
|
107 |
"step": 140
|
108 |
},
|
109 |
{
|
110 |
-
"epoch": 0.
|
111 |
-
"grad_norm":
|
112 |
"learning_rate": 1.7e-05,
|
113 |
-
"loss":
|
114 |
"step": 150
|
115 |
},
|
116 |
{
|
117 |
-
"epoch": 0.
|
118 |
-
"grad_norm":
|
119 |
"learning_rate": 1.6800000000000002e-05,
|
120 |
-
"loss": 1.
|
121 |
"step": 160
|
122 |
},
|
123 |
{
|
124 |
-
"epoch": 0.
|
125 |
-
"grad_norm":
|
126 |
"learning_rate": 1.66e-05,
|
127 |
-
"loss": 1.
|
128 |
"step": 170
|
129 |
},
|
130 |
{
|
131 |
-
"epoch": 0.
|
132 |
-
"grad_norm":
|
133 |
"learning_rate": 1.64e-05,
|
134 |
-
"loss":
|
135 |
"step": 180
|
136 |
},
|
137 |
{
|
138 |
-
"epoch": 0.
|
139 |
-
"grad_norm":
|
140 |
"learning_rate": 1.62e-05,
|
141 |
-
"loss":
|
142 |
"step": 190
|
143 |
},
|
144 |
{
|
145 |
-
"epoch": 0.
|
146 |
-
"grad_norm":
|
147 |
"learning_rate": 1.6000000000000003e-05,
|
148 |
-
"loss":
|
149 |
"step": 200
|
150 |
},
|
151 |
{
|
152 |
-
"epoch": 0.
|
153 |
-
"grad_norm":
|
154 |
"learning_rate": 1.58e-05,
|
155 |
-
"loss": 1.
|
156 |
"step": 210
|
157 |
},
|
158 |
{
|
159 |
-
"epoch": 0.
|
160 |
-
"grad_norm":
|
161 |
"learning_rate": 1.5600000000000003e-05,
|
162 |
-
"loss":
|
163 |
"step": 220
|
164 |
},
|
165 |
{
|
166 |
-
"epoch": 0.
|
167 |
-
"grad_norm":
|
168 |
"learning_rate": 1.54e-05,
|
169 |
-
"loss":
|
170 |
"step": 230
|
171 |
},
|
172 |
{
|
173 |
-
"epoch": 0.
|
174 |
-
"grad_norm":
|
175 |
"learning_rate": 1.5200000000000002e-05,
|
176 |
-
"loss": 1.
|
177 |
"step": 240
|
178 |
},
|
179 |
{
|
180 |
-
"epoch": 0.
|
181 |
-
"grad_norm":
|
182 |
"learning_rate": 1.5000000000000002e-05,
|
183 |
-
"loss": 1.
|
184 |
"step": 250
|
185 |
},
|
186 |
{
|
187 |
-
"epoch": 0.
|
188 |
-
"eval_loss": 1.
|
189 |
-
"eval_runtime": 30.
|
190 |
-
"eval_samples_per_second": 33.
|
191 |
-
"eval_steps_per_second": 33.
|
192 |
"step": 250
|
193 |
},
|
194 |
{
|
195 |
-
"epoch": 0.
|
196 |
-
"grad_norm":
|
197 |
"learning_rate": 1.48e-05,
|
198 |
-
"loss":
|
199 |
"step": 260
|
200 |
},
|
201 |
{
|
202 |
-
"epoch": 0.
|
203 |
-
"grad_norm":
|
204 |
"learning_rate": 1.46e-05,
|
205 |
-
"loss": 1.
|
206 |
"step": 270
|
207 |
},
|
208 |
{
|
209 |
-
"epoch": 0.
|
210 |
-
"grad_norm":
|
211 |
"learning_rate": 1.4400000000000001e-05,
|
212 |
-
"loss": 1.
|
213 |
"step": 280
|
214 |
},
|
215 |
{
|
216 |
-
"epoch": 0.
|
217 |
-
"grad_norm":
|
218 |
"learning_rate": 1.4200000000000001e-05,
|
219 |
-
"loss": 1.
|
220 |
"step": 290
|
221 |
},
|
222 |
{
|
223 |
-
"epoch": 0.
|
224 |
-
"grad_norm":
|
225 |
"learning_rate": 1.4e-05,
|
226 |
-
"loss": 1.
|
227 |
"step": 300
|
228 |
},
|
229 |
{
|
230 |
-
"epoch": 0.
|
231 |
-
"grad_norm":
|
232 |
"learning_rate": 1.38e-05,
|
233 |
-
"loss": 1.
|
234 |
"step": 310
|
235 |
},
|
236 |
{
|
237 |
-
"epoch": 0.
|
238 |
-
"grad_norm":
|
239 |
"learning_rate": 1.3600000000000002e-05,
|
240 |
-
"loss": 1.
|
241 |
"step": 320
|
242 |
},
|
243 |
{
|
244 |
-
"epoch": 0.
|
245 |
-
"grad_norm":
|
246 |
"learning_rate": 1.3400000000000002e-05,
|
247 |
-
"loss": 1.
|
248 |
"step": 330
|
249 |
},
|
250 |
{
|
251 |
-
"epoch": 0.
|
252 |
-
"grad_norm": 9.
|
253 |
"learning_rate": 1.3200000000000002e-05,
|
254 |
-
"loss": 1.
|
255 |
"step": 340
|
256 |
},
|
257 |
{
|
258 |
-
"epoch": 0.
|
259 |
-
"grad_norm":
|
260 |
"learning_rate": 1.3000000000000001e-05,
|
261 |
-
"loss": 1.
|
262 |
"step": 350
|
263 |
},
|
264 |
{
|
265 |
-
"epoch": 0.
|
266 |
-
"grad_norm":
|
267 |
"learning_rate": 1.2800000000000001e-05,
|
268 |
-
"loss": 1.
|
269 |
"step": 360
|
270 |
},
|
271 |
{
|
272 |
-
"epoch": 0.
|
273 |
-
"grad_norm":
|
274 |
"learning_rate": 1.2600000000000001e-05,
|
275 |
-
"loss": 1.
|
276 |
"step": 370
|
277 |
},
|
278 |
{
|
279 |
-
"epoch": 0.
|
280 |
-
"grad_norm":
|
281 |
"learning_rate": 1.2400000000000002e-05,
|
282 |
-
"loss": 1.
|
283 |
"step": 380
|
284 |
},
|
285 |
{
|
286 |
-
"epoch": 0.
|
287 |
-
"grad_norm":
|
288 |
"learning_rate": 1.22e-05,
|
289 |
-
"loss":
|
290 |
"step": 390
|
291 |
},
|
292 |
{
|
293 |
-
"epoch": 0.
|
294 |
-
"grad_norm":
|
295 |
"learning_rate": 1.2e-05,
|
296 |
-
"loss": 1.
|
297 |
"step": 400
|
298 |
},
|
299 |
{
|
300 |
-
"epoch": 0.
|
301 |
-
"grad_norm":
|
302 |
"learning_rate": 1.18e-05,
|
303 |
-
"loss":
|
304 |
"step": 410
|
305 |
},
|
306 |
{
|
307 |
-
"epoch": 0.
|
308 |
-
"grad_norm":
|
309 |
"learning_rate": 1.16e-05,
|
310 |
-
"loss": 1.
|
311 |
"step": 420
|
312 |
},
|
313 |
{
|
314 |
-
"epoch": 0.
|
315 |
-
"grad_norm": 8.
|
316 |
"learning_rate": 1.14e-05,
|
317 |
-
"loss": 1.
|
318 |
"step": 430
|
319 |
},
|
320 |
{
|
321 |
-
"epoch": 0.
|
322 |
-
"grad_norm":
|
323 |
"learning_rate": 1.1200000000000001e-05,
|
324 |
-
"loss": 1.
|
325 |
"step": 440
|
326 |
},
|
327 |
{
|
328 |
-
"epoch": 0.
|
329 |
-
"grad_norm":
|
330 |
"learning_rate": 1.1000000000000001e-05,
|
331 |
-
"loss": 1.
|
332 |
"step": 450
|
333 |
},
|
334 |
{
|
335 |
-
"epoch": 0.
|
336 |
-
"grad_norm":
|
337 |
"learning_rate": 1.0800000000000002e-05,
|
338 |
-
"loss": 1.
|
339 |
"step": 460
|
340 |
},
|
341 |
{
|
342 |
-
"epoch": 0.
|
343 |
-
"grad_norm":
|
344 |
"learning_rate": 1.0600000000000002e-05,
|
345 |
-
"loss": 1.
|
346 |
"step": 470
|
347 |
},
|
348 |
{
|
349 |
-
"epoch": 0.
|
350 |
-
"grad_norm":
|
351 |
"learning_rate": 1.04e-05,
|
352 |
-
"loss": 1.
|
353 |
"step": 480
|
354 |
},
|
355 |
{
|
356 |
-
"epoch": 0.
|
357 |
-
"grad_norm":
|
358 |
"learning_rate": 1.02e-05,
|
359 |
-
"loss": 1.
|
360 |
"step": 490
|
361 |
},
|
362 |
{
|
363 |
-
"epoch": 0.
|
364 |
-
"grad_norm":
|
365 |
"learning_rate": 1e-05,
|
366 |
-
"loss": 1.
|
367 |
"step": 500
|
368 |
},
|
369 |
{
|
370 |
-
"epoch": 0.
|
371 |
-
"eval_loss": 1.
|
372 |
-
"eval_runtime": 30.
|
373 |
-
"eval_samples_per_second": 33.
|
374 |
-
"eval_steps_per_second": 33.
|
375 |
"step": 500
|
376 |
},
|
377 |
{
|
378 |
-
"epoch": 0.
|
379 |
-
"grad_norm":
|
380 |
"learning_rate": 9.800000000000001e-06,
|
381 |
-
"loss":
|
382 |
"step": 510
|
383 |
},
|
384 |
{
|
385 |
-
"epoch": 0.
|
386 |
-
"grad_norm": 12.
|
387 |
"learning_rate": 9.600000000000001e-06,
|
388 |
-
"loss": 1.
|
389 |
"step": 520
|
390 |
},
|
391 |
{
|
392 |
-
"epoch": 0.
|
393 |
-
"grad_norm":
|
394 |
"learning_rate": 9.4e-06,
|
395 |
-
"loss": 1.
|
396 |
"step": 530
|
397 |
},
|
398 |
{
|
399 |
-
"epoch": 0.
|
400 |
-
"grad_norm":
|
401 |
"learning_rate": 9.200000000000002e-06,
|
402 |
-
"loss": 1.
|
403 |
"step": 540
|
404 |
},
|
405 |
{
|
406 |
-
"epoch": 0.
|
407 |
-
"grad_norm":
|
408 |
"learning_rate": 9e-06,
|
409 |
-
"loss": 1.
|
410 |
"step": 550
|
411 |
},
|
412 |
{
|
413 |
-
"epoch": 0.
|
414 |
-
"grad_norm":
|
415 |
"learning_rate": 8.8e-06,
|
416 |
-
"loss": 1.
|
417 |
"step": 560
|
418 |
},
|
419 |
{
|
420 |
-
"epoch": 0.
|
421 |
-
"grad_norm": 9.
|
422 |
"learning_rate": 8.6e-06,
|
423 |
-
"loss":
|
424 |
"step": 570
|
425 |
},
|
426 |
{
|
427 |
-
"epoch": 0.
|
428 |
-
"grad_norm":
|
429 |
"learning_rate": 8.400000000000001e-06,
|
430 |
-
"loss": 1.
|
431 |
"step": 580
|
432 |
},
|
433 |
{
|
434 |
-
"epoch": 0.
|
435 |
-
"grad_norm":
|
436 |
"learning_rate": 8.2e-06,
|
437 |
-
"loss": 1.
|
438 |
"step": 590
|
439 |
},
|
440 |
{
|
441 |
-
"epoch": 0.
|
442 |
-
"grad_norm": 10.
|
443 |
"learning_rate": 8.000000000000001e-06,
|
444 |
-
"loss": 1.
|
445 |
"step": 600
|
446 |
},
|
447 |
{
|
448 |
-
"epoch": 0.
|
449 |
-
"grad_norm":
|
450 |
"learning_rate": 7.800000000000002e-06,
|
451 |
-
"loss": 1.
|
452 |
"step": 610
|
453 |
},
|
454 |
{
|
455 |
-
"epoch": 0.
|
456 |
-
"grad_norm":
|
457 |
"learning_rate": 7.600000000000001e-06,
|
458 |
-
"loss":
|
459 |
"step": 620
|
460 |
},
|
461 |
{
|
462 |
-
"epoch": 0.
|
463 |
-
"grad_norm":
|
464 |
"learning_rate": 7.4e-06,
|
465 |
-
"loss": 1.
|
466 |
"step": 630
|
467 |
},
|
468 |
{
|
469 |
-
"epoch": 0.
|
470 |
-
"grad_norm": 10.
|
471 |
"learning_rate": 7.2000000000000005e-06,
|
472 |
-
"loss":
|
473 |
"step": 640
|
474 |
},
|
475 |
{
|
476 |
-
"epoch": 0.
|
477 |
-
"grad_norm":
|
478 |
"learning_rate": 7e-06,
|
479 |
-
"loss": 1.
|
480 |
"step": 650
|
481 |
},
|
482 |
{
|
483 |
-
"epoch": 0.
|
484 |
-
"grad_norm":
|
485 |
"learning_rate": 6.800000000000001e-06,
|
486 |
-
"loss":
|
487 |
"step": 660
|
488 |
},
|
489 |
{
|
490 |
-
"epoch": 0.
|
491 |
-
"grad_norm":
|
492 |
"learning_rate": 6.600000000000001e-06,
|
493 |
-
"loss":
|
494 |
"step": 670
|
495 |
},
|
496 |
{
|
497 |
-
"epoch": 0.
|
498 |
-
"grad_norm":
|
499 |
"learning_rate": 6.4000000000000006e-06,
|
500 |
-
"loss": 1.
|
501 |
"step": 680
|
502 |
},
|
503 |
{
|
504 |
-
"epoch": 0.
|
505 |
-
"grad_norm": 11.
|
506 |
"learning_rate": 6.200000000000001e-06,
|
507 |
-
"loss":
|
508 |
"step": 690
|
509 |
},
|
510 |
{
|
511 |
-
"epoch": 0.
|
512 |
-
"grad_norm":
|
513 |
"learning_rate": 6e-06,
|
514 |
-
"loss": 1.
|
515 |
"step": 700
|
516 |
},
|
517 |
{
|
518 |
-
"epoch": 0.
|
519 |
-
"grad_norm":
|
520 |
"learning_rate": 5.8e-06,
|
521 |
-
"loss": 1.
|
522 |
"step": 710
|
523 |
},
|
524 |
{
|
525 |
-
"epoch": 0.
|
526 |
-
"grad_norm":
|
527 |
"learning_rate": 5.600000000000001e-06,
|
528 |
-
"loss":
|
529 |
"step": 720
|
530 |
},
|
531 |
{
|
532 |
-
"epoch": 0.
|
533 |
-
"grad_norm": 9.
|
534 |
"learning_rate": 5.400000000000001e-06,
|
535 |
-
"loss": 1.
|
536 |
"step": 730
|
537 |
},
|
538 |
{
|
539 |
-
"epoch": 0.
|
540 |
-
"grad_norm":
|
541 |
"learning_rate": 5.2e-06,
|
542 |
-
"loss": 1.
|
543 |
"step": 740
|
544 |
},
|
545 |
{
|
546 |
-
"epoch": 0.
|
547 |
-
"grad_norm":
|
548 |
"learning_rate": 5e-06,
|
549 |
-
"loss": 1.
|
550 |
"step": 750
|
551 |
},
|
552 |
{
|
553 |
-
"epoch": 0.
|
554 |
-
"eval_loss": 1.
|
555 |
-
"eval_runtime":
|
556 |
-
"eval_samples_per_second": 33.
|
557 |
-
"eval_steps_per_second": 33.
|
558 |
"step": 750
|
559 |
},
|
560 |
{
|
561 |
-
"epoch": 0.
|
562 |
-
"grad_norm": 11.
|
563 |
"learning_rate": 4.800000000000001e-06,
|
564 |
-
"loss": 1.
|
565 |
"step": 760
|
566 |
},
|
567 |
{
|
568 |
-
"epoch": 0.
|
569 |
-
"grad_norm":
|
570 |
"learning_rate": 4.600000000000001e-06,
|
571 |
-
"loss": 1.
|
572 |
"step": 770
|
573 |
},
|
574 |
{
|
575 |
-
"epoch": 0.
|
576 |
-
"grad_norm":
|
577 |
"learning_rate": 4.4e-06,
|
578 |
-
"loss": 1.
|
579 |
"step": 780
|
580 |
},
|
581 |
{
|
582 |
-
"epoch": 0.
|
583 |
-
"grad_norm":
|
584 |
"learning_rate": 4.2000000000000004e-06,
|
585 |
-
"loss": 1.
|
586 |
"step": 790
|
587 |
},
|
588 |
{
|
589 |
-
"epoch": 0.
|
590 |
-
"grad_norm":
|
591 |
"learning_rate": 4.000000000000001e-06,
|
592 |
-
"loss": 1.
|
593 |
"step": 800
|
594 |
},
|
595 |
{
|
596 |
-
"epoch": 0.
|
597 |
-
"grad_norm":
|
598 |
"learning_rate": 3.8000000000000005e-06,
|
599 |
-
"loss": 1.
|
600 |
"step": 810
|
601 |
},
|
602 |
{
|
603 |
-
"epoch": 0.
|
604 |
-
"grad_norm":
|
605 |
"learning_rate": 3.6000000000000003e-06,
|
606 |
-
"loss": 1.
|
607 |
"step": 820
|
608 |
},
|
609 |
{
|
610 |
-
"epoch": 0.
|
611 |
-
"grad_norm": 8.
|
612 |
"learning_rate": 3.4000000000000005e-06,
|
613 |
-
"loss": 1.
|
614 |
"step": 830
|
615 |
},
|
616 |
{
|
617 |
-
"epoch": 0.
|
618 |
-
"grad_norm":
|
619 |
"learning_rate": 3.2000000000000003e-06,
|
620 |
-
"loss": 1.
|
621 |
"step": 840
|
622 |
},
|
623 |
{
|
624 |
-
"epoch": 0.
|
625 |
-
"grad_norm":
|
626 |
"learning_rate": 3e-06,
|
627 |
-
"loss": 1.
|
628 |
"step": 850
|
629 |
},
|
630 |
{
|
631 |
-
"epoch": 0.
|
632 |
-
"grad_norm":
|
633 |
"learning_rate": 2.8000000000000003e-06,
|
634 |
-
"loss": 1.
|
635 |
"step": 860
|
636 |
},
|
637 |
{
|
638 |
-
"epoch": 0.
|
639 |
-
"grad_norm":
|
640 |
"learning_rate": 2.6e-06,
|
641 |
-
"loss": 1.
|
642 |
"step": 870
|
643 |
},
|
644 |
{
|
645 |
-
"epoch": 0.
|
646 |
-
"grad_norm":
|
647 |
"learning_rate": 2.4000000000000003e-06,
|
648 |
-
"loss": 1.
|
649 |
"step": 880
|
650 |
},
|
651 |
{
|
652 |
-
"epoch": 0.
|
653 |
-
"grad_norm":
|
654 |
"learning_rate": 2.2e-06,
|
655 |
-
"loss": 1.
|
656 |
"step": 890
|
657 |
},
|
658 |
{
|
659 |
-
"epoch": 0.
|
660 |
-
"grad_norm":
|
661 |
"learning_rate": 2.0000000000000003e-06,
|
662 |
-
"loss": 1.
|
663 |
"step": 900
|
664 |
},
|
665 |
{
|
666 |
-
"epoch": 0.
|
667 |
-
"grad_norm": 10.
|
668 |
"learning_rate": 1.8000000000000001e-06,
|
669 |
-
"loss": 1.
|
670 |
"step": 910
|
671 |
},
|
672 |
{
|
673 |
-
"epoch": 0.
|
674 |
-
"grad_norm": 12.
|
675 |
"learning_rate": 1.6000000000000001e-06,
|
676 |
-
"loss": 1.
|
677 |
"step": 920
|
678 |
},
|
679 |
{
|
680 |
-
"epoch": 0.
|
681 |
-
"grad_norm":
|
682 |
"learning_rate": 1.4000000000000001e-06,
|
683 |
-
"loss": 1.
|
684 |
"step": 930
|
685 |
},
|
686 |
{
|
687 |
-
"epoch": 0.
|
688 |
-
"grad_norm":
|
689 |
"learning_rate": 1.2000000000000002e-06,
|
690 |
-
"loss": 1.
|
691 |
"step": 940
|
692 |
},
|
693 |
{
|
694 |
-
"epoch": 0.
|
695 |
-
"grad_norm":
|
696 |
"learning_rate": 1.0000000000000002e-06,
|
697 |
-
"loss":
|
698 |
"step": 950
|
699 |
},
|
700 |
{
|
701 |
-
"epoch": 0.
|
702 |
-
"grad_norm":
|
703 |
"learning_rate": 8.000000000000001e-07,
|
704 |
-
"loss": 1.
|
705 |
"step": 960
|
706 |
},
|
707 |
{
|
708 |
-
"epoch": 0.
|
709 |
"grad_norm": 10.6875,
|
710 |
"learning_rate": 6.000000000000001e-07,
|
711 |
-
"loss": 1.
|
712 |
"step": 970
|
713 |
},
|
714 |
{
|
715 |
-
"epoch": 0.
|
716 |
-
"grad_norm":
|
717 |
"learning_rate": 4.0000000000000003e-07,
|
718 |
-
"loss": 1.
|
719 |
"step": 980
|
720 |
},
|
721 |
{
|
722 |
-
"epoch": 0.
|
723 |
-
"grad_norm":
|
724 |
"learning_rate": 2.0000000000000002e-07,
|
725 |
-
"loss":
|
726 |
"step": 990
|
727 |
},
|
728 |
{
|
729 |
-
"epoch": 0.
|
730 |
-
"grad_norm":
|
731 |
"learning_rate": 0.0,
|
732 |
-
"loss": 1.
|
733 |
"step": 1000
|
734 |
},
|
735 |
{
|
736 |
-
"epoch": 0.
|
737 |
-
"eval_loss": 1.
|
738 |
-
"eval_runtime": 30.
|
739 |
-
"eval_samples_per_second": 33.
|
740 |
-
"eval_steps_per_second": 33.
|
741 |
"step": 1000
|
742 |
}
|
743 |
],
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.16666666666666666,
|
5 |
"eval_steps": 250,
|
6 |
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
+
"grad_norm": 8.4375,
|
14 |
"learning_rate": 1.98e-05,
|
15 |
+
"loss": 1.6341,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 7.34375,
|
21 |
"learning_rate": 1.9600000000000002e-05,
|
22 |
+
"loss": 1.8818,
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.01,
|
27 |
+
"grad_norm": 9.4375,
|
28 |
"learning_rate": 1.94e-05,
|
29 |
+
"loss": 2.2104,
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.01,
|
34 |
+
"grad_norm": 9.0625,
|
35 |
"learning_rate": 1.9200000000000003e-05,
|
36 |
+
"loss": 2.0186,
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.01,
|
41 |
+
"grad_norm": 10.0625,
|
42 |
"learning_rate": 1.9e-05,
|
43 |
+
"loss": 1.7541,
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.01,
|
48 |
+
"grad_norm": 10.0,
|
49 |
"learning_rate": 1.88e-05,
|
50 |
+
"loss": 1.8193,
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.01,
|
55 |
+
"grad_norm": 6.71875,
|
56 |
"learning_rate": 1.86e-05,
|
57 |
+
"loss": 1.9009,
|
58 |
"step": 70
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 0.01,
|
62 |
+
"grad_norm": 11.625,
|
63 |
"learning_rate": 1.8400000000000003e-05,
|
64 |
+
"loss": 1.666,
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 0.01,
|
69 |
+
"grad_norm": 10.4375,
|
70 |
"learning_rate": 1.8200000000000002e-05,
|
71 |
+
"loss": 2.0143,
|
72 |
"step": 90
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 0.02,
|
76 |
+
"grad_norm": 9.0625,
|
77 |
"learning_rate": 1.8e-05,
|
78 |
+
"loss": 1.4298,
|
79 |
"step": 100
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 0.02,
|
83 |
+
"grad_norm": 6.03125,
|
84 |
"learning_rate": 1.7800000000000002e-05,
|
85 |
+
"loss": 1.995,
|
86 |
"step": 110
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 0.02,
|
90 |
+
"grad_norm": 9.1875,
|
91 |
"learning_rate": 1.76e-05,
|
92 |
+
"loss": 1.9436,
|
93 |
"step": 120
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 0.02,
|
97 |
+
"grad_norm": 8.125,
|
98 |
"learning_rate": 1.7400000000000003e-05,
|
99 |
+
"loss": 2.1217,
|
100 |
"step": 130
|
101 |
},
|
102 |
{
|
103 |
+
"epoch": 0.02,
|
104 |
+
"grad_norm": 11.0625,
|
105 |
"learning_rate": 1.72e-05,
|
106 |
+
"loss": 1.6722,
|
107 |
"step": 140
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 0.03,
|
111 |
+
"grad_norm": 8.4375,
|
112 |
"learning_rate": 1.7e-05,
|
113 |
+
"loss": 2.353,
|
114 |
"step": 150
|
115 |
},
|
116 |
{
|
117 |
+
"epoch": 0.03,
|
118 |
+
"grad_norm": 18.75,
|
119 |
"learning_rate": 1.6800000000000002e-05,
|
120 |
+
"loss": 1.5962,
|
121 |
"step": 160
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 0.03,
|
125 |
+
"grad_norm": 8.875,
|
126 |
"learning_rate": 1.66e-05,
|
127 |
+
"loss": 1.8234,
|
128 |
"step": 170
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 0.03,
|
132 |
+
"grad_norm": 13.375,
|
133 |
"learning_rate": 1.64e-05,
|
134 |
+
"loss": 2.0789,
|
135 |
"step": 180
|
136 |
},
|
137 |
{
|
138 |
+
"epoch": 0.03,
|
139 |
+
"grad_norm": 7.875,
|
140 |
"learning_rate": 1.62e-05,
|
141 |
+
"loss": 2.0655,
|
142 |
"step": 190
|
143 |
},
|
144 |
{
|
145 |
+
"epoch": 0.03,
|
146 |
+
"grad_norm": 7.0,
|
147 |
"learning_rate": 1.6000000000000003e-05,
|
148 |
+
"loss": 1.6532,
|
149 |
"step": 200
|
150 |
},
|
151 |
{
|
152 |
+
"epoch": 0.04,
|
153 |
+
"grad_norm": 11.5625,
|
154 |
"learning_rate": 1.58e-05,
|
155 |
+
"loss": 1.5957,
|
156 |
"step": 210
|
157 |
},
|
158 |
{
|
159 |
+
"epoch": 0.04,
|
160 |
+
"grad_norm": 11.375,
|
161 |
"learning_rate": 1.5600000000000003e-05,
|
162 |
+
"loss": 1.907,
|
163 |
"step": 220
|
164 |
},
|
165 |
{
|
166 |
+
"epoch": 0.04,
|
167 |
+
"grad_norm": 8.5625,
|
168 |
"learning_rate": 1.54e-05,
|
169 |
+
"loss": 2.0679,
|
170 |
"step": 230
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 0.04,
|
174 |
+
"grad_norm": 6.53125,
|
175 |
"learning_rate": 1.5200000000000002e-05,
|
176 |
+
"loss": 1.6835,
|
177 |
"step": 240
|
178 |
},
|
179 |
{
|
180 |
+
"epoch": 0.04,
|
181 |
+
"grad_norm": 8.1875,
|
182 |
"learning_rate": 1.5000000000000002e-05,
|
183 |
+
"loss": 1.7236,
|
184 |
"step": 250
|
185 |
},
|
186 |
{
|
187 |
+
"epoch": 0.04,
|
188 |
+
"eval_loss": 1.8578436374664307,
|
189 |
+
"eval_runtime": 30.0677,
|
190 |
+
"eval_samples_per_second": 33.258,
|
191 |
+
"eval_steps_per_second": 33.258,
|
192 |
"step": 250
|
193 |
},
|
194 |
{
|
195 |
+
"epoch": 0.04,
|
196 |
+
"grad_norm": 10.375,
|
197 |
"learning_rate": 1.48e-05,
|
198 |
+
"loss": 2.0319,
|
199 |
"step": 260
|
200 |
},
|
201 |
{
|
202 |
+
"epoch": 0.04,
|
203 |
+
"grad_norm": 8.75,
|
204 |
"learning_rate": 1.46e-05,
|
205 |
+
"loss": 1.5004,
|
206 |
"step": 270
|
207 |
},
|
208 |
{
|
209 |
+
"epoch": 0.05,
|
210 |
+
"grad_norm": 8.5,
|
211 |
"learning_rate": 1.4400000000000001e-05,
|
212 |
+
"loss": 1.481,
|
213 |
"step": 280
|
214 |
},
|
215 |
{
|
216 |
+
"epoch": 0.05,
|
217 |
+
"grad_norm": 9.375,
|
218 |
"learning_rate": 1.4200000000000001e-05,
|
219 |
+
"loss": 1.7318,
|
220 |
"step": 290
|
221 |
},
|
222 |
{
|
223 |
+
"epoch": 0.05,
|
224 |
+
"grad_norm": 7.15625,
|
225 |
"learning_rate": 1.4e-05,
|
226 |
+
"loss": 1.6412,
|
227 |
"step": 300
|
228 |
},
|
229 |
{
|
230 |
+
"epoch": 0.05,
|
231 |
+
"grad_norm": 8.5,
|
232 |
"learning_rate": 1.38e-05,
|
233 |
+
"loss": 1.84,
|
234 |
"step": 310
|
235 |
},
|
236 |
{
|
237 |
+
"epoch": 0.05,
|
238 |
+
"grad_norm": 6.71875,
|
239 |
"learning_rate": 1.3600000000000002e-05,
|
240 |
+
"loss": 1.5797,
|
241 |
"step": 320
|
242 |
},
|
243 |
{
|
244 |
+
"epoch": 0.06,
|
245 |
+
"grad_norm": 8.625,
|
246 |
"learning_rate": 1.3400000000000002e-05,
|
247 |
+
"loss": 1.6014,
|
248 |
"step": 330
|
249 |
},
|
250 |
{
|
251 |
+
"epoch": 0.06,
|
252 |
+
"grad_norm": 9.1875,
|
253 |
"learning_rate": 1.3200000000000002e-05,
|
254 |
+
"loss": 1.9005,
|
255 |
"step": 340
|
256 |
},
|
257 |
{
|
258 |
+
"epoch": 0.06,
|
259 |
+
"grad_norm": 8.125,
|
260 |
"learning_rate": 1.3000000000000001e-05,
|
261 |
+
"loss": 1.6747,
|
262 |
"step": 350
|
263 |
},
|
264 |
{
|
265 |
+
"epoch": 0.06,
|
266 |
+
"grad_norm": 12.625,
|
267 |
"learning_rate": 1.2800000000000001e-05,
|
268 |
+
"loss": 1.8032,
|
269 |
"step": 360
|
270 |
},
|
271 |
{
|
272 |
+
"epoch": 0.06,
|
273 |
+
"grad_norm": 11.375,
|
274 |
"learning_rate": 1.2600000000000001e-05,
|
275 |
+
"loss": 1.665,
|
276 |
"step": 370
|
277 |
},
|
278 |
{
|
279 |
+
"epoch": 0.06,
|
280 |
+
"grad_norm": 6.0,
|
281 |
"learning_rate": 1.2400000000000002e-05,
|
282 |
+
"loss": 1.5209,
|
283 |
"step": 380
|
284 |
},
|
285 |
{
|
286 |
+
"epoch": 0.07,
|
287 |
+
"grad_norm": 9.375,
|
288 |
"learning_rate": 1.22e-05,
|
289 |
+
"loss": 2.0018,
|
290 |
"step": 390
|
291 |
},
|
292 |
{
|
293 |
+
"epoch": 0.07,
|
294 |
+
"grad_norm": 16.375,
|
295 |
"learning_rate": 1.2e-05,
|
296 |
+
"loss": 1.9263,
|
297 |
"step": 400
|
298 |
},
|
299 |
{
|
300 |
+
"epoch": 0.07,
|
301 |
+
"grad_norm": 9.5,
|
302 |
"learning_rate": 1.18e-05,
|
303 |
+
"loss": 1.7349,
|
304 |
"step": 410
|
305 |
},
|
306 |
{
|
307 |
+
"epoch": 0.07,
|
308 |
+
"grad_norm": 10.3125,
|
309 |
"learning_rate": 1.16e-05,
|
310 |
+
"loss": 1.9482,
|
311 |
"step": 420
|
312 |
},
|
313 |
{
|
314 |
+
"epoch": 0.07,
|
315 |
+
"grad_norm": 8.1875,
|
316 |
"learning_rate": 1.14e-05,
|
317 |
+
"loss": 1.6666,
|
318 |
"step": 430
|
319 |
},
|
320 |
{
|
321 |
+
"epoch": 0.07,
|
322 |
+
"grad_norm": 9.6875,
|
323 |
"learning_rate": 1.1200000000000001e-05,
|
324 |
+
"loss": 1.5945,
|
325 |
"step": 440
|
326 |
},
|
327 |
{
|
328 |
+
"epoch": 0.07,
|
329 |
+
"grad_norm": 13.125,
|
330 |
"learning_rate": 1.1000000000000001e-05,
|
331 |
+
"loss": 1.5596,
|
332 |
"step": 450
|
333 |
},
|
334 |
{
|
335 |
+
"epoch": 0.08,
|
336 |
+
"grad_norm": 14.0,
|
337 |
"learning_rate": 1.0800000000000002e-05,
|
338 |
+
"loss": 1.984,
|
339 |
"step": 460
|
340 |
},
|
341 |
{
|
342 |
+
"epoch": 0.08,
|
343 |
+
"grad_norm": 13.8125,
|
344 |
"learning_rate": 1.0600000000000002e-05,
|
345 |
+
"loss": 1.831,
|
346 |
"step": 470
|
347 |
},
|
348 |
{
|
349 |
+
"epoch": 0.08,
|
350 |
+
"grad_norm": 8.125,
|
351 |
"learning_rate": 1.04e-05,
|
352 |
+
"loss": 1.8916,
|
353 |
"step": 480
|
354 |
},
|
355 |
{
|
356 |
+
"epoch": 0.08,
|
357 |
+
"grad_norm": 10.1875,
|
358 |
"learning_rate": 1.02e-05,
|
359 |
+
"loss": 1.9689,
|
360 |
"step": 490
|
361 |
},
|
362 |
{
|
363 |
+
"epoch": 0.08,
|
364 |
+
"grad_norm": 10.3125,
|
365 |
"learning_rate": 1e-05,
|
366 |
+
"loss": 1.7186,
|
367 |
"step": 500
|
368 |
},
|
369 |
{
|
370 |
+
"epoch": 0.08,
|
371 |
+
"eval_loss": 1.7672193050384521,
|
372 |
+
"eval_runtime": 30.0143,
|
373 |
+
"eval_samples_per_second": 33.317,
|
374 |
+
"eval_steps_per_second": 33.317,
|
375 |
"step": 500
|
376 |
},
|
377 |
{
|
378 |
+
"epoch": 0.09,
|
379 |
+
"grad_norm": 8.75,
|
380 |
"learning_rate": 9.800000000000001e-06,
|
381 |
+
"loss": 2.1063,
|
382 |
"step": 510
|
383 |
},
|
384 |
{
|
385 |
+
"epoch": 0.09,
|
386 |
+
"grad_norm": 12.875,
|
387 |
"learning_rate": 9.600000000000001e-06,
|
388 |
+
"loss": 1.5813,
|
389 |
"step": 520
|
390 |
},
|
391 |
{
|
392 |
+
"epoch": 0.09,
|
393 |
+
"grad_norm": 6.0,
|
394 |
"learning_rate": 9.4e-06,
|
395 |
+
"loss": 1.8224,
|
396 |
"step": 530
|
397 |
},
|
398 |
{
|
399 |
+
"epoch": 0.09,
|
400 |
+
"grad_norm": 8.0625,
|
401 |
"learning_rate": 9.200000000000002e-06,
|
402 |
+
"loss": 1.8282,
|
403 |
"step": 540
|
404 |
},
|
405 |
{
|
406 |
+
"epoch": 0.09,
|
407 |
+
"grad_norm": 8.375,
|
408 |
"learning_rate": 9e-06,
|
409 |
+
"loss": 1.9588,
|
410 |
"step": 550
|
411 |
},
|
412 |
{
|
413 |
+
"epoch": 0.09,
|
414 |
+
"grad_norm": 7.125,
|
415 |
"learning_rate": 8.8e-06,
|
416 |
+
"loss": 1.9539,
|
417 |
"step": 560
|
418 |
},
|
419 |
{
|
420 |
+
"epoch": 0.1,
|
421 |
+
"grad_norm": 9.375,
|
422 |
"learning_rate": 8.6e-06,
|
423 |
+
"loss": 2.3026,
|
424 |
"step": 570
|
425 |
},
|
426 |
{
|
427 |
+
"epoch": 0.1,
|
428 |
+
"grad_norm": 10.875,
|
429 |
"learning_rate": 8.400000000000001e-06,
|
430 |
+
"loss": 1.7161,
|
431 |
"step": 580
|
432 |
},
|
433 |
{
|
434 |
+
"epoch": 0.1,
|
435 |
+
"grad_norm": 9.9375,
|
436 |
"learning_rate": 8.2e-06,
|
437 |
+
"loss": 1.9426,
|
438 |
"step": 590
|
439 |
},
|
440 |
{
|
441 |
+
"epoch": 0.1,
|
442 |
+
"grad_norm": 10.4375,
|
443 |
"learning_rate": 8.000000000000001e-06,
|
444 |
+
"loss": 1.52,
|
445 |
"step": 600
|
446 |
},
|
447 |
{
|
448 |
+
"epoch": 0.1,
|
449 |
+
"grad_norm": 9.125,
|
450 |
"learning_rate": 7.800000000000002e-06,
|
451 |
+
"loss": 1.3651,
|
452 |
"step": 610
|
453 |
},
|
454 |
{
|
455 |
+
"epoch": 0.1,
|
456 |
+
"grad_norm": 20.375,
|
457 |
"learning_rate": 7.600000000000001e-06,
|
458 |
+
"loss": 2.0648,
|
459 |
"step": 620
|
460 |
},
|
461 |
{
|
462 |
+
"epoch": 0.1,
|
463 |
+
"grad_norm": 12.125,
|
464 |
"learning_rate": 7.4e-06,
|
465 |
+
"loss": 1.9258,
|
466 |
"step": 630
|
467 |
},
|
468 |
{
|
469 |
+
"epoch": 0.11,
|
470 |
+
"grad_norm": 10.0,
|
471 |
"learning_rate": 7.2000000000000005e-06,
|
472 |
+
"loss": 2.1298,
|
473 |
"step": 640
|
474 |
},
|
475 |
{
|
476 |
+
"epoch": 0.11,
|
477 |
+
"grad_norm": 21.25,
|
478 |
"learning_rate": 7e-06,
|
479 |
+
"loss": 1.6867,
|
480 |
"step": 650
|
481 |
},
|
482 |
{
|
483 |
+
"epoch": 0.11,
|
484 |
+
"grad_norm": 15.75,
|
485 |
"learning_rate": 6.800000000000001e-06,
|
486 |
+
"loss": 2.0713,
|
487 |
"step": 660
|
488 |
},
|
489 |
{
|
490 |
+
"epoch": 0.11,
|
491 |
+
"grad_norm": 8.375,
|
492 |
"learning_rate": 6.600000000000001e-06,
|
493 |
+
"loss": 2.0162,
|
494 |
"step": 670
|
495 |
},
|
496 |
{
|
497 |
+
"epoch": 0.11,
|
498 |
+
"grad_norm": 19.5,
|
499 |
"learning_rate": 6.4000000000000006e-06,
|
500 |
+
"loss": 1.7879,
|
501 |
"step": 680
|
502 |
},
|
503 |
{
|
504 |
+
"epoch": 0.12,
|
505 |
+
"grad_norm": 11.75,
|
506 |
"learning_rate": 6.200000000000001e-06,
|
507 |
+
"loss": 2.1711,
|
508 |
"step": 690
|
509 |
},
|
510 |
{
|
511 |
+
"epoch": 0.12,
|
512 |
+
"grad_norm": 9.4375,
|
513 |
"learning_rate": 6e-06,
|
514 |
+
"loss": 1.7888,
|
515 |
"step": 700
|
516 |
},
|
517 |
{
|
518 |
+
"epoch": 0.12,
|
519 |
+
"grad_norm": 9.5,
|
520 |
"learning_rate": 5.8e-06,
|
521 |
+
"loss": 1.99,
|
522 |
"step": 710
|
523 |
},
|
524 |
{
|
525 |
+
"epoch": 0.12,
|
526 |
+
"grad_norm": 9.6875,
|
527 |
"learning_rate": 5.600000000000001e-06,
|
528 |
+
"loss": 2.0291,
|
529 |
"step": 720
|
530 |
},
|
531 |
{
|
532 |
+
"epoch": 0.12,
|
533 |
+
"grad_norm": 9.25,
|
534 |
"learning_rate": 5.400000000000001e-06,
|
535 |
+
"loss": 1.5828,
|
536 |
"step": 730
|
537 |
},
|
538 |
{
|
539 |
+
"epoch": 0.12,
|
540 |
+
"grad_norm": 9.75,
|
541 |
"learning_rate": 5.2e-06,
|
542 |
+
"loss": 1.8112,
|
543 |
"step": 740
|
544 |
},
|
545 |
{
|
546 |
+
"epoch": 0.12,
|
547 |
+
"grad_norm": 7.5625,
|
548 |
"learning_rate": 5e-06,
|
549 |
+
"loss": 1.8888,
|
550 |
"step": 750
|
551 |
},
|
552 |
{
|
553 |
+
"epoch": 0.12,
|
554 |
+
"eval_loss": 1.7764592170715332,
|
555 |
+
"eval_runtime": 29.9989,
|
556 |
+
"eval_samples_per_second": 33.335,
|
557 |
+
"eval_steps_per_second": 33.335,
|
558 |
"step": 750
|
559 |
},
|
560 |
{
|
561 |
+
"epoch": 0.13,
|
562 |
+
"grad_norm": 11.6875,
|
563 |
"learning_rate": 4.800000000000001e-06,
|
564 |
+
"loss": 1.3511,
|
565 |
"step": 760
|
566 |
},
|
567 |
{
|
568 |
+
"epoch": 0.13,
|
569 |
+
"grad_norm": 11.1875,
|
570 |
"learning_rate": 4.600000000000001e-06,
|
571 |
+
"loss": 1.7889,
|
572 |
"step": 770
|
573 |
},
|
574 |
{
|
575 |
+
"epoch": 0.13,
|
576 |
+
"grad_norm": 12.5,
|
577 |
"learning_rate": 4.4e-06,
|
578 |
+
"loss": 1.9403,
|
579 |
"step": 780
|
580 |
},
|
581 |
{
|
582 |
+
"epoch": 0.13,
|
583 |
+
"grad_norm": 9.375,
|
584 |
"learning_rate": 4.2000000000000004e-06,
|
585 |
+
"loss": 1.7881,
|
586 |
"step": 790
|
587 |
},
|
588 |
{
|
589 |
+
"epoch": 0.13,
|
590 |
+
"grad_norm": 7.53125,
|
591 |
"learning_rate": 4.000000000000001e-06,
|
592 |
+
"loss": 1.8992,
|
593 |
"step": 800
|
594 |
},
|
595 |
{
|
596 |
+
"epoch": 0.14,
|
597 |
+
"grad_norm": 9.5625,
|
598 |
"learning_rate": 3.8000000000000005e-06,
|
599 |
+
"loss": 1.8407,
|
600 |
"step": 810
|
601 |
},
|
602 |
{
|
603 |
+
"epoch": 0.14,
|
604 |
+
"grad_norm": 18.125,
|
605 |
"learning_rate": 3.6000000000000003e-06,
|
606 |
+
"loss": 1.5022,
|
607 |
"step": 820
|
608 |
},
|
609 |
{
|
610 |
+
"epoch": 0.14,
|
611 |
+
"grad_norm": 8.1875,
|
612 |
"learning_rate": 3.4000000000000005e-06,
|
613 |
+
"loss": 1.8158,
|
614 |
"step": 830
|
615 |
},
|
616 |
{
|
617 |
+
"epoch": 0.14,
|
618 |
+
"grad_norm": 12.6875,
|
619 |
"learning_rate": 3.2000000000000003e-06,
|
620 |
+
"loss": 1.9418,
|
621 |
"step": 840
|
622 |
},
|
623 |
{
|
624 |
+
"epoch": 0.14,
|
625 |
+
"grad_norm": 14.6875,
|
626 |
"learning_rate": 3e-06,
|
627 |
+
"loss": 1.7942,
|
628 |
"step": 850
|
629 |
},
|
630 |
{
|
631 |
+
"epoch": 0.14,
|
632 |
+
"grad_norm": 5.75,
|
633 |
"learning_rate": 2.8000000000000003e-06,
|
634 |
+
"loss": 1.3924,
|
635 |
"step": 860
|
636 |
},
|
637 |
{
|
638 |
+
"epoch": 0.14,
|
639 |
+
"grad_norm": 10.375,
|
640 |
"learning_rate": 2.6e-06,
|
641 |
+
"loss": 1.8403,
|
642 |
"step": 870
|
643 |
},
|
644 |
{
|
645 |
+
"epoch": 0.15,
|
646 |
+
"grad_norm": 8.875,
|
647 |
"learning_rate": 2.4000000000000003e-06,
|
648 |
+
"loss": 1.7975,
|
649 |
"step": 880
|
650 |
},
|
651 |
{
|
652 |
+
"epoch": 0.15,
|
653 |
+
"grad_norm": 10.625,
|
654 |
"learning_rate": 2.2e-06,
|
655 |
+
"loss": 1.792,
|
656 |
"step": 890
|
657 |
},
|
658 |
{
|
659 |
+
"epoch": 0.15,
|
660 |
+
"grad_norm": 8.9375,
|
661 |
"learning_rate": 2.0000000000000003e-06,
|
662 |
+
"loss": 1.98,
|
663 |
"step": 900
|
664 |
},
|
665 |
{
|
666 |
+
"epoch": 0.15,
|
667 |
+
"grad_norm": 10.9375,
|
668 |
"learning_rate": 1.8000000000000001e-06,
|
669 |
+
"loss": 1.6802,
|
670 |
"step": 910
|
671 |
},
|
672 |
{
|
673 |
+
"epoch": 0.15,
|
674 |
+
"grad_norm": 12.4375,
|
675 |
"learning_rate": 1.6000000000000001e-06,
|
676 |
+
"loss": 1.9608,
|
677 |
"step": 920
|
678 |
},
|
679 |
{
|
680 |
+
"epoch": 0.15,
|
681 |
+
"grad_norm": 8.125,
|
682 |
"learning_rate": 1.4000000000000001e-06,
|
683 |
+
"loss": 1.7228,
|
684 |
"step": 930
|
685 |
},
|
686 |
{
|
687 |
+
"epoch": 0.16,
|
688 |
+
"grad_norm": 7.75,
|
689 |
"learning_rate": 1.2000000000000002e-06,
|
690 |
+
"loss": 1.2766,
|
691 |
"step": 940
|
692 |
},
|
693 |
{
|
694 |
+
"epoch": 0.16,
|
695 |
+
"grad_norm": 10.5625,
|
696 |
"learning_rate": 1.0000000000000002e-06,
|
697 |
+
"loss": 2.0451,
|
698 |
"step": 950
|
699 |
},
|
700 |
{
|
701 |
+
"epoch": 0.16,
|
702 |
+
"grad_norm": 8.3125,
|
703 |
"learning_rate": 8.000000000000001e-07,
|
704 |
+
"loss": 1.8266,
|
705 |
"step": 960
|
706 |
},
|
707 |
{
|
708 |
+
"epoch": 0.16,
|
709 |
"grad_norm": 10.6875,
|
710 |
"learning_rate": 6.000000000000001e-07,
|
711 |
+
"loss": 1.7288,
|
712 |
"step": 970
|
713 |
},
|
714 |
{
|
715 |
+
"epoch": 0.16,
|
716 |
+
"grad_norm": 10.875,
|
717 |
"learning_rate": 4.0000000000000003e-07,
|
718 |
+
"loss": 1.9444,
|
719 |
"step": 980
|
720 |
},
|
721 |
{
|
722 |
+
"epoch": 0.17,
|
723 |
+
"grad_norm": 9.1875,
|
724 |
"learning_rate": 2.0000000000000002e-07,
|
725 |
+
"loss": 2.0397,
|
726 |
"step": 990
|
727 |
},
|
728 |
{
|
729 |
+
"epoch": 0.17,
|
730 |
+
"grad_norm": 9.375,
|
731 |
"learning_rate": 0.0,
|
732 |
+
"loss": 1.84,
|
733 |
"step": 1000
|
734 |
},
|
735 |
{
|
736 |
+
"epoch": 0.17,
|
737 |
+
"eval_loss": 1.800995111465454,
|
738 |
+
"eval_runtime": 30.0231,
|
739 |
+
"eval_samples_per_second": 33.308,
|
740 |
+
"eval_steps_per_second": 33.308,
|
741 |
"step": 1000
|
742 |
}
|
743 |
],
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb8be8fbab15133351348d557c845e8c137056441e2c8727a75128871efdd689
|
3 |
size 4984
|