Namronaldo2004
commited on
Commit
·
14ed909
1
Parent(s):
be673c2
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 +202 -377
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -20,12 +20,12 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"up_proj",
|
24 |
-
"v_proj",
|
25 |
-
"k_proj",
|
26 |
"o_proj",
|
27 |
-
"
|
28 |
"q_proj",
|
|
|
|
|
|
|
29 |
"gate_proj"
|
30 |
],
|
31 |
"task_type": " CAUSAL_LM",
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
23 |
"o_proj",
|
24 |
+
"k_proj",
|
25 |
"q_proj",
|
26 |
+
"v_proj",
|
27 |
+
"down_proj",
|
28 |
+
"up_proj",
|
29 |
"gate_proj"
|
30 |
],
|
31 |
"task_type": " CAUSAL_LM",
|
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 sha256:430a11259d17a49541e9f31c838ea163b82b162b916c4215762ffab0b4917a07
|
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 sha256:2e45b6af16f366e2479a1fda5784a26168e5d866ba82ed55f4eb013e34c3ceee
|
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:b0654b1e5962e1d264ec17c40dcea6c3de9060e283aa95a5fea4d3b6d181505f
|
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:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -3,539 +3,364 @@
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 5.0,
|
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":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate": 0.
|
22 |
-
"loss": 0.
|
23 |
"step": 2
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm": 0.
|
28 |
-
"learning_rate": 0.
|
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":
|
83 |
-
"grad_norm": 0.
|
84 |
-
"learning_rate": 0.
|
85 |
-
"loss": 0.
|
86 |
"step": 11
|
87 |
},
|
88 |
{
|
89 |
-
"epoch":
|
90 |
-
"grad_norm": 0.
|
91 |
-
"learning_rate": 0.
|
92 |
-
"loss": 0.
|
93 |
"step": 12
|
94 |
},
|
95 |
{
|
96 |
-
"epoch":
|
97 |
-
"grad_norm": 0.
|
98 |
-
"learning_rate": 0.
|
99 |
-
"loss": 0.
|
100 |
"step": 13
|
101 |
},
|
102 |
{
|
103 |
-
"epoch":
|
104 |
-
"grad_norm": 0.
|
105 |
-
"learning_rate": 0.
|
106 |
-
"loss": 0.
|
107 |
"step": 14
|
108 |
},
|
109 |
{
|
110 |
-
"epoch": 1.
|
111 |
-
"grad_norm": 0.
|
112 |
-
"learning_rate": 0.
|
113 |
-
"loss": 0.
|
114 |
"step": 15
|
115 |
},
|
116 |
{
|
117 |
-
"epoch": 1.
|
118 |
-
"grad_norm": 0.
|
119 |
-
"learning_rate": 0.
|
120 |
-
"loss": 0.
|
121 |
"step": 16
|
122 |
},
|
123 |
{
|
124 |
-
"epoch": 1.
|
125 |
-
"grad_norm": 0.
|
126 |
-
"learning_rate": 0.
|
127 |
-
"loss": 0.
|
128 |
"step": 17
|
129 |
},
|
130 |
{
|
131 |
-
"epoch": 1.
|
132 |
-
"grad_norm": 0.
|
133 |
-
"learning_rate": 0.
|
134 |
-
"loss": 0.
|
135 |
"step": 18
|
136 |
},
|
137 |
{
|
138 |
-
"epoch": 1.
|
139 |
-
"grad_norm": 0.
|
140 |
-
"learning_rate": 0.
|
141 |
-
"loss": 0.
|
142 |
"step": 19
|
143 |
},
|
144 |
{
|
145 |
-
"epoch":
|
146 |
-
"grad_norm": 0.
|
147 |
-
"learning_rate": 0.
|
148 |
-
"loss": 0.
|
149 |
"step": 20
|
150 |
},
|
151 |
{
|
152 |
-
"epoch": 1
|
153 |
-
"grad_norm": 0.
|
154 |
-
"learning_rate": 0.
|
155 |
-
"loss": 0.
|
156 |
"step": 21
|
157 |
},
|
158 |
{
|
159 |
-
"epoch":
|
160 |
-
"grad_norm": 0.
|
161 |
-
"learning_rate": 0.
|
162 |
-
"loss": 0.
|
163 |
"step": 22
|
164 |
},
|
165 |
{
|
166 |
-
"epoch":
|
167 |
-
"grad_norm": 0.
|
168 |
-
"learning_rate": 0.
|
169 |
-
"loss": 0.
|
170 |
"step": 23
|
171 |
},
|
172 |
{
|
173 |
-
"epoch":
|
174 |
-
"grad_norm": 0.
|
175 |
-
"learning_rate": 0.
|
176 |
-
"loss": 0.
|
177 |
"step": 24
|
178 |
},
|
179 |
{
|
180 |
-
"epoch":
|
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":
|
197 |
-
"loss": 0.
|
198 |
"step": 27
|
199 |
},
|
200 |
{
|
201 |
-
"epoch":
|
202 |
-
"grad_norm": 0.
|
203 |
-
"learning_rate":
|
204 |
-
"loss": 0.
|
205 |
"step": 28
|
206 |
},
|
207 |
{
|
208 |
-
"epoch":
|
209 |
-
"grad_norm": 0.
|
210 |
-
"learning_rate":
|
211 |
-
"loss": 0.
|
212 |
"step": 29
|
213 |
},
|
214 |
{
|
215 |
-
"epoch":
|
216 |
-
"grad_norm": 0.
|
217 |
-
"learning_rate":
|
218 |
-
"loss": 0.
|
219 |
"step": 30
|
220 |
},
|
221 |
{
|
222 |
-
"epoch":
|
223 |
-
"grad_norm": 0.
|
224 |
-
"learning_rate":
|
225 |
-
"loss": 0.
|
226 |
"step": 31
|
227 |
},
|
228 |
{
|
229 |
-
"epoch": 2
|
230 |
-
"grad_norm": 0.
|
231 |
-
"learning_rate":
|
232 |
-
"loss": 0.
|
233 |
"step": 32
|
234 |
},
|
235 |
{
|
236 |
-
"epoch":
|
237 |
-
"grad_norm": 0.
|
238 |
-
"learning_rate":
|
239 |
-
"loss": 0.
|
240 |
"step": 33
|
241 |
},
|
242 |
{
|
243 |
-
"epoch":
|
244 |
-
"grad_norm": 0.
|
245 |
-
"learning_rate":
|
246 |
-
"loss": 0.
|
247 |
"step": 34
|
248 |
},
|
249 |
{
|
250 |
-
"epoch":
|
251 |
-
"grad_norm": 0.
|
252 |
-
"learning_rate":
|
253 |
-
"loss": 0.
|
254 |
"step": 35
|
255 |
},
|
256 |
{
|
257 |
-
"epoch":
|
258 |
-
"grad_norm": 0.
|
259 |
-
"learning_rate":
|
260 |
-
"loss": 0.
|
261 |
"step": 36
|
262 |
},
|
263 |
{
|
264 |
-
"epoch":
|
265 |
-
"grad_norm": 0.
|
266 |
-
"learning_rate":
|
267 |
-
"loss": 0.
|
268 |
"step": 37
|
269 |
},
|
270 |
{
|
271 |
-
"epoch":
|
272 |
-
"grad_norm": 0.
|
273 |
-
"learning_rate":
|
274 |
-
"loss": 0.
|
275 |
"step": 38
|
276 |
},
|
277 |
{
|
278 |
-
"epoch":
|
279 |
-
"grad_norm": 0.
|
280 |
-
"learning_rate":
|
281 |
-
"loss": 0.
|
282 |
"step": 39
|
283 |
},
|
284 |
{
|
285 |
-
"epoch":
|
286 |
-
"grad_norm": 0.
|
287 |
-
"learning_rate":
|
288 |
-
"loss": 0.
|
289 |
"step": 40
|
290 |
},
|
291 |
{
|
292 |
-
"epoch":
|
293 |
-
"grad_norm": 0.
|
294 |
-
"learning_rate":
|
295 |
-
"loss": 0.
|
296 |
"step": 41
|
297 |
},
|
298 |
{
|
299 |
-
"epoch": 2
|
300 |
-
"grad_norm": 0.
|
301 |
-
"learning_rate":
|
302 |
-
"loss": 0.
|
303 |
"step": 42
|
304 |
},
|
305 |
{
|
306 |
-
"epoch":
|
307 |
-
"grad_norm": 0.
|
308 |
-
"learning_rate":
|
309 |
-
"loss": 0.
|
310 |
"step": 43
|
311 |
},
|
312 |
{
|
313 |
-
"epoch":
|
314 |
-
"grad_norm": 0.
|
315 |
-
"learning_rate":
|
316 |
-
"loss": 0.
|
317 |
"step": 44
|
318 |
},
|
319 |
{
|
320 |
-
"epoch":
|
321 |
-
"grad_norm": 0.
|
322 |
-
"learning_rate":
|
323 |
-
"loss": 0.
|
324 |
"step": 45
|
325 |
},
|
326 |
{
|
327 |
-
"epoch":
|
328 |
-
"grad_norm": 0.
|
329 |
-
"learning_rate":
|
330 |
-
"loss": 0.
|
331 |
"step": 46
|
332 |
},
|
333 |
{
|
334 |
-
"epoch":
|
335 |
-
"grad_norm": 0.
|
336 |
-
"learning_rate":
|
337 |
-
"loss": 0.
|
338 |
"step": 47
|
339 |
},
|
340 |
{
|
341 |
-
"epoch":
|
342 |
-
"grad_norm": 0.
|
343 |
-
"learning_rate":
|
344 |
-
"loss": 0.
|
345 |
"step": 48
|
346 |
},
|
347 |
{
|
348 |
-
"epoch":
|
349 |
-
"grad_norm": 0.
|
350 |
-
"learning_rate":
|
351 |
-
"loss": 0.
|
352 |
"step": 49
|
353 |
},
|
354 |
-
{
|
355 |
-
"epoch": 3.3333333333333335,
|
356 |
-
"grad_norm": 0.2558125853538513,
|
357 |
-
"learning_rate": 5.5193321601242156e-05,
|
358 |
-
"loss": 0.3467,
|
359 |
-
"step": 50
|
360 |
-
},
|
361 |
-
{
|
362 |
-
"epoch": 3.4,
|
363 |
-
"grad_norm": 0.2603452503681183,
|
364 |
-
"learning_rate": 5.1282715603920374e-05,
|
365 |
-
"loss": 0.3606,
|
366 |
-
"step": 51
|
367 |
-
},
|
368 |
-
{
|
369 |
-
"epoch": 3.466666666666667,
|
370 |
-
"grad_norm": 0.2685030996799469,
|
371 |
-
"learning_rate": 4.746747597857014e-05,
|
372 |
-
"loss": 0.3385,
|
373 |
-
"step": 52
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"epoch": 3.533333333333333,
|
377 |
-
"grad_norm": 0.2547042965888977,
|
378 |
-
"learning_rate": 4.375507123592194e-05,
|
379 |
-
"loss": 0.3502,
|
380 |
-
"step": 53
|
381 |
-
},
|
382 |
-
{
|
383 |
-
"epoch": 3.6,
|
384 |
-
"grad_norm": 0.25863558053970337,
|
385 |
-
"learning_rate": 4.015276858259427e-05,
|
386 |
-
"loss": 0.3353,
|
387 |
-
"step": 54
|
388 |
-
},
|
389 |
-
{
|
390 |
-
"epoch": 3.6666666666666665,
|
391 |
-
"grad_norm": 0.25985899567604065,
|
392 |
-
"learning_rate": 3.6667619695195285e-05,
|
393 |
-
"loss": 0.3314,
|
394 |
-
"step": 55
|
395 |
-
},
|
396 |
-
{
|
397 |
-
"epoch": 3.7333333333333334,
|
398 |
-
"grad_norm": 0.2722785174846649,
|
399 |
-
"learning_rate": 3.330644691633492e-05,
|
400 |
-
"loss": 0.3224,
|
401 |
-
"step": 56
|
402 |
-
},
|
403 |
-
{
|
404 |
-
"epoch": 3.8,
|
405 |
-
"grad_norm": 0.2661519944667816,
|
406 |
-
"learning_rate": 3.0075829899568597e-05,
|
407 |
-
"loss": 0.3487,
|
408 |
-
"step": 57
|
409 |
-
},
|
410 |
-
{
|
411 |
-
"epoch": 3.8666666666666667,
|
412 |
-
"grad_norm": 0.2682656943798065,
|
413 |
-
"learning_rate": 2.6982092729416587e-05,
|
414 |
-
"loss": 0.3412,
|
415 |
-
"step": 58
|
416 |
-
},
|
417 |
-
{
|
418 |
-
"epoch": 3.9333333333333336,
|
419 |
-
"grad_norm": 0.2595905363559723,
|
420 |
-
"learning_rate": 2.403129154167153e-05,
|
421 |
-
"loss": 0.3242,
|
422 |
-
"step": 59
|
423 |
-
},
|
424 |
-
{
|
425 |
-
"epoch": 4.0,
|
426 |
-
"grad_norm": 0.2578358054161072,
|
427 |
-
"learning_rate": 2.1229202668228197e-05,
|
428 |
-
"loss": 0.306,
|
429 |
-
"step": 60
|
430 |
-
},
|
431 |
-
{
|
432 |
-
"epoch": 4.066666666666666,
|
433 |
-
"grad_norm": 0.2525722086429596,
|
434 |
-
"learning_rate": 1.858131132964259e-05,
|
435 |
-
"loss": 0.3234,
|
436 |
-
"step": 61
|
437 |
-
},
|
438 |
-
{
|
439 |
-
"epoch": 4.133333333333334,
|
440 |
-
"grad_norm": 0.2557724118232727,
|
441 |
-
"learning_rate": 1.609280089755515e-05,
|
442 |
-
"loss": 0.2945,
|
443 |
-
"step": 62
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 4.2,
|
447 |
-
"grad_norm": 0.2506673038005829,
|
448 |
-
"learning_rate": 1.3768542747997215e-05,
|
449 |
-
"loss": 0.3157,
|
450 |
-
"step": 63
|
451 |
-
},
|
452 |
-
{
|
453 |
-
"epoch": 4.266666666666667,
|
454 |
-
"grad_norm": 0.25794729590415955,
|
455 |
-
"learning_rate": 1.161308672544389e-05,
|
456 |
-
"loss": 0.3085,
|
457 |
-
"step": 64
|
458 |
-
},
|
459 |
-
{
|
460 |
-
"epoch": 4.333333333333333,
|
461 |
-
"grad_norm": 0.2558946907520294,
|
462 |
-
"learning_rate": 9.630652236279625e-06,
|
463 |
-
"loss": 0.3096,
|
464 |
-
"step": 65
|
465 |
-
},
|
466 |
-
{
|
467 |
-
"epoch": 4.4,
|
468 |
-
"grad_norm": 0.25984814763069153,
|
469 |
-
"learning_rate": 7.825119989112173e-06,
|
470 |
-
"loss": 0.311,
|
471 |
-
"step": 66
|
472 |
-
},
|
473 |
-
{
|
474 |
-
"epoch": 4.466666666666667,
|
475 |
-
"grad_norm": 0.24387367069721222,
|
476 |
-
"learning_rate": 6.200024398103255e-06,
|
477 |
-
"loss": 0.3083,
|
478 |
-
"step": 67
|
479 |
-
},
|
480 |
-
{
|
481 |
-
"epoch": 4.533333333333333,
|
482 |
-
"grad_norm": 0.24648573994636536,
|
483 |
-
"learning_rate": 4.758546664186869e-06,
|
484 |
-
"loss": 0.2929,
|
485 |
-
"step": 68
|
486 |
-
},
|
487 |
-
{
|
488 |
-
"epoch": 4.6,
|
489 |
-
"grad_norm": 0.24927794933319092,
|
490 |
-
"learning_rate": 3.5035085477190143e-06,
|
491 |
-
"loss": 0.312,
|
492 |
-
"step": 69
|
493 |
-
},
|
494 |
-
{
|
495 |
-
"epoch": 4.666666666666667,
|
496 |
-
"grad_norm": 0.25699713826179504,
|
497 |
-
"learning_rate": 2.4373668447493224e-06,
|
498 |
-
"loss": 0.3157,
|
499 |
-
"step": 70
|
500 |
-
},
|
501 |
-
{
|
502 |
-
"epoch": 4.733333333333333,
|
503 |
-
"grad_norm": 0.25668400526046753,
|
504 |
-
"learning_rate": 1.562208577727442e-06,
|
505 |
-
"loss": 0.297,
|
506 |
-
"step": 71
|
507 |
-
},
|
508 |
-
{
|
509 |
-
"epoch": 4.8,
|
510 |
-
"grad_norm": 0.25037774443626404,
|
511 |
-
"learning_rate": 8.797469100585431e-07,
|
512 |
-
"loss": 0.2887,
|
513 |
-
"step": 72
|
514 |
-
},
|
515 |
-
{
|
516 |
-
"epoch": 4.866666666666667,
|
517 |
-
"grad_norm": 0.24792499840259552,
|
518 |
-
"learning_rate": 3.913177925055189e-07,
|
519 |
-
"loss": 0.3156,
|
520 |
-
"step": 73
|
521 |
-
},
|
522 |
-
{
|
523 |
-
"epoch": 4.933333333333334,
|
524 |
-
"grad_norm": 0.2463802695274353,
|
525 |
-
"learning_rate": 9.78773480026396e-08,
|
526 |
-
"loss": 0.2867,
|
527 |
-
"step": 74
|
528 |
-
},
|
529 |
{
|
530 |
"epoch": 5.0,
|
531 |
-
"grad_norm": 0.
|
532 |
"learning_rate": 0.0,
|
533 |
-
"loss": 0.
|
534 |
-
"step":
|
535 |
}
|
536 |
],
|
537 |
"logging_steps": 1,
|
538 |
-
"max_steps":
|
539 |
"num_input_tokens_seen": 0,
|
540 |
"num_train_epochs": 5,
|
541 |
"save_steps": 500,
|
@@ -551,7 +376,7 @@
|
|
551 |
"attributes": {}
|
552 |
}
|
553 |
},
|
554 |
-
"total_flos":
|
555 |
"train_batch_size": 1,
|
556 |
"trial_name": null,
|
557 |
"trial_params": null
|
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.1,
|
13 |
+
"grad_norm": 0.886165976524353,
|
14 |
+
"learning_rate": 6.666666666666667e-05,
|
15 |
+
"loss": 0.8569,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.2,
|
20 |
+
"grad_norm": 0.9352289438247681,
|
21 |
+
"learning_rate": 0.00013333333333333334,
|
22 |
+
"loss": 0.9157,
|
23 |
"step": 2
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.3,
|
27 |
+
"grad_norm": 0.6887379288673401,
|
28 |
+
"learning_rate": 0.0002,
|
29 |
+
"loss": 0.8368,
|
30 |
"step": 3
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.4,
|
34 |
+
"grad_norm": 0.5438244938850403,
|
35 |
+
"learning_rate": 0.00019977668786231534,
|
36 |
+
"loss": 0.7759,
|
37 |
"step": 4
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 0.5,
|
41 |
+
"grad_norm": 0.4049173593521118,
|
42 |
+
"learning_rate": 0.000199107748815478,
|
43 |
+
"loss": 0.7108,
|
44 |
"step": 5
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.6,
|
48 |
+
"grad_norm": 0.3374454379081726,
|
49 |
+
"learning_rate": 0.0001979961705036587,
|
50 |
+
"loss": 0.6949,
|
51 |
"step": 6
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.7,
|
55 |
+
"grad_norm": 0.31860846281051636,
|
56 |
+
"learning_rate": 0.00019644691750543767,
|
57 |
+
"loss": 0.6725,
|
58 |
"step": 7
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 0.8,
|
62 |
+
"grad_norm": 0.3116016089916229,
|
63 |
+
"learning_rate": 0.0001944669091607919,
|
64 |
+
"loss": 0.6814,
|
65 |
"step": 8
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 0.9,
|
69 |
+
"grad_norm": 0.3020254969596863,
|
70 |
+
"learning_rate": 0.00019206498866764288,
|
71 |
+
"loss": 0.6628,
|
72 |
"step": 9
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 1.0,
|
76 |
+
"grad_norm": 0.3751624524593353,
|
77 |
+
"learning_rate": 0.00018925188358598813,
|
78 |
+
"loss": 0.6491,
|
79 |
"step": 10
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 1.1,
|
83 |
+
"grad_norm": 0.33873409032821655,
|
84 |
+
"learning_rate": 0.00018604015792601396,
|
85 |
+
"loss": 0.5887,
|
86 |
"step": 11
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 1.2,
|
90 |
+
"grad_norm": 0.3233942985534668,
|
91 |
+
"learning_rate": 0.00018244415603417603,
|
92 |
+
"loss": 0.5414,
|
93 |
"step": 12
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 1.3,
|
97 |
+
"grad_norm": 0.33184298872947693,
|
98 |
+
"learning_rate": 0.0001784799385278661,
|
99 |
+
"loss": 0.5534,
|
100 |
"step": 13
|
101 |
},
|
102 |
{
|
103 |
+
"epoch": 1.4,
|
104 |
+
"grad_norm": 0.3251623511314392,
|
105 |
+
"learning_rate": 0.00017416521056479577,
|
106 |
+
"loss": 0.5303,
|
107 |
"step": 14
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 1.5,
|
111 |
+
"grad_norm": 0.30667614936828613,
|
112 |
+
"learning_rate": 0.00016951924276746425,
|
113 |
+
"loss": 0.5261,
|
114 |
"step": 15
|
115 |
},
|
116 |
{
|
117 |
+
"epoch": 1.6,
|
118 |
+
"grad_norm": 0.30262428522109985,
|
119 |
+
"learning_rate": 0.00016456278515588024,
|
120 |
+
"loss": 0.5101,
|
121 |
"step": 16
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 1.7,
|
125 |
+
"grad_norm": 0.30721279978752136,
|
126 |
+
"learning_rate": 0.00015931797447293552,
|
127 |
+
"loss": 0.5059,
|
128 |
"step": 17
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 1.8,
|
132 |
+
"grad_norm": 0.2939946949481964,
|
133 |
+
"learning_rate": 0.00015380823531633729,
|
134 |
+
"loss": 0.4949,
|
135 |
"step": 18
|
136 |
},
|
137 |
{
|
138 |
+
"epoch": 1.9,
|
139 |
+
"grad_norm": 0.28288447856903076,
|
140 |
+
"learning_rate": 0.00014805817551866838,
|
141 |
+
"loss": 0.4869,
|
142 |
"step": 19
|
143 |
},
|
144 |
{
|
145 |
+
"epoch": 2.0,
|
146 |
+
"grad_norm": 0.2906552255153656,
|
147 |
+
"learning_rate": 0.0001420934762428335,
|
148 |
+
"loss": 0.4605,
|
149 |
"step": 20
|
150 |
},
|
151 |
{
|
152 |
+
"epoch": 2.1,
|
153 |
+
"grad_norm": 0.2544306218624115,
|
154 |
+
"learning_rate": 0.00013594077728375128,
|
155 |
+
"loss": 0.4436,
|
156 |
"step": 21
|
157 |
},
|
158 |
{
|
159 |
+
"epoch": 2.2,
|
160 |
+
"grad_norm": 0.2552658021450043,
|
161 |
+
"learning_rate": 0.00012962755808856342,
|
162 |
+
"loss": 0.4192,
|
163 |
"step": 22
|
164 |
},
|
165 |
{
|
166 |
+
"epoch": 2.3,
|
167 |
+
"grad_norm": 0.2546628713607788,
|
168 |
+
"learning_rate": 0.00012318201502675285,
|
169 |
+
"loss": 0.4106,
|
170 |
"step": 23
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 2.4,
|
174 |
+
"grad_norm": 0.23741765320301056,
|
175 |
+
"learning_rate": 0.00011663293545831302,
|
176 |
+
"loss": 0.3938,
|
177 |
"step": 24
|
178 |
},
|
179 |
{
|
180 |
+
"epoch": 2.5,
|
181 |
+
"grad_norm": 0.2525660991668701,
|
182 |
+
"learning_rate": 0.00011000956916240985,
|
183 |
+
"loss": 0.4017,
|
184 |
"step": 25
|
185 |
},
|
186 |
{
|
187 |
+
"epoch": 2.6,
|
188 |
+
"grad_norm": 0.2451285570859909,
|
189 |
+
"learning_rate": 0.00010334149770076747,
|
190 |
+
"loss": 0.3794,
|
191 |
"step": 26
|
192 |
},
|
193 |
{
|
194 |
+
"epoch": 2.7,
|
195 |
+
"grad_norm": 0.2524901032447815,
|
196 |
+
"learning_rate": 9.665850229923258e-05,
|
197 |
+
"loss": 0.3855,
|
198 |
"step": 27
|
199 |
},
|
200 |
{
|
201 |
+
"epoch": 2.8,
|
202 |
+
"grad_norm": 0.24502427875995636,
|
203 |
+
"learning_rate": 8.999043083759017e-05,
|
204 |
+
"loss": 0.3616,
|
205 |
"step": 28
|
206 |
},
|
207 |
{
|
208 |
+
"epoch": 2.9,
|
209 |
+
"grad_norm": 0.2539559602737427,
|
210 |
+
"learning_rate": 8.336706454168701e-05,
|
211 |
+
"loss": 0.3763,
|
212 |
"step": 29
|
213 |
},
|
214 |
{
|
215 |
+
"epoch": 3.0,
|
216 |
+
"grad_norm": 0.24636436998844147,
|
217 |
+
"learning_rate": 7.681798497324716e-05,
|
218 |
+
"loss": 0.3517,
|
219 |
"step": 30
|
220 |
},
|
221 |
{
|
222 |
+
"epoch": 3.1,
|
223 |
+
"grad_norm": 0.23345255851745605,
|
224 |
+
"learning_rate": 7.037244191143661e-05,
|
225 |
+
"loss": 0.3284,
|
226 |
"step": 31
|
227 |
},
|
228 |
{
|
229 |
+
"epoch": 3.2,
|
230 |
+
"grad_norm": 0.2510325014591217,
|
231 |
+
"learning_rate": 6.405922271624874e-05,
|
232 |
+
"loss": 0.3301,
|
233 |
"step": 32
|
234 |
},
|
235 |
{
|
236 |
+
"epoch": 3.3,
|
237 |
+
"grad_norm": 0.24276795983314514,
|
238 |
+
"learning_rate": 5.790652375716652e-05,
|
239 |
+
"loss": 0.3339,
|
240 |
"step": 33
|
241 |
},
|
242 |
{
|
243 |
+
"epoch": 3.4,
|
244 |
+
"grad_norm": 0.23698894679546356,
|
245 |
+
"learning_rate": 5.1941824481331626e-05,
|
246 |
+
"loss": 0.3273,
|
247 |
"step": 34
|
248 |
},
|
249 |
{
|
250 |
+
"epoch": 3.5,
|
251 |
+
"grad_norm": 0.24454469978809357,
|
252 |
+
"learning_rate": 4.6191764683662744e-05,
|
253 |
+
"loss": 0.3073,
|
254 |
"step": 35
|
255 |
},
|
256 |
{
|
257 |
+
"epoch": 3.6,
|
258 |
+
"grad_norm": 0.25007879734039307,
|
259 |
+
"learning_rate": 4.0682025527064486e-05,
|
260 |
+
"loss": 0.3149,
|
261 |
"step": 36
|
262 |
},
|
263 |
{
|
264 |
+
"epoch": 3.7,
|
265 |
+
"grad_norm": 0.25587430596351624,
|
266 |
+
"learning_rate": 3.543721484411976e-05,
|
267 |
+
"loss": 0.3081,
|
268 |
"step": 37
|
269 |
},
|
270 |
{
|
271 |
+
"epoch": 3.8,
|
272 |
+
"grad_norm": 0.2517322599887848,
|
273 |
+
"learning_rate": 3.0480757232535772e-05,
|
274 |
+
"loss": 0.3131,
|
275 |
"step": 38
|
276 |
},
|
277 |
{
|
278 |
+
"epoch": 3.9,
|
279 |
+
"grad_norm": 0.23721425235271454,
|
280 |
+
"learning_rate": 2.5834789435204243e-05,
|
281 |
+
"loss": 0.2987,
|
282 |
"step": 39
|
283 |
},
|
284 |
{
|
285 |
+
"epoch": 4.0,
|
286 |
+
"grad_norm": 0.23976309597492218,
|
287 |
+
"learning_rate": 2.1520061472133902e-05,
|
288 |
+
"loss": 0.3148,
|
289 |
"step": 40
|
290 |
},
|
291 |
{
|
292 |
+
"epoch": 4.1,
|
293 |
+
"grad_norm": 0.22691340744495392,
|
294 |
+
"learning_rate": 1.7555843965823992e-05,
|
295 |
+
"loss": 0.2777,
|
296 |
"step": 41
|
297 |
},
|
298 |
{
|
299 |
+
"epoch": 4.2,
|
300 |
+
"grad_norm": 0.23945631086826324,
|
301 |
+
"learning_rate": 1.3959842073986085e-05,
|
302 |
+
"loss": 0.2954,
|
303 |
"step": 42
|
304 |
},
|
305 |
{
|
306 |
+
"epoch": 4.3,
|
307 |
+
"grad_norm": 0.23303616046905518,
|
308 |
+
"learning_rate": 1.0748116414011888e-05,
|
309 |
+
"loss": 0.2882,
|
310 |
"step": 43
|
311 |
},
|
312 |
{
|
313 |
+
"epoch": 4.4,
|
314 |
+
"grad_norm": 0.24104540050029755,
|
315 |
+
"learning_rate": 7.935011332357112e-06,
|
316 |
+
"loss": 0.2939,
|
317 |
"step": 44
|
318 |
},
|
319 |
{
|
320 |
+
"epoch": 4.5,
|
321 |
+
"grad_norm": 0.23101571202278137,
|
322 |
+
"learning_rate": 5.533090839208133e-06,
|
323 |
+
"loss": 0.2789,
|
324 |
"step": 45
|
325 |
},
|
326 |
{
|
327 |
+
"epoch": 4.6,
|
328 |
+
"grad_norm": 0.2310316413640976,
|
329 |
+
"learning_rate": 3.5530824945623542e-06,
|
330 |
+
"loss": 0.2925,
|
331 |
"step": 46
|
332 |
},
|
333 |
{
|
334 |
+
"epoch": 4.7,
|
335 |
+
"grad_norm": 0.23140206933021545,
|
336 |
+
"learning_rate": 2.003829496341325e-06,
|
337 |
+
"loss": 0.2824,
|
338 |
"step": 47
|
339 |
},
|
340 |
{
|
341 |
+
"epoch": 4.8,
|
342 |
+
"grad_norm": 0.22320057451725006,
|
343 |
+
"learning_rate": 8.922511845219971e-07,
|
344 |
+
"loss": 0.2975,
|
345 |
"step": 48
|
346 |
},
|
347 |
{
|
348 |
+
"epoch": 4.9,
|
349 |
+
"grad_norm": 0.22732405364513397,
|
350 |
+
"learning_rate": 2.2331213768468363e-07,
|
351 |
+
"loss": 0.2891,
|
352 |
"step": 49
|
353 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
354 |
{
|
355 |
"epoch": 5.0,
|
356 |
+
"grad_norm": 0.2486155927181244,
|
357 |
"learning_rate": 0.0,
|
358 |
+
"loss": 0.2815,
|
359 |
+
"step": 50
|
360 |
}
|
361 |
],
|
362 |
"logging_steps": 1,
|
363 |
+
"max_steps": 50,
|
364 |
"num_input_tokens_seen": 0,
|
365 |
"num_train_epochs": 5,
|
366 |
"save_steps": 500,
|
|
|
376 |
"attributes": {}
|
377 |
}
|
378 |
},
|
379 |
+
"total_flos": 7.457968683122688e+16,
|
380 |
"train_batch_size": 1,
|
381 |
"trial_name": null,
|
382 |
"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 sha256:379e9b75008263e92f24f632d566b21e4ea482a4e680b4f98fef9cb95afe9d88
|
3 |
size 5240
|