Delete trainer_state.json
Browse files- trainer_state.json +0 -1589
trainer_state.json
DELETED
@@ -1,1589 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 3.0,
|
5 |
-
"eval_steps": 500,
|
6 |
-
"global_step": 2217,
|
7 |
-
"is_hyper_param_search": false,
|
8 |
-
"is_local_process_zero": true,
|
9 |
-
"is_world_process_zero": true,
|
10 |
-
"log_history": [
|
11 |
-
{
|
12 |
-
"epoch": 0.013531799729364006,
|
13 |
-
"grad_norm": 3.034516595682754,
|
14 |
-
"learning_rate": 2.2522522522522524e-07,
|
15 |
-
"loss": 0.6411,
|
16 |
-
"step": 10
|
17 |
-
},
|
18 |
-
{
|
19 |
-
"epoch": 0.02706359945872801,
|
20 |
-
"grad_norm": 2.7841028225351487,
|
21 |
-
"learning_rate": 4.504504504504505e-07,
|
22 |
-
"loss": 0.6332,
|
23 |
-
"step": 20
|
24 |
-
},
|
25 |
-
{
|
26 |
-
"epoch": 0.04059539918809202,
|
27 |
-
"grad_norm": 1.8710512230715446,
|
28 |
-
"learning_rate": 6.756756756756758e-07,
|
29 |
-
"loss": 0.6135,
|
30 |
-
"step": 30
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 0.05412719891745602,
|
34 |
-
"grad_norm": 1.5248415557438793,
|
35 |
-
"learning_rate": 9.00900900900901e-07,
|
36 |
-
"loss": 0.6095,
|
37 |
-
"step": 40
|
38 |
-
},
|
39 |
-
{
|
40 |
-
"epoch": 0.06765899864682003,
|
41 |
-
"grad_norm": 1.330731637337357,
|
42 |
-
"learning_rate": 1.1261261261261262e-06,
|
43 |
-
"loss": 0.5672,
|
44 |
-
"step": 50
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.08119079837618404,
|
48 |
-
"grad_norm": 1.1702536060306041,
|
49 |
-
"learning_rate": 1.3513513513513515e-06,
|
50 |
-
"loss": 0.5592,
|
51 |
-
"step": 60
|
52 |
-
},
|
53 |
-
{
|
54 |
-
"epoch": 0.09472259810554803,
|
55 |
-
"grad_norm": 1.2129816143771526,
|
56 |
-
"learning_rate": 1.5765765765765766e-06,
|
57 |
-
"loss": 0.527,
|
58 |
-
"step": 70
|
59 |
-
},
|
60 |
-
{
|
61 |
-
"epoch": 0.10825439783491204,
|
62 |
-
"grad_norm": 1.234538155408458,
|
63 |
-
"learning_rate": 1.801801801801802e-06,
|
64 |
-
"loss": 0.5421,
|
65 |
-
"step": 80
|
66 |
-
},
|
67 |
-
{
|
68 |
-
"epoch": 0.12178619756427606,
|
69 |
-
"grad_norm": 1.1711228120854185,
|
70 |
-
"learning_rate": 2.0270270270270273e-06,
|
71 |
-
"loss": 0.5292,
|
72 |
-
"step": 90
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"epoch": 0.13531799729364005,
|
76 |
-
"grad_norm": 1.2936648719718322,
|
77 |
-
"learning_rate": 2.2522522522522524e-06,
|
78 |
-
"loss": 0.5479,
|
79 |
-
"step": 100
|
80 |
-
},
|
81 |
-
{
|
82 |
-
"epoch": 0.14884979702300405,
|
83 |
-
"grad_norm": 1.291284989397587,
|
84 |
-
"learning_rate": 2.4774774774774775e-06,
|
85 |
-
"loss": 0.5416,
|
86 |
-
"step": 110
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.16238159675236807,
|
90 |
-
"grad_norm": 1.34797590127609,
|
91 |
-
"learning_rate": 2.702702702702703e-06,
|
92 |
-
"loss": 0.5152,
|
93 |
-
"step": 120
|
94 |
-
},
|
95 |
-
{
|
96 |
-
"epoch": 0.17591339648173207,
|
97 |
-
"grad_norm": 1.360973654533329,
|
98 |
-
"learning_rate": 2.927927927927928e-06,
|
99 |
-
"loss": 0.5129,
|
100 |
-
"step": 130
|
101 |
-
},
|
102 |
-
{
|
103 |
-
"epoch": 0.18944519621109607,
|
104 |
-
"grad_norm": 1.2536822051142262,
|
105 |
-
"learning_rate": 3.1531531531531532e-06,
|
106 |
-
"loss": 0.5281,
|
107 |
-
"step": 140
|
108 |
-
},
|
109 |
-
{
|
110 |
-
"epoch": 0.2029769959404601,
|
111 |
-
"grad_norm": 1.3088135261215759,
|
112 |
-
"learning_rate": 3.3783783783783788e-06,
|
113 |
-
"loss": 0.5209,
|
114 |
-
"step": 150
|
115 |
-
},
|
116 |
-
{
|
117 |
-
"epoch": 0.2165087956698241,
|
118 |
-
"grad_norm": 1.288765418316905,
|
119 |
-
"learning_rate": 3.603603603603604e-06,
|
120 |
-
"loss": 0.5174,
|
121 |
-
"step": 160
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"epoch": 0.23004059539918809,
|
125 |
-
"grad_norm": 1.393215959864774,
|
126 |
-
"learning_rate": 3.828828828828829e-06,
|
127 |
-
"loss": 0.5207,
|
128 |
-
"step": 170
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 0.2435723951285521,
|
132 |
-
"grad_norm": 1.2564229102790085,
|
133 |
-
"learning_rate": 4.0540540540540545e-06,
|
134 |
-
"loss": 0.5273,
|
135 |
-
"step": 180
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"epoch": 0.2571041948579161,
|
139 |
-
"grad_norm": 1.2582309298347993,
|
140 |
-
"learning_rate": 4.27927927927928e-06,
|
141 |
-
"loss": 0.4934,
|
142 |
-
"step": 190
|
143 |
-
},
|
144 |
-
{
|
145 |
-
"epoch": 0.2706359945872801,
|
146 |
-
"grad_norm": 1.227173613438421,
|
147 |
-
"learning_rate": 4.504504504504505e-06,
|
148 |
-
"loss": 0.5112,
|
149 |
-
"step": 200
|
150 |
-
},
|
151 |
-
{
|
152 |
-
"epoch": 0.28416779431664413,
|
153 |
-
"grad_norm": 1.3112186763708722,
|
154 |
-
"learning_rate": 4.72972972972973e-06,
|
155 |
-
"loss": 0.4982,
|
156 |
-
"step": 210
|
157 |
-
},
|
158 |
-
{
|
159 |
-
"epoch": 0.2976995940460081,
|
160 |
-
"grad_norm": 1.3637637039109458,
|
161 |
-
"learning_rate": 4.954954954954955e-06,
|
162 |
-
"loss": 0.5229,
|
163 |
-
"step": 220
|
164 |
-
},
|
165 |
-
{
|
166 |
-
"epoch": 0.3112313937753721,
|
167 |
-
"grad_norm": 1.375489718620912,
|
168 |
-
"learning_rate": 4.999801619861762e-06,
|
169 |
-
"loss": 0.5042,
|
170 |
-
"step": 230
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 0.32476319350473615,
|
174 |
-
"grad_norm": 1.2608972862462173,
|
175 |
-
"learning_rate": 4.99899575450882e-06,
|
176 |
-
"loss": 0.5127,
|
177 |
-
"step": 240
|
178 |
-
},
|
179 |
-
{
|
180 |
-
"epoch": 0.3382949932341001,
|
181 |
-
"grad_norm": 1.2911890277318863,
|
182 |
-
"learning_rate": 4.9975702048619155e-06,
|
183 |
-
"loss": 0.5033,
|
184 |
-
"step": 250
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"epoch": 0.35182679296346414,
|
188 |
-
"grad_norm": 1.3078317427998958,
|
189 |
-
"learning_rate": 4.995525324419338e-06,
|
190 |
-
"loss": 0.5002,
|
191 |
-
"step": 260
|
192 |
-
},
|
193 |
-
{
|
194 |
-
"epoch": 0.36535859269282817,
|
195 |
-
"grad_norm": 1.3588495282283148,
|
196 |
-
"learning_rate": 4.992861620256898e-06,
|
197 |
-
"loss": 0.5065,
|
198 |
-
"step": 270
|
199 |
-
},
|
200 |
-
{
|
201 |
-
"epoch": 0.37889039242219213,
|
202 |
-
"grad_norm": 1.3626322380792617,
|
203 |
-
"learning_rate": 4.98957975290218e-06,
|
204 |
-
"loss": 0.511,
|
205 |
-
"step": 280
|
206 |
-
},
|
207 |
-
{
|
208 |
-
"epoch": 0.39242219215155616,
|
209 |
-
"grad_norm": 1.3701159835791592,
|
210 |
-
"learning_rate": 4.985680536170754e-06,
|
211 |
-
"loss": 0.5137,
|
212 |
-
"step": 290
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 0.4059539918809202,
|
216 |
-
"grad_norm": 1.2997955232042016,
|
217 |
-
"learning_rate": 4.981164936964371e-06,
|
218 |
-
"loss": 0.4965,
|
219 |
-
"step": 300
|
220 |
-
},
|
221 |
-
{
|
222 |
-
"epoch": 0.41948579161028415,
|
223 |
-
"grad_norm": 1.3519542829203703,
|
224 |
-
"learning_rate": 4.976034075031193e-06,
|
225 |
-
"loss": 0.512,
|
226 |
-
"step": 310
|
227 |
-
},
|
228 |
-
{
|
229 |
-
"epoch": 0.4330175913396482,
|
230 |
-
"grad_norm": 1.2630076374904904,
|
231 |
-
"learning_rate": 4.970289222688129e-06,
|
232 |
-
"loss": 0.5028,
|
233 |
-
"step": 320
|
234 |
-
},
|
235 |
-
{
|
236 |
-
"epoch": 0.4465493910690122,
|
237 |
-
"grad_norm": 1.2707537109175924,
|
238 |
-
"learning_rate": 4.963931804505335e-06,
|
239 |
-
"loss": 0.5032,
|
240 |
-
"step": 330
|
241 |
-
},
|
242 |
-
{
|
243 |
-
"epoch": 0.46008119079837617,
|
244 |
-
"grad_norm": 1.2589722075840526,
|
245 |
-
"learning_rate": 4.956963396952954e-06,
|
246 |
-
"loss": 0.4913,
|
247 |
-
"step": 340
|
248 |
-
},
|
249 |
-
{
|
250 |
-
"epoch": 0.4736129905277402,
|
251 |
-
"grad_norm": 1.250431061653177,
|
252 |
-
"learning_rate": 4.949385728010199e-06,
|
253 |
-
"loss": 0.4805,
|
254 |
-
"step": 350
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 0.4871447902571042,
|
258 |
-
"grad_norm": 1.3372965532968473,
|
259 |
-
"learning_rate": 4.941200676736856e-06,
|
260 |
-
"loss": 0.4991,
|
261 |
-
"step": 360
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"epoch": 0.5006765899864682,
|
265 |
-
"grad_norm": 1.342662150633839,
|
266 |
-
"learning_rate": 4.932410272807328e-06,
|
267 |
-
"loss": 0.5066,
|
268 |
-
"step": 370
|
269 |
-
},
|
270 |
-
{
|
271 |
-
"epoch": 0.5142083897158322,
|
272 |
-
"grad_norm": 1.2238441786277905,
|
273 |
-
"learning_rate": 4.9230166960073325e-06,
|
274 |
-
"loss": 0.4863,
|
275 |
-
"step": 380
|
276 |
-
},
|
277 |
-
{
|
278 |
-
"epoch": 0.5277401894451962,
|
279 |
-
"grad_norm": 1.359535295509501,
|
280 |
-
"learning_rate": 4.913022275693372e-06,
|
281 |
-
"loss": 0.4949,
|
282 |
-
"step": 390
|
283 |
-
},
|
284 |
-
{
|
285 |
-
"epoch": 0.5412719891745602,
|
286 |
-
"grad_norm": 1.2168352667558966,
|
287 |
-
"learning_rate": 4.902429490215112e-06,
|
288 |
-
"loss": 0.4887,
|
289 |
-
"step": 400
|
290 |
-
},
|
291 |
-
{
|
292 |
-
"epoch": 0.5548037889039242,
|
293 |
-
"grad_norm": 1.4624621853482647,
|
294 |
-
"learning_rate": 4.891240966300822e-06,
|
295 |
-
"loss": 0.4969,
|
296 |
-
"step": 410
|
297 |
-
},
|
298 |
-
{
|
299 |
-
"epoch": 0.5683355886332883,
|
300 |
-
"grad_norm": 1.238588018136266,
|
301 |
-
"learning_rate": 4.879459478406012e-06,
|
302 |
-
"loss": 0.5067,
|
303 |
-
"step": 420
|
304 |
-
},
|
305 |
-
{
|
306 |
-
"epoch": 0.5818673883626523,
|
307 |
-
"grad_norm": 1.3181900309459351,
|
308 |
-
"learning_rate": 4.867087948025444e-06,
|
309 |
-
"loss": 0.4791,
|
310 |
-
"step": 430
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"epoch": 0.5953991880920162,
|
314 |
-
"grad_norm": 1.2954274899523053,
|
315 |
-
"learning_rate": 4.854129442968679e-06,
|
316 |
-
"loss": 0.4927,
|
317 |
-
"step": 440
|
318 |
-
},
|
319 |
-
{
|
320 |
-
"epoch": 0.6089309878213802,
|
321 |
-
"grad_norm": 1.4125967606025722,
|
322 |
-
"learning_rate": 4.8405871765993435e-06,
|
323 |
-
"loss": 0.4879,
|
324 |
-
"step": 450
|
325 |
-
},
|
326 |
-
{
|
327 |
-
"epoch": 0.6224627875507442,
|
328 |
-
"grad_norm": 1.3930229082121182,
|
329 |
-
"learning_rate": 4.8264645070382964e-06,
|
330 |
-
"loss": 0.5073,
|
331 |
-
"step": 460
|
332 |
-
},
|
333 |
-
{
|
334 |
-
"epoch": 0.6359945872801083,
|
335 |
-
"grad_norm": 1.0709300883023405,
|
336 |
-
"learning_rate": 4.8117649363309105e-06,
|
337 |
-
"loss": 0.4729,
|
338 |
-
"step": 470
|
339 |
-
},
|
340 |
-
{
|
341 |
-
"epoch": 0.6495263870094723,
|
342 |
-
"grad_norm": 1.2926318844200286,
|
343 |
-
"learning_rate": 4.796492109578655e-06,
|
344 |
-
"loss": 0.4956,
|
345 |
-
"step": 480
|
346 |
-
},
|
347 |
-
{
|
348 |
-
"epoch": 0.6630581867388363,
|
349 |
-
"grad_norm": 1.2313258024791178,
|
350 |
-
"learning_rate": 4.780649814035205e-06,
|
351 |
-
"loss": 0.5152,
|
352 |
-
"step": 490
|
353 |
-
},
|
354 |
-
{
|
355 |
-
"epoch": 0.6765899864682002,
|
356 |
-
"grad_norm": 1.178544127732,
|
357 |
-
"learning_rate": 4.764241978167314e-06,
|
358 |
-
"loss": 0.4859,
|
359 |
-
"step": 500
|
360 |
-
},
|
361 |
-
{
|
362 |
-
"epoch": 0.6901217861975643,
|
363 |
-
"grad_norm": 1.3295118207561514,
|
364 |
-
"learning_rate": 4.747272670680646e-06,
|
365 |
-
"loss": 0.4676,
|
366 |
-
"step": 510
|
367 |
-
},
|
368 |
-
{
|
369 |
-
"epoch": 0.7036535859269283,
|
370 |
-
"grad_norm": 1.2304742068887151,
|
371 |
-
"learning_rate": 4.729746099510853e-06,
|
372 |
-
"loss": 0.4678,
|
373 |
-
"step": 520
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"epoch": 0.7171853856562923,
|
377 |
-
"grad_norm": 1.3372876193995562,
|
378 |
-
"learning_rate": 4.711666610780115e-06,
|
379 |
-
"loss": 0.4831,
|
380 |
-
"step": 530
|
381 |
-
},
|
382 |
-
{
|
383 |
-
"epoch": 0.7307171853856563,
|
384 |
-
"grad_norm": 1.1886552687072083,
|
385 |
-
"learning_rate": 4.693038687719424e-06,
|
386 |
-
"loss": 0.4767,
|
387 |
-
"step": 540
|
388 |
-
},
|
389 |
-
{
|
390 |
-
"epoch": 0.7442489851150202,
|
391 |
-
"grad_norm": 1.1599254136343242,
|
392 |
-
"learning_rate": 4.673866949556854e-06,
|
393 |
-
"loss": 0.4936,
|
394 |
-
"step": 550
|
395 |
-
},
|
396 |
-
{
|
397 |
-
"epoch": 0.7577807848443843,
|
398 |
-
"grad_norm": 1.3619743128031154,
|
399 |
-
"learning_rate": 4.654156150372123e-06,
|
400 |
-
"loss": 0.4932,
|
401 |
-
"step": 560
|
402 |
-
},
|
403 |
-
{
|
404 |
-
"epoch": 0.7713125845737483,
|
405 |
-
"grad_norm": 1.2317704190385679,
|
406 |
-
"learning_rate": 4.633911177917701e-06,
|
407 |
-
"loss": 0.4823,
|
408 |
-
"step": 570
|
409 |
-
},
|
410 |
-
{
|
411 |
-
"epoch": 0.7848443843031123,
|
412 |
-
"grad_norm": 1.1895331578985897,
|
413 |
-
"learning_rate": 4.613137052406783e-06,
|
414 |
-
"loss": 0.4828,
|
415 |
-
"step": 580
|
416 |
-
},
|
417 |
-
{
|
418 |
-
"epoch": 0.7983761840324763,
|
419 |
-
"grad_norm": 1.2879457390422215,
|
420 |
-
"learning_rate": 4.5918389252684115e-06,
|
421 |
-
"loss": 0.4779,
|
422 |
-
"step": 590
|
423 |
-
},
|
424 |
-
{
|
425 |
-
"epoch": 0.8119079837618404,
|
426 |
-
"grad_norm": 1.2202436257043876,
|
427 |
-
"learning_rate": 4.570022077870051e-06,
|
428 |
-
"loss": 0.4875,
|
429 |
-
"step": 600
|
430 |
-
},
|
431 |
-
{
|
432 |
-
"epoch": 0.8254397834912043,
|
433 |
-
"grad_norm": 1.191014968745712,
|
434 |
-
"learning_rate": 4.547691920207958e-06,
|
435 |
-
"loss": 0.4726,
|
436 |
-
"step": 610
|
437 |
-
},
|
438 |
-
{
|
439 |
-
"epoch": 0.8389715832205683,
|
440 |
-
"grad_norm": 1.3456732382536576,
|
441 |
-
"learning_rate": 4.524853989565644e-06,
|
442 |
-
"loss": 0.4716,
|
443 |
-
"step": 620
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 0.8525033829499323,
|
447 |
-
"grad_norm": 1.1703319949253694,
|
448 |
-
"learning_rate": 4.501513949140776e-06,
|
449 |
-
"loss": 0.4715,
|
450 |
-
"step": 630
|
451 |
-
},
|
452 |
-
{
|
453 |
-
"epoch": 0.8660351826792964,
|
454 |
-
"grad_norm": 1.2604743747219656,
|
455 |
-
"learning_rate": 4.477677586640854e-06,
|
456 |
-
"loss": 0.483,
|
457 |
-
"step": 640
|
458 |
-
},
|
459 |
-
{
|
460 |
-
"epoch": 0.8795669824086604,
|
461 |
-
"grad_norm": 1.2589734283703884,
|
462 |
-
"learning_rate": 4.453350812848014e-06,
|
463 |
-
"loss": 0.4788,
|
464 |
-
"step": 650
|
465 |
-
},
|
466 |
-
{
|
467 |
-
"epoch": 0.8930987821380244,
|
468 |
-
"grad_norm": 1.3165298623822046,
|
469 |
-
"learning_rate": 4.428539660153315e-06,
|
470 |
-
"loss": 0.4781,
|
471 |
-
"step": 660
|
472 |
-
},
|
473 |
-
{
|
474 |
-
"epoch": 0.9066305818673883,
|
475 |
-
"grad_norm": 1.2879141623482424,
|
476 |
-
"learning_rate": 4.403250281060862e-06,
|
477 |
-
"loss": 0.4663,
|
478 |
-
"step": 670
|
479 |
-
},
|
480 |
-
{
|
481 |
-
"epoch": 0.9201623815967523,
|
482 |
-
"grad_norm": 1.2076038888483498,
|
483 |
-
"learning_rate": 4.377488946662152e-06,
|
484 |
-
"loss": 0.4808,
|
485 |
-
"step": 680
|
486 |
-
},
|
487 |
-
{
|
488 |
-
"epoch": 0.9336941813261164,
|
489 |
-
"grad_norm": 1.1851588037695613,
|
490 |
-
"learning_rate": 4.3512620450810115e-06,
|
491 |
-
"loss": 0.4793,
|
492 |
-
"step": 690
|
493 |
-
},
|
494 |
-
{
|
495 |
-
"epoch": 0.9472259810554804,
|
496 |
-
"grad_norm": 1.2950814486817164,
|
497 |
-
"learning_rate": 4.324576079889508e-06,
|
498 |
-
"loss": 0.4922,
|
499 |
-
"step": 700
|
500 |
-
},
|
501 |
-
{
|
502 |
-
"epoch": 0.9607577807848444,
|
503 |
-
"grad_norm": 1.201177645302697,
|
504 |
-
"learning_rate": 4.297437668495241e-06,
|
505 |
-
"loss": 0.4789,
|
506 |
-
"step": 710
|
507 |
-
},
|
508 |
-
{
|
509 |
-
"epoch": 0.9742895805142084,
|
510 |
-
"grad_norm": 1.217638325880889,
|
511 |
-
"learning_rate": 4.269853540500404e-06,
|
512 |
-
"loss": 0.4777,
|
513 |
-
"step": 720
|
514 |
-
},
|
515 |
-
{
|
516 |
-
"epoch": 0.9878213802435724,
|
517 |
-
"grad_norm": 1.2410357155495917,
|
518 |
-
"learning_rate": 4.2418305360330135e-06,
|
519 |
-
"loss": 0.4677,
|
520 |
-
"step": 730
|
521 |
-
},
|
522 |
-
{
|
523 |
-
"epoch": 1.0013531799729365,
|
524 |
-
"grad_norm": 1.4640185730269493,
|
525 |
-
"learning_rate": 4.21337560405075e-06,
|
526 |
-
"loss": 0.4706,
|
527 |
-
"step": 740
|
528 |
-
},
|
529 |
-
{
|
530 |
-
"epoch": 1.0148849797023005,
|
531 |
-
"grad_norm": 1.38525301927104,
|
532 |
-
"learning_rate": 4.184495800617795e-06,
|
533 |
-
"loss": 0.3663,
|
534 |
-
"step": 750
|
535 |
-
},
|
536 |
-
{
|
537 |
-
"epoch": 1.0284167794316643,
|
538 |
-
"grad_norm": 1.3150399206192376,
|
539 |
-
"learning_rate": 4.1551982871551195e-06,
|
540 |
-
"loss": 0.3446,
|
541 |
-
"step": 760
|
542 |
-
},
|
543 |
-
{
|
544 |
-
"epoch": 1.0419485791610283,
|
545 |
-
"grad_norm": 1.2508231428791732,
|
546 |
-
"learning_rate": 4.125490328664639e-06,
|
547 |
-
"loss": 0.3433,
|
548 |
-
"step": 770
|
549 |
-
},
|
550 |
-
{
|
551 |
-
"epoch": 1.0554803788903924,
|
552 |
-
"grad_norm": 1.1828710966111038,
|
553 |
-
"learning_rate": 4.095379291927689e-06,
|
554 |
-
"loss": 0.3372,
|
555 |
-
"step": 780
|
556 |
-
},
|
557 |
-
{
|
558 |
-
"epoch": 1.0690121786197564,
|
559 |
-
"grad_norm": 1.3234842465450887,
|
560 |
-
"learning_rate": 4.064872643678261e-06,
|
561 |
-
"loss": 0.3492,
|
562 |
-
"step": 790
|
563 |
-
},
|
564 |
-
{
|
565 |
-
"epoch": 1.0825439783491204,
|
566 |
-
"grad_norm": 1.3510823566344805,
|
567 |
-
"learning_rate": 4.033977948751445e-06,
|
568 |
-
"loss": 0.3538,
|
569 |
-
"step": 800
|
570 |
-
},
|
571 |
-
{
|
572 |
-
"epoch": 1.0960757780784844,
|
573 |
-
"grad_norm": 1.162520339907919,
|
574 |
-
"learning_rate": 4.002702868207563e-06,
|
575 |
-
"loss": 0.3462,
|
576 |
-
"step": 810
|
577 |
-
},
|
578 |
-
{
|
579 |
-
"epoch": 1.1096075778078485,
|
580 |
-
"grad_norm": 1.2976046378570087,
|
581 |
-
"learning_rate": 3.971055157432421e-06,
|
582 |
-
"loss": 0.3474,
|
583 |
-
"step": 820
|
584 |
-
},
|
585 |
-
{
|
586 |
-
"epoch": 1.1231393775372125,
|
587 |
-
"grad_norm": 1.2857491708515112,
|
588 |
-
"learning_rate": 3.939042664214185e-06,
|
589 |
-
"loss": 0.3365,
|
590 |
-
"step": 830
|
591 |
-
},
|
592 |
-
{
|
593 |
-
"epoch": 1.1366711772665765,
|
594 |
-
"grad_norm": 1.2956865515811835,
|
595 |
-
"learning_rate": 3.9066733267973335e-06,
|
596 |
-
"loss": 0.3483,
|
597 |
-
"step": 840
|
598 |
-
},
|
599 |
-
{
|
600 |
-
"epoch": 1.1502029769959405,
|
601 |
-
"grad_norm": 1.2863826250955843,
|
602 |
-
"learning_rate": 3.873955171914196e-06,
|
603 |
-
"loss": 0.3515,
|
604 |
-
"step": 850
|
605 |
-
},
|
606 |
-
{
|
607 |
-
"epoch": 1.1637347767253043,
|
608 |
-
"grad_norm": 1.48236681103959,
|
609 |
-
"learning_rate": 3.840896312794523e-06,
|
610 |
-
"loss": 0.3502,
|
611 |
-
"step": 860
|
612 |
-
},
|
613 |
-
{
|
614 |
-
"epoch": 1.1772665764546684,
|
615 |
-
"grad_norm": 1.333493280950809,
|
616 |
-
"learning_rate": 3.8075049471536317e-06,
|
617 |
-
"loss": 0.3402,
|
618 |
-
"step": 870
|
619 |
-
},
|
620 |
-
{
|
621 |
-
"epoch": 1.1907983761840324,
|
622 |
-
"grad_norm": 1.3845427764767562,
|
623 |
-
"learning_rate": 3.773789355159587e-06,
|
624 |
-
"loss": 0.3634,
|
625 |
-
"step": 880
|
626 |
-
},
|
627 |
-
{
|
628 |
-
"epoch": 1.2043301759133964,
|
629 |
-
"grad_norm": 1.1768813996050986,
|
630 |
-
"learning_rate": 3.7397578973799432e-06,
|
631 |
-
"loss": 0.3426,
|
632 |
-
"step": 890
|
633 |
-
},
|
634 |
-
{
|
635 |
-
"epoch": 1.2178619756427604,
|
636 |
-
"grad_norm": 1.2400576449491367,
|
637 |
-
"learning_rate": 3.7054190127085414e-06,
|
638 |
-
"loss": 0.3643,
|
639 |
-
"step": 900
|
640 |
-
},
|
641 |
-
{
|
642 |
-
"epoch": 1.2313937753721245,
|
643 |
-
"grad_norm": 1.3771269453073722,
|
644 |
-
"learning_rate": 3.6707812162728963e-06,
|
645 |
-
"loss": 0.3618,
|
646 |
-
"step": 910
|
647 |
-
},
|
648 |
-
{
|
649 |
-
"epoch": 1.2449255751014885,
|
650 |
-
"grad_norm": 1.342260391925942,
|
651 |
-
"learning_rate": 3.6358530973226634e-06,
|
652 |
-
"loss": 0.3619,
|
653 |
-
"step": 920
|
654 |
-
},
|
655 |
-
{
|
656 |
-
"epoch": 1.2584573748308525,
|
657 |
-
"grad_norm": 1.305612405058302,
|
658 |
-
"learning_rate": 3.600643317099742e-06,
|
659 |
-
"loss": 0.343,
|
660 |
-
"step": 930
|
661 |
-
},
|
662 |
-
{
|
663 |
-
"epoch": 1.2719891745602165,
|
664 |
-
"grad_norm": 1.2499532104940625,
|
665 |
-
"learning_rate": 3.5651606066905125e-06,
|
666 |
-
"loss": 0.3469,
|
667 |
-
"step": 940
|
668 |
-
},
|
669 |
-
{
|
670 |
-
"epoch": 1.2855209742895806,
|
671 |
-
"grad_norm": 1.3139038237546603,
|
672 |
-
"learning_rate": 3.529413764860763e-06,
|
673 |
-
"loss": 0.3547,
|
674 |
-
"step": 950
|
675 |
-
},
|
676 |
-
{
|
677 |
-
"epoch": 1.2990527740189446,
|
678 |
-
"grad_norm": 1.3891975036748492,
|
679 |
-
"learning_rate": 3.493411655873826e-06,
|
680 |
-
"loss": 0.3565,
|
681 |
-
"step": 960
|
682 |
-
},
|
683 |
-
{
|
684 |
-
"epoch": 1.3125845737483086,
|
685 |
-
"grad_norm": 1.31663081113206,
|
686 |
-
"learning_rate": 3.4571632072924853e-06,
|
687 |
-
"loss": 0.3459,
|
688 |
-
"step": 970
|
689 |
-
},
|
690 |
-
{
|
691 |
-
"epoch": 1.3261163734776726,
|
692 |
-
"grad_norm": 1.4316096903150302,
|
693 |
-
"learning_rate": 3.4206774077651706e-06,
|
694 |
-
"loss": 0.3435,
|
695 |
-
"step": 980
|
696 |
-
},
|
697 |
-
{
|
698 |
-
"epoch": 1.3396481732070367,
|
699 |
-
"grad_norm": 1.2148334230866564,
|
700 |
-
"learning_rate": 3.383963304797016e-06,
|
701 |
-
"loss": 0.3505,
|
702 |
-
"step": 990
|
703 |
-
},
|
704 |
-
{
|
705 |
-
"epoch": 1.3531799729364005,
|
706 |
-
"grad_norm": 1.371605209380619,
|
707 |
-
"learning_rate": 3.347030002506321e-06,
|
708 |
-
"loss": 0.3367,
|
709 |
-
"step": 1000
|
710 |
-
},
|
711 |
-
{
|
712 |
-
"epoch": 1.3667117726657645,
|
713 |
-
"grad_norm": 1.2492881761277035,
|
714 |
-
"learning_rate": 3.309886659366967e-06,
|
715 |
-
"loss": 0.3409,
|
716 |
-
"step": 1010
|
717 |
-
},
|
718 |
-
{
|
719 |
-
"epoch": 1.3802435723951285,
|
720 |
-
"grad_norm": 1.3599908217112529,
|
721 |
-
"learning_rate": 3.272542485937369e-06,
|
722 |
-
"loss": 0.3485,
|
723 |
-
"step": 1020
|
724 |
-
},
|
725 |
-
{
|
726 |
-
"epoch": 1.3937753721244925,
|
727 |
-
"grad_norm": 1.3587500825976617,
|
728 |
-
"learning_rate": 3.2350067425764932e-06,
|
729 |
-
"loss": 0.3564,
|
730 |
-
"step": 1030
|
731 |
-
},
|
732 |
-
{
|
733 |
-
"epoch": 1.4073071718538566,
|
734 |
-
"grad_norm": 1.286120602039562,
|
735 |
-
"learning_rate": 3.1972887371475404e-06,
|
736 |
-
"loss": 0.3445,
|
737 |
-
"step": 1040
|
738 |
-
},
|
739 |
-
{
|
740 |
-
"epoch": 1.4208389715832206,
|
741 |
-
"grad_norm": 1.3034585004391024,
|
742 |
-
"learning_rate": 3.1593978227098442e-06,
|
743 |
-
"loss": 0.3499,
|
744 |
-
"step": 1050
|
745 |
-
},
|
746 |
-
{
|
747 |
-
"epoch": 1.4343707713125846,
|
748 |
-
"grad_norm": 1.4093897542299632,
|
749 |
-
"learning_rate": 3.1213433951995585e-06,
|
750 |
-
"loss": 0.3476,
|
751 |
-
"step": 1060
|
752 |
-
},
|
753 |
-
{
|
754 |
-
"epoch": 1.4479025710419486,
|
755 |
-
"grad_norm": 1.2311850270587112,
|
756 |
-
"learning_rate": 3.0831348910997206e-06,
|
757 |
-
"loss": 0.3364,
|
758 |
-
"step": 1070
|
759 |
-
},
|
760 |
-
{
|
761 |
-
"epoch": 1.4614343707713127,
|
762 |
-
"grad_norm": 1.222347605205662,
|
763 |
-
"learning_rate": 3.0447817851002493e-06,
|
764 |
-
"loss": 0.3479,
|
765 |
-
"step": 1080
|
766 |
-
},
|
767 |
-
{
|
768 |
-
"epoch": 1.4749661705006765,
|
769 |
-
"grad_norm": 1.296829055261883,
|
770 |
-
"learning_rate": 3.0062935877484807e-06,
|
771 |
-
"loss": 0.3483,
|
772 |
-
"step": 1090
|
773 |
-
},
|
774 |
-
{
|
775 |
-
"epoch": 1.4884979702300405,
|
776 |
-
"grad_norm": 1.4143686463454304,
|
777 |
-
"learning_rate": 2.9676798430908e-06,
|
778 |
-
"loss": 0.3468,
|
779 |
-
"step": 1100
|
780 |
-
},
|
781 |
-
{
|
782 |
-
"epoch": 1.5020297699594045,
|
783 |
-
"grad_norm": 1.3314404969152827,
|
784 |
-
"learning_rate": 2.9289501263059796e-06,
|
785 |
-
"loss": 0.3526,
|
786 |
-
"step": 1110
|
787 |
-
},
|
788 |
-
{
|
789 |
-
"epoch": 1.5155615696887685,
|
790 |
-
"grad_norm": 1.2209137417793836,
|
791 |
-
"learning_rate": 2.890114041330782e-06,
|
792 |
-
"loss": 0.3527,
|
793 |
-
"step": 1120
|
794 |
-
},
|
795 |
-
{
|
796 |
-
"epoch": 1.5290933694181326,
|
797 |
-
"grad_norm": 1.3653030646734905,
|
798 |
-
"learning_rate": 2.8511812184784476e-06,
|
799 |
-
"loss": 0.3486,
|
800 |
-
"step": 1130
|
801 |
-
},
|
802 |
-
{
|
803 |
-
"epoch": 1.5426251691474966,
|
804 |
-
"grad_norm": 1.3012446208990969,
|
805 |
-
"learning_rate": 2.8121613120506274e-06,
|
806 |
-
"loss": 0.3541,
|
807 |
-
"step": 1140
|
808 |
-
},
|
809 |
-
{
|
810 |
-
"epoch": 1.5561569688768606,
|
811 |
-
"grad_norm": 1.1960147547589701,
|
812 |
-
"learning_rate": 2.7730639979433778e-06,
|
813 |
-
"loss": 0.3473,
|
814 |
-
"step": 1150
|
815 |
-
},
|
816 |
-
{
|
817 |
-
"epoch": 1.5696887686062246,
|
818 |
-
"grad_norm": 1.4960354983589137,
|
819 |
-
"learning_rate": 2.733898971247795e-06,
|
820 |
-
"loss": 0.3456,
|
821 |
-
"step": 1160
|
822 |
-
},
|
823 |
-
{
|
824 |
-
"epoch": 1.5832205683355887,
|
825 |
-
"grad_norm": 1.2152217200297626,
|
826 |
-
"learning_rate": 2.6946759438458898e-06,
|
827 |
-
"loss": 0.3433,
|
828 |
-
"step": 1170
|
829 |
-
},
|
830 |
-
{
|
831 |
-
"epoch": 1.5967523680649527,
|
832 |
-
"grad_norm": 1.3453974757862506,
|
833 |
-
"learning_rate": 2.655404642002304e-06,
|
834 |
-
"loss": 0.3409,
|
835 |
-
"step": 1180
|
836 |
-
},
|
837 |
-
{
|
838 |
-
"epoch": 1.6102841677943167,
|
839 |
-
"grad_norm": 1.3428793347679469,
|
840 |
-
"learning_rate": 2.6160948039524497e-06,
|
841 |
-
"loss": 0.3419,
|
842 |
-
"step": 1190
|
843 |
-
},
|
844 |
-
{
|
845 |
-
"epoch": 1.6238159675236807,
|
846 |
-
"grad_norm": 1.2285874250356115,
|
847 |
-
"learning_rate": 2.576756177487694e-06,
|
848 |
-
"loss": 0.3508,
|
849 |
-
"step": 1200
|
850 |
-
},
|
851 |
-
{
|
852 |
-
"epoch": 1.6373477672530448,
|
853 |
-
"grad_norm": 1.3449344602808873,
|
854 |
-
"learning_rate": 2.5373985175381595e-06,
|
855 |
-
"loss": 0.3503,
|
856 |
-
"step": 1210
|
857 |
-
},
|
858 |
-
{
|
859 |
-
"epoch": 1.6508795669824088,
|
860 |
-
"grad_norm": 1.296420958776628,
|
861 |
-
"learning_rate": 2.4980315837537682e-06,
|
862 |
-
"loss": 0.3562,
|
863 |
-
"step": 1220
|
864 |
-
},
|
865 |
-
{
|
866 |
-
"epoch": 1.6644113667117728,
|
867 |
-
"grad_norm": 1.3437387415224382,
|
868 |
-
"learning_rate": 2.458665138084104e-06,
|
869 |
-
"loss": 0.3405,
|
870 |
-
"step": 1230
|
871 |
-
},
|
872 |
-
{
|
873 |
-
"epoch": 1.6779431664411368,
|
874 |
-
"grad_norm": 1.388342667143761,
|
875 |
-
"learning_rate": 2.4193089423577125e-06,
|
876 |
-
"loss": 0.3609,
|
877 |
-
"step": 1240
|
878 |
-
},
|
879 |
-
{
|
880 |
-
"epoch": 1.6914749661705006,
|
881 |
-
"grad_norm": 1.2780103853967297,
|
882 |
-
"learning_rate": 2.379972755861427e-06,
|
883 |
-
"loss": 0.3464,
|
884 |
-
"step": 1250
|
885 |
-
},
|
886 |
-
{
|
887 |
-
"epoch": 1.7050067658998647,
|
888 |
-
"grad_norm": 1.3272035289197703,
|
889 |
-
"learning_rate": 2.3406663329203235e-06,
|
890 |
-
"loss": 0.3495,
|
891 |
-
"step": 1260
|
892 |
-
},
|
893 |
-
{
|
894 |
-
"epoch": 1.7185385656292287,
|
895 |
-
"grad_norm": 1.329132748454747,
|
896 |
-
"learning_rate": 2.3013994204789125e-06,
|
897 |
-
"loss": 0.3445,
|
898 |
-
"step": 1270
|
899 |
-
},
|
900 |
-
{
|
901 |
-
"epoch": 1.7320703653585927,
|
902 |
-
"grad_norm": 1.398385700455576,
|
903 |
-
"learning_rate": 2.262181755684152e-06,
|
904 |
-
"loss": 0.3525,
|
905 |
-
"step": 1280
|
906 |
-
},
|
907 |
-
{
|
908 |
-
"epoch": 1.7456021650879567,
|
909 |
-
"grad_norm": 1.3017040678134042,
|
910 |
-
"learning_rate": 2.2230230634709004e-06,
|
911 |
-
"loss": 0.3437,
|
912 |
-
"step": 1290
|
913 |
-
},
|
914 |
-
{
|
915 |
-
"epoch": 1.7591339648173205,
|
916 |
-
"grad_norm": 1.2733756916822523,
|
917 |
-
"learning_rate": 2.1839330541503846e-06,
|
918 |
-
"loss": 0.3507,
|
919 |
-
"step": 1300
|
920 |
-
},
|
921 |
-
{
|
922 |
-
"epoch": 1.7726657645466846,
|
923 |
-
"grad_norm": 1.2687781856621299,
|
924 |
-
"learning_rate": 2.14492142100231e-06,
|
925 |
-
"loss": 0.343,
|
926 |
-
"step": 1310
|
927 |
-
},
|
928 |
-
{
|
929 |
-
"epoch": 1.7861975642760486,
|
930 |
-
"grad_norm": 1.2837756754284302,
|
931 |
-
"learning_rate": 2.105997837871179e-06,
|
932 |
-
"loss": 0.3567,
|
933 |
-
"step": 1320
|
934 |
-
},
|
935 |
-
{
|
936 |
-
"epoch": 1.7997293640054126,
|
937 |
-
"grad_norm": 1.2388730929923404,
|
938 |
-
"learning_rate": 2.0671719567674396e-06,
|
939 |
-
"loss": 0.344,
|
940 |
-
"step": 1330
|
941 |
-
},
|
942 |
-
{
|
943 |
-
"epoch": 1.8132611637347766,
|
944 |
-
"grad_norm": 1.2901053029094909,
|
945 |
-
"learning_rate": 2.028453405474043e-06,
|
946 |
-
"loss": 0.3517,
|
947 |
-
"step": 1340
|
948 |
-
},
|
949 |
-
{
|
950 |
-
"epoch": 1.8267929634641407,
|
951 |
-
"grad_norm": 1.2731165360362213,
|
952 |
-
"learning_rate": 1.9898517851590085e-06,
|
953 |
-
"loss": 0.3386,
|
954 |
-
"step": 1350
|
955 |
-
},
|
956 |
-
{
|
957 |
-
"epoch": 1.8403247631935047,
|
958 |
-
"grad_norm": 1.3976657362615021,
|
959 |
-
"learning_rate": 1.951376667994594e-06,
|
960 |
-
"loss": 0.341,
|
961 |
-
"step": 1360
|
962 |
-
},
|
963 |
-
{
|
964 |
-
"epoch": 1.8538565629228687,
|
965 |
-
"grad_norm": 1.3707046787252906,
|
966 |
-
"learning_rate": 1.913037594783648e-06,
|
967 |
-
"loss": 0.3537,
|
968 |
-
"step": 1370
|
969 |
-
},
|
970 |
-
{
|
971 |
-
"epoch": 1.8673883626522327,
|
972 |
-
"grad_norm": 1.2631835198560484,
|
973 |
-
"learning_rate": 1.8748440725937485e-06,
|
974 |
-
"loss": 0.3565,
|
975 |
-
"step": 1380
|
976 |
-
},
|
977 |
-
{
|
978 |
-
"epoch": 1.8809201623815968,
|
979 |
-
"grad_norm": 1.2721719565376515,
|
980 |
-
"learning_rate": 1.8368055723997013e-06,
|
981 |
-
"loss": 0.3522,
|
982 |
-
"step": 1390
|
983 |
-
},
|
984 |
-
{
|
985 |
-
"epoch": 1.8944519621109608,
|
986 |
-
"grad_norm": 1.2577752707995227,
|
987 |
-
"learning_rate": 1.7989315267349936e-06,
|
988 |
-
"loss": 0.3454,
|
989 |
-
"step": 1400
|
990 |
-
},
|
991 |
-
{
|
992 |
-
"epoch": 1.9079837618403248,
|
993 |
-
"grad_norm": 1.514027269766047,
|
994 |
-
"learning_rate": 1.7612313273527731e-06,
|
995 |
-
"loss": 0.3496,
|
996 |
-
"step": 1410
|
997 |
-
},
|
998 |
-
{
|
999 |
-
"epoch": 1.9215155615696888,
|
1000 |
-
"grad_norm": 1.292691163793762,
|
1001 |
-
"learning_rate": 1.7237143228969488e-06,
|
1002 |
-
"loss": 0.348,
|
1003 |
-
"step": 1420
|
1004 |
-
},
|
1005 |
-
{
|
1006 |
-
"epoch": 1.9350473612990529,
|
1007 |
-
"grad_norm": 1.3014087462969852,
|
1008 |
-
"learning_rate": 1.686389816583973e-06,
|
1009 |
-
"loss": 0.3577,
|
1010 |
-
"step": 1430
|
1011 |
-
},
|
1012 |
-
{
|
1013 |
-
"epoch": 1.9485791610284169,
|
1014 |
-
"grad_norm": 1.214993986220213,
|
1015 |
-
"learning_rate": 1.6492670638958924e-06,
|
1016 |
-
"loss": 0.3362,
|
1017 |
-
"step": 1440
|
1018 |
-
},
|
1019 |
-
{
|
1020 |
-
"epoch": 1.962110960757781,
|
1021 |
-
"grad_norm": 1.221639454284981,
|
1022 |
-
"learning_rate": 1.6123552702852375e-06,
|
1023 |
-
"loss": 0.3347,
|
1024 |
-
"step": 1450
|
1025 |
-
},
|
1026 |
-
{
|
1027 |
-
"epoch": 1.975642760487145,
|
1028 |
-
"grad_norm": 1.36951304107227,
|
1029 |
-
"learning_rate": 1.5756635888923122e-06,
|
1030 |
-
"loss": 0.3408,
|
1031 |
-
"step": 1460
|
1032 |
-
},
|
1033 |
-
{
|
1034 |
-
"epoch": 1.989174560216509,
|
1035 |
-
"grad_norm": 1.291050299529943,
|
1036 |
-
"learning_rate": 1.539201118275463e-06,
|
1037 |
-
"loss": 0.3516,
|
1038 |
-
"step": 1470
|
1039 |
-
},
|
1040 |
-
{
|
1041 |
-
"epoch": 2.002706359945873,
|
1042 |
-
"grad_norm": 1.5299892777665929,
|
1043 |
-
"learning_rate": 1.502976900154876e-06,
|
1044 |
-
"loss": 0.3294,
|
1045 |
-
"step": 1480
|
1046 |
-
},
|
1047 |
-
{
|
1048 |
-
"epoch": 2.016238159675237,
|
1049 |
-
"grad_norm": 1.4268912812659167,
|
1050 |
-
"learning_rate": 1.4669999171704742e-06,
|
1051 |
-
"loss": 0.2451,
|
1052 |
-
"step": 1490
|
1053 |
-
},
|
1054 |
-
{
|
1055 |
-
"epoch": 2.029769959404601,
|
1056 |
-
"grad_norm": 1.3062098172273324,
|
1057 |
-
"learning_rate": 1.43127909065446e-06,
|
1058 |
-
"loss": 0.2438,
|
1059 |
-
"step": 1500
|
1060 |
-
},
|
1061 |
-
{
|
1062 |
-
"epoch": 2.0433017591339646,
|
1063 |
-
"grad_norm": 1.4093327122429686,
|
1064 |
-
"learning_rate": 1.395823278419065e-06,
|
1065 |
-
"loss": 0.2458,
|
1066 |
-
"step": 1510
|
1067 |
-
},
|
1068 |
-
{
|
1069 |
-
"epoch": 2.0568335588633286,
|
1070 |
-
"grad_norm": 1.3446778247332223,
|
1071 |
-
"learning_rate": 1.3606412725600471e-06,
|
1072 |
-
"loss": 0.2483,
|
1073 |
-
"step": 1520
|
1074 |
-
},
|
1075 |
-
{
|
1076 |
-
"epoch": 2.0703653585926927,
|
1077 |
-
"grad_norm": 1.288956301952182,
|
1078 |
-
"learning_rate": 1.3257417972764853e-06,
|
1079 |
-
"loss": 0.242,
|
1080 |
-
"step": 1530
|
1081 |
-
},
|
1082 |
-
{
|
1083 |
-
"epoch": 2.0838971583220567,
|
1084 |
-
"grad_norm": 1.2722385458217775,
|
1085 |
-
"learning_rate": 1.2911335067074108e-06,
|
1086 |
-
"loss": 0.2318,
|
1087 |
-
"step": 1540
|
1088 |
-
},
|
1089 |
-
{
|
1090 |
-
"epoch": 2.0974289580514207,
|
1091 |
-
"grad_norm": 1.3902319886251955,
|
1092 |
-
"learning_rate": 1.2568249827858153e-06,
|
1093 |
-
"loss": 0.2331,
|
1094 |
-
"step": 1550
|
1095 |
-
},
|
1096 |
-
{
|
1097 |
-
"epoch": 2.1109607577807847,
|
1098 |
-
"grad_norm": 1.343020265634266,
|
1099 |
-
"learning_rate": 1.2228247331105541e-06,
|
1100 |
-
"loss": 0.242,
|
1101 |
-
"step": 1560
|
1102 |
-
},
|
1103 |
-
{
|
1104 |
-
"epoch": 2.1244925575101488,
|
1105 |
-
"grad_norm": 1.3796390105439542,
|
1106 |
-
"learning_rate": 1.1891411888366933e-06,
|
1107 |
-
"loss": 0.2494,
|
1108 |
-
"step": 1570
|
1109 |
-
},
|
1110 |
-
{
|
1111 |
-
"epoch": 2.138024357239513,
|
1112 |
-
"grad_norm": 1.287377449079076,
|
1113 |
-
"learning_rate": 1.1557827025848048e-06,
|
1114 |
-
"loss": 0.2373,
|
1115 |
-
"step": 1580
|
1116 |
-
},
|
1117 |
-
{
|
1118 |
-
"epoch": 2.151556156968877,
|
1119 |
-
"grad_norm": 1.2636968613031825,
|
1120 |
-
"learning_rate": 1.122757546369744e-06,
|
1121 |
-
"loss": 0.2276,
|
1122 |
-
"step": 1590
|
1123 |
-
},
|
1124 |
-
{
|
1125 |
-
"epoch": 2.165087956698241,
|
1126 |
-
"grad_norm": 1.3768480512381478,
|
1127 |
-
"learning_rate": 1.0900739095494053e-06,
|
1128 |
-
"loss": 0.2392,
|
1129 |
-
"step": 1600
|
1130 |
-
},
|
1131 |
-
{
|
1132 |
-
"epoch": 2.178619756427605,
|
1133 |
-
"grad_norm": 1.3082506088448747,
|
1134 |
-
"learning_rate": 1.0577398967939824e-06,
|
1135 |
-
"loss": 0.2361,
|
1136 |
-
"step": 1610
|
1137 |
-
},
|
1138 |
-
{
|
1139 |
-
"epoch": 2.192151556156969,
|
1140 |
-
"grad_norm": 1.4034690066329039,
|
1141 |
-
"learning_rate": 1.0257635260762281e-06,
|
1142 |
-
"loss": 0.2319,
|
1143 |
-
"step": 1620
|
1144 |
-
},
|
1145 |
-
{
|
1146 |
-
"epoch": 2.205683355886333,
|
1147 |
-
"grad_norm": 1.2317759668032917,
|
1148 |
-
"learning_rate": 9.941527266832064e-07,
|
1149 |
-
"loss": 0.2493,
|
1150 |
-
"step": 1630
|
1151 |
-
},
|
1152 |
-
{
|
1153 |
-
"epoch": 2.219215155615697,
|
1154 |
-
"grad_norm": 1.2971411614293273,
|
1155 |
-
"learning_rate": 9.62915337250044e-07,
|
1156 |
-
"loss": 0.2277,
|
1157 |
-
"step": 1640
|
1158 |
-
},
|
1159 |
-
{
|
1160 |
-
"epoch": 2.232746955345061,
|
1161 |
-
"grad_norm": 1.3135829424346515,
|
1162 |
-
"learning_rate": 9.320591038161575e-07,
|
1163 |
-
"loss": 0.2328,
|
1164 |
-
"step": 1650
|
1165 |
-
},
|
1166 |
-
{
|
1167 |
-
"epoch": 2.246278755074425,
|
1168 |
-
"grad_norm": 1.38689896774966,
|
1169 |
-
"learning_rate": 9.015916779044429e-07,
|
1170 |
-
"loss": 0.2376,
|
1171 |
-
"step": 1660
|
1172 |
-
},
|
1173 |
-
{
|
1174 |
-
"epoch": 2.259810554803789,
|
1175 |
-
"grad_norm": 1.3904871269861285,
|
1176 |
-
"learning_rate": 8.715206146238989e-07,
|
1177 |
-
"loss": 0.2365,
|
1178 |
-
"step": 1670
|
1179 |
-
},
|
1180 |
-
{
|
1181 |
-
"epoch": 2.273342354533153,
|
1182 |
-
"grad_norm": 1.2344911252878241,
|
1183 |
-
"learning_rate": 8.418533707961635e-07,
|
1184 |
-
"loss": 0.2398,
|
1185 |
-
"step": 1680
|
1186 |
-
},
|
1187 |
-
{
|
1188 |
-
"epoch": 2.286874154262517,
|
1189 |
-
"grad_norm": 1.404914010406795,
|
1190 |
-
"learning_rate": 8.125973031064241e-07,
|
1191 |
-
"loss": 0.2375,
|
1192 |
-
"step": 1690
|
1193 |
-
},
|
1194 |
-
{
|
1195 |
-
"epoch": 2.300405953991881,
|
1196 |
-
"grad_norm": 1.4005244602892066,
|
1197 |
-
"learning_rate": 7.837596662791492e-07,
|
1198 |
-
"loss": 0.2418,
|
1199 |
-
"step": 1700
|
1200 |
-
},
|
1201 |
-
{
|
1202 |
-
"epoch": 2.313937753721245,
|
1203 |
-
"grad_norm": 1.3420607852511892,
|
1204 |
-
"learning_rate": 7.553476112791156e-07,
|
1205 |
-
"loss": 0.2332,
|
1206 |
-
"step": 1710
|
1207 |
-
},
|
1208 |
-
{
|
1209 |
-
"epoch": 2.3274695534506087,
|
1210 |
-
"grad_norm": 1.3547101946313251,
|
1211 |
-
"learning_rate": 7.273681835381569e-07,
|
1212 |
-
"loss": 0.229,
|
1213 |
-
"step": 1720
|
1214 |
-
},
|
1215 |
-
{
|
1216 |
-
"epoch": 2.3410013531799727,
|
1217 |
-
"grad_norm": 1.4020705762318206,
|
1218 |
-
"learning_rate": 6.998283212080873e-07,
|
1219 |
-
"loss": 0.2328,
|
1220 |
-
"step": 1730
|
1221 |
-
},
|
1222 |
-
{
|
1223 |
-
"epoch": 2.3545331529093367,
|
1224 |
-
"grad_norm": 1.3623596919516412,
|
1225 |
-
"learning_rate": 6.727348534402217e-07,
|
1226 |
-
"loss": 0.2525,
|
1227 |
-
"step": 1740
|
1228 |
-
},
|
1229 |
-
{
|
1230 |
-
"epoch": 2.3680649526387008,
|
1231 |
-
"grad_norm": 1.3512700634608603,
|
1232 |
-
"learning_rate": 6.460944986919296e-07,
|
1233 |
-
"loss": 0.2408,
|
1234 |
-
"step": 1750
|
1235 |
-
},
|
1236 |
-
{
|
1237 |
-
"epoch": 2.381596752368065,
|
1238 |
-
"grad_norm": 1.3266784606321098,
|
1239 |
-
"learning_rate": 6.199138630606389e-07,
|
1240 |
-
"loss": 0.234,
|
1241 |
-
"step": 1760
|
1242 |
-
},
|
1243 |
-
{
|
1244 |
-
"epoch": 2.395128552097429,
|
1245 |
-
"grad_norm": 1.3645670227625384,
|
1246 |
-
"learning_rate": 5.941994386456962e-07,
|
1247 |
-
"loss": 0.2339,
|
1248 |
-
"step": 1770
|
1249 |
-
},
|
1250 |
-
{
|
1251 |
-
"epoch": 2.408660351826793,
|
1252 |
-
"grad_norm": 1.4293775086324754,
|
1253 |
-
"learning_rate": 5.689576019385015e-07,
|
1254 |
-
"loss": 0.2386,
|
1255 |
-
"step": 1780
|
1256 |
-
},
|
1257 |
-
{
|
1258 |
-
"epoch": 2.422192151556157,
|
1259 |
-
"grad_norm": 1.4511738533160017,
|
1260 |
-
"learning_rate": 5.441946122413086e-07,
|
1261 |
-
"loss": 0.2456,
|
1262 |
-
"step": 1790
|
1263 |
-
},
|
1264 |
-
{
|
1265 |
-
"epoch": 2.435723951285521,
|
1266 |
-
"grad_norm": 1.4144969812794062,
|
1267 |
-
"learning_rate": 5.199166101150854e-07,
|
1268 |
-
"loss": 0.242,
|
1269 |
-
"step": 1800
|
1270 |
-
},
|
1271 |
-
{
|
1272 |
-
"epoch": 2.449255751014885,
|
1273 |
-
"grad_norm": 1.3760683860213159,
|
1274 |
-
"learning_rate": 4.96129615856816e-07,
|
1275 |
-
"loss": 0.2319,
|
1276 |
-
"step": 1810
|
1277 |
-
},
|
1278 |
-
{
|
1279 |
-
"epoch": 2.462787550744249,
|
1280 |
-
"grad_norm": 1.2962323322234228,
|
1281 |
-
"learning_rate": 4.7283952800663086e-07,
|
1282 |
-
"loss": 0.239,
|
1283 |
-
"step": 1820
|
1284 |
-
},
|
1285 |
-
{
|
1286 |
-
"epoch": 2.476319350473613,
|
1287 |
-
"grad_norm": 1.3785919346369462,
|
1288 |
-
"learning_rate": 4.500521218851234e-07,
|
1289 |
-
"loss": 0.2291,
|
1290 |
-
"step": 1830
|
1291 |
-
},
|
1292 |
-
{
|
1293 |
-
"epoch": 2.489851150202977,
|
1294 |
-
"grad_norm": 1.3198852846590903,
|
1295 |
-
"learning_rate": 4.2777304816122744e-07,
|
1296 |
-
"loss": 0.2294,
|
1297 |
-
"step": 1840
|
1298 |
-
},
|
1299 |
-
{
|
1300 |
-
"epoch": 2.503382949932341,
|
1301 |
-
"grad_norm": 1.3791429787991882,
|
1302 |
-
"learning_rate": 4.0600783145099935e-07,
|
1303 |
-
"loss": 0.2398,
|
1304 |
-
"step": 1850
|
1305 |
-
},
|
1306 |
-
{
|
1307 |
-
"epoch": 2.516914749661705,
|
1308 |
-
"grad_norm": 1.3758327911725443,
|
1309 |
-
"learning_rate": 3.847618689476612e-07,
|
1310 |
-
"loss": 0.2311,
|
1311 |
-
"step": 1860
|
1312 |
-
},
|
1313 |
-
{
|
1314 |
-
"epoch": 2.530446549391069,
|
1315 |
-
"grad_norm": 1.329309433256462,
|
1316 |
-
"learning_rate": 3.640404290832433e-07,
|
1317 |
-
"loss": 0.2322,
|
1318 |
-
"step": 1870
|
1319 |
-
},
|
1320 |
-
{
|
1321 |
-
"epoch": 2.543978349120433,
|
1322 |
-
"grad_norm": 1.3667475875891038,
|
1323 |
-
"learning_rate": 3.438486502221494e-07,
|
1324 |
-
"loss": 0.2471,
|
1325 |
-
"step": 1880
|
1326 |
-
},
|
1327 |
-
{
|
1328 |
-
"epoch": 2.557510148849797,
|
1329 |
-
"grad_norm": 1.4518282018049613,
|
1330 |
-
"learning_rate": 3.2419153938698295e-07,
|
1331 |
-
"loss": 0.2346,
|
1332 |
-
"step": 1890
|
1333 |
-
},
|
1334 |
-
{
|
1335 |
-
"epoch": 2.571041948579161,
|
1336 |
-
"grad_norm": 1.334115365965958,
|
1337 |
-
"learning_rate": 3.0507397101693565e-07,
|
1338 |
-
"loss": 0.2383,
|
1339 |
-
"step": 1900
|
1340 |
-
},
|
1341 |
-
{
|
1342 |
-
"epoch": 2.584573748308525,
|
1343 |
-
"grad_norm": 1.368769415739159,
|
1344 |
-
"learning_rate": 2.865006857590619e-07,
|
1345 |
-
"loss": 0.2344,
|
1346 |
-
"step": 1910
|
1347 |
-
},
|
1348 |
-
{
|
1349 |
-
"epoch": 2.598105548037889,
|
1350 |
-
"grad_norm": 1.2174336094447944,
|
1351 |
-
"learning_rate": 2.684762892927184e-07,
|
1352 |
-
"loss": 0.2354,
|
1353 |
-
"step": 1920
|
1354 |
-
},
|
1355 |
-
{
|
1356 |
-
"epoch": 2.611637347767253,
|
1357 |
-
"grad_norm": 1.3104470556604222,
|
1358 |
-
"learning_rate": 2.510052511874822e-07,
|
1359 |
-
"loss": 0.2297,
|
1360 |
-
"step": 1930
|
1361 |
-
},
|
1362 |
-
{
|
1363 |
-
"epoch": 2.6251691474966172,
|
1364 |
-
"grad_norm": 1.3766509507609574,
|
1365 |
-
"learning_rate": 2.3409190379481723e-07,
|
1366 |
-
"loss": 0.2294,
|
1367 |
-
"step": 1940
|
1368 |
-
},
|
1369 |
-
{
|
1370 |
-
"epoch": 2.6387009472259813,
|
1371 |
-
"grad_norm": 1.2110460902512004,
|
1372 |
-
"learning_rate": 2.1774044117376407e-07,
|
1373 |
-
"loss": 0.2273,
|
1374 |
-
"step": 1950
|
1375 |
-
},
|
1376 |
-
{
|
1377 |
-
"epoch": 2.6522327469553453,
|
1378 |
-
"grad_norm": 1.294674188348231,
|
1379 |
-
"learning_rate": 2.019549180509267e-07,
|
1380 |
-
"loss": 0.2304,
|
1381 |
-
"step": 1960
|
1382 |
-
},
|
1383 |
-
{
|
1384 |
-
"epoch": 2.6657645466847093,
|
1385 |
-
"grad_norm": 1.4025491240100805,
|
1386 |
-
"learning_rate": 1.8673924881500826e-07,
|
1387 |
-
"loss": 0.2361,
|
1388 |
-
"step": 1970
|
1389 |
-
},
|
1390 |
-
{
|
1391 |
-
"epoch": 2.6792963464140733,
|
1392 |
-
"grad_norm": 1.3312582202000482,
|
1393 |
-
"learning_rate": 1.7209720654614793e-07,
|
1394 |
-
"loss": 0.2417,
|
1395 |
-
"step": 1980
|
1396 |
-
},
|
1397 |
-
{
|
1398 |
-
"epoch": 2.6928281461434374,
|
1399 |
-
"grad_norm": 1.279370227399727,
|
1400 |
-
"learning_rate": 1.580324220802959e-07,
|
1401 |
-
"loss": 0.2306,
|
1402 |
-
"step": 1990
|
1403 |
-
},
|
1404 |
-
{
|
1405 |
-
"epoch": 2.706359945872801,
|
1406 |
-
"grad_norm": 1.32387777543638,
|
1407 |
-
"learning_rate": 1.4454838310886427e-07,
|
1408 |
-
"loss": 0.2293,
|
1409 |
-
"step": 2000
|
1410 |
-
},
|
1411 |
-
{
|
1412 |
-
"epoch": 2.719891745602165,
|
1413 |
-
"grad_norm": 1.4245015480114729,
|
1414 |
-
"learning_rate": 1.3164843331387123e-07,
|
1415 |
-
"loss": 0.2311,
|
1416 |
-
"step": 2010
|
1417 |
-
},
|
1418 |
-
{
|
1419 |
-
"epoch": 2.733423545331529,
|
1420 |
-
"grad_norm": 1.3831803662571336,
|
1421 |
-
"learning_rate": 1.1933577153879993e-07,
|
1422 |
-
"loss": 0.2387,
|
1423 |
-
"step": 2020
|
1424 |
-
},
|
1425 |
-
{
|
1426 |
-
"epoch": 2.746955345060893,
|
1427 |
-
"grad_norm": 1.341165321378542,
|
1428 |
-
"learning_rate": 1.0761345099536691e-07,
|
1429 |
-
"loss": 0.2406,
|
1430 |
-
"step": 2030
|
1431 |
-
},
|
1432 |
-
{
|
1433 |
-
"epoch": 2.760487144790257,
|
1434 |
-
"grad_norm": 1.4225949777687765,
|
1435 |
-
"learning_rate": 9.648437850640929e-08,
|
1436 |
-
"loss": 0.2334,
|
1437 |
-
"step": 2040
|
1438 |
-
},
|
1439 |
-
{
|
1440 |
-
"epoch": 2.774018944519621,
|
1441 |
-
"grad_norm": 1.2903746437594332,
|
1442 |
-
"learning_rate": 8.595131378507038e-08,
|
1443 |
-
"loss": 0.2302,
|
1444 |
-
"step": 2050
|
1445 |
-
},
|
1446 |
-
{
|
1447 |
-
"epoch": 2.787550744248985,
|
1448 |
-
"grad_norm": 1.4459041867407572,
|
1449 |
-
"learning_rate": 7.601686875046338e-08,
|
1450 |
-
"loss": 0.2357,
|
1451 |
-
"step": 2060
|
1452 |
-
},
|
1453 |
-
{
|
1454 |
-
"epoch": 2.801082543978349,
|
1455 |
-
"grad_norm": 1.43510005352293,
|
1456 |
-
"learning_rate": 6.668350687998565e-08,
|
1457 |
-
"loss": 0.2354,
|
1458 |
-
"step": 2070
|
1459 |
-
},
|
1460 |
-
{
|
1461 |
-
"epoch": 2.814614343707713,
|
1462 |
-
"grad_norm": 1.3495037373612448,
|
1463 |
-
"learning_rate": 5.7953542598441215e-08,
|
1464 |
-
"loss": 0.2299,
|
1465 |
-
"step": 2080
|
1466 |
-
},
|
1467 |
-
{
|
1468 |
-
"epoch": 2.828146143437077,
|
1469 |
-
"grad_norm": 1.2822048194805191,
|
1470 |
-
"learning_rate": 4.9829140704127644e-08,
|
1471 |
-
"loss": 0.2304,
|
1472 |
-
"step": 2090
|
1473 |
-
},
|
1474 |
-
{
|
1475 |
-
"epoch": 2.841677943166441,
|
1476 |
-
"grad_norm": 1.4152294147048579,
|
1477 |
-
"learning_rate": 4.231231583201989e-08,
|
1478 |
-
"loss": 0.2373,
|
1479 |
-
"step": 2100
|
1480 |
-
},
|
1481 |
-
{
|
1482 |
-
"epoch": 2.855209742895805,
|
1483 |
-
"grad_norm": 1.4204373591003197,
|
1484 |
-
"learning_rate": 3.5404931954197696e-08,
|
1485 |
-
"loss": 0.2359,
|
1486 |
-
"step": 2110
|
1487 |
-
},
|
1488 |
-
{
|
1489 |
-
"epoch": 2.8687415426251692,
|
1490 |
-
"grad_norm": 1.3793380734018237,
|
1491 |
-
"learning_rate": 2.9108701917630043e-08,
|
1492 |
-
"loss": 0.2447,
|
1493 |
-
"step": 2120
|
1494 |
-
},
|
1495 |
-
{
|
1496 |
-
"epoch": 2.8822733423545333,
|
1497 |
-
"grad_norm": 1.2804260757138324,
|
1498 |
-
"learning_rate": 2.3425187019432415e-08,
|
1499 |
-
"loss": 0.2446,
|
1500 |
-
"step": 2130
|
1501 |
-
},
|
1502 |
-
{
|
1503 |
-
"epoch": 2.8958051420838973,
|
1504 |
-
"grad_norm": 1.3777377768354557,
|
1505 |
-
"learning_rate": 1.8355796619708988e-08,
|
1506 |
-
"loss": 0.2367,
|
1507 |
-
"step": 2140
|
1508 |
-
},
|
1509 |
-
{
|
1510 |
-
"epoch": 2.9093369418132613,
|
1511 |
-
"grad_norm": 1.3764369341392175,
|
1512 |
-
"learning_rate": 1.39017877920683e-08,
|
1513 |
-
"loss": 0.2357,
|
1514 |
-
"step": 2150
|
1515 |
-
},
|
1516 |
-
{
|
1517 |
-
"epoch": 2.9228687415426253,
|
1518 |
-
"grad_norm": 1.4731353222848615,
|
1519 |
-
"learning_rate": 1.006426501190233e-08,
|
1520 |
-
"loss": 0.2355,
|
1521 |
-
"step": 2160
|
1522 |
-
},
|
1523 |
-
{
|
1524 |
-
"epoch": 2.936400541271989,
|
1525 |
-
"grad_norm": 1.3695944357270635,
|
1526 |
-
"learning_rate": 6.844179882506685e-09,
|
1527 |
-
"loss": 0.2312,
|
1528 |
-
"step": 2170
|
1529 |
-
},
|
1530 |
-
{
|
1531 |
-
"epoch": 2.949932341001353,
|
1532 |
-
"grad_norm": 1.3973969195223515,
|
1533 |
-
"learning_rate": 4.242330899106861e-09,
|
1534 |
-
"loss": 0.2403,
|
1535 |
-
"step": 2180
|
1536 |
-
},
|
1537 |
-
{
|
1538 |
-
"epoch": 2.963464140730717,
|
1539 |
-
"grad_norm": 1.330953340046642,
|
1540 |
-
"learning_rate": 2.259363250854685e-09,
|
1541 |
-
"loss": 0.2264,
|
1542 |
-
"step": 2190
|
1543 |
-
},
|
1544 |
-
{
|
1545 |
-
"epoch": 2.976995940460081,
|
1546 |
-
"grad_norm": 1.305324417569301,
|
1547 |
-
"learning_rate": 8.957686608371263e-10,
|
1548 |
-
"loss": 0.2328,
|
1549 |
-
"step": 2200
|
1550 |
-
},
|
1551 |
-
{
|
1552 |
-
"epoch": 2.990527740189445,
|
1553 |
-
"grad_norm": 1.349805214463894,
|
1554 |
-
"learning_rate": 1.5188526414244842e-10,
|
1555 |
-
"loss": 0.2348,
|
1556 |
-
"step": 2210
|
1557 |
-
},
|
1558 |
-
{
|
1559 |
-
"epoch": 3.0,
|
1560 |
-
"step": 2217,
|
1561 |
-
"total_flos": 438250533027840.0,
|
1562 |
-
"train_loss": 0.3635299830593717,
|
1563 |
-
"train_runtime": 20239.4479,
|
1564 |
-
"train_samples_per_second": 14.013,
|
1565 |
-
"train_steps_per_second": 0.11
|
1566 |
-
}
|
1567 |
-
],
|
1568 |
-
"logging_steps": 10,
|
1569 |
-
"max_steps": 2217,
|
1570 |
-
"num_input_tokens_seen": 0,
|
1571 |
-
"num_train_epochs": 3,
|
1572 |
-
"save_steps": 10086,
|
1573 |
-
"stateful_callbacks": {
|
1574 |
-
"TrainerControl": {
|
1575 |
-
"args": {
|
1576 |
-
"should_epoch_stop": false,
|
1577 |
-
"should_evaluate": false,
|
1578 |
-
"should_log": false,
|
1579 |
-
"should_save": false,
|
1580 |
-
"should_training_stop": false
|
1581 |
-
},
|
1582 |
-
"attributes": {}
|
1583 |
-
}
|
1584 |
-
},
|
1585 |
-
"total_flos": 438250533027840.0,
|
1586 |
-
"train_batch_size": 8,
|
1587 |
-
"trial_name": null,
|
1588 |
-
"trial_params": null
|
1589 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|