Delete trainer_state.json with huggingface_hub
Browse files- trainer_state.json +0 -879
trainer_state.json
DELETED
@@ -1,879 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.9166666666666666,
|
5 |
-
"eval_steps": 30,
|
6 |
-
"global_step": 990,
|
7 |
-
"is_hyper_param_search": false,
|
8 |
-
"is_local_process_zero": true,
|
9 |
-
"is_world_process_zero": true,
|
10 |
-
"log_history": [
|
11 |
-
{
|
12 |
-
"epoch": 0.01,
|
13 |
-
"learning_rate": 3.0000000000000004e-07,
|
14 |
-
"loss": 1.4898,
|
15 |
-
"step": 10
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"epoch": 0.02,
|
19 |
-
"learning_rate": 6.000000000000001e-07,
|
20 |
-
"loss": 1.603,
|
21 |
-
"step": 20
|
22 |
-
},
|
23 |
-
{
|
24 |
-
"epoch": 0.03,
|
25 |
-
"learning_rate": 9e-07,
|
26 |
-
"loss": 1.7131,
|
27 |
-
"step": 30
|
28 |
-
},
|
29 |
-
{
|
30 |
-
"epoch": 0.03,
|
31 |
-
"eval_loss": 1.6769884824752808,
|
32 |
-
"eval_runtime": 42.9173,
|
33 |
-
"eval_samples_per_second": 4.66,
|
34 |
-
"eval_steps_per_second": 0.583,
|
35 |
-
"step": 30
|
36 |
-
},
|
37 |
-
{
|
38 |
-
"epoch": 0.04,
|
39 |
-
"learning_rate": 1.2000000000000002e-06,
|
40 |
-
"loss": 1.7649,
|
41 |
-
"step": 40
|
42 |
-
},
|
43 |
-
{
|
44 |
-
"epoch": 0.05,
|
45 |
-
"learning_rate": 1.5e-06,
|
46 |
-
"loss": 1.9524,
|
47 |
-
"step": 50
|
48 |
-
},
|
49 |
-
{
|
50 |
-
"epoch": 0.06,
|
51 |
-
"learning_rate": 1.8e-06,
|
52 |
-
"loss": 1.5466,
|
53 |
-
"step": 60
|
54 |
-
},
|
55 |
-
{
|
56 |
-
"epoch": 0.06,
|
57 |
-
"eval_loss": 1.6383670568466187,
|
58 |
-
"eval_runtime": 43.1224,
|
59 |
-
"eval_samples_per_second": 4.638,
|
60 |
-
"eval_steps_per_second": 0.58,
|
61 |
-
"step": 60
|
62 |
-
},
|
63 |
-
{
|
64 |
-
"epoch": 0.06,
|
65 |
-
"learning_rate": 2.1e-06,
|
66 |
-
"loss": 1.5196,
|
67 |
-
"step": 70
|
68 |
-
},
|
69 |
-
{
|
70 |
-
"epoch": 0.07,
|
71 |
-
"learning_rate": 2.4000000000000003e-06,
|
72 |
-
"loss": 1.5654,
|
73 |
-
"step": 80
|
74 |
-
},
|
75 |
-
{
|
76 |
-
"epoch": 0.08,
|
77 |
-
"learning_rate": 2.7e-06,
|
78 |
-
"loss": 1.6131,
|
79 |
-
"step": 90
|
80 |
-
},
|
81 |
-
{
|
82 |
-
"epoch": 0.08,
|
83 |
-
"eval_loss": 1.572911262512207,
|
84 |
-
"eval_runtime": 43.1916,
|
85 |
-
"eval_samples_per_second": 4.631,
|
86 |
-
"eval_steps_per_second": 0.579,
|
87 |
-
"step": 90
|
88 |
-
},
|
89 |
-
{
|
90 |
-
"epoch": 0.09,
|
91 |
-
"learning_rate": 3e-06,
|
92 |
-
"loss": 1.6717,
|
93 |
-
"step": 100
|
94 |
-
},
|
95 |
-
{
|
96 |
-
"epoch": 0.1,
|
97 |
-
"learning_rate": 2.9990862405286437e-06,
|
98 |
-
"loss": 1.403,
|
99 |
-
"step": 110
|
100 |
-
},
|
101 |
-
{
|
102 |
-
"epoch": 0.11,
|
103 |
-
"learning_rate": 2.9963460753897363e-06,
|
104 |
-
"loss": 1.3671,
|
105 |
-
"step": 120
|
106 |
-
},
|
107 |
-
{
|
108 |
-
"epoch": 0.11,
|
109 |
-
"eval_loss": 1.4739114046096802,
|
110 |
-
"eval_runtime": 43.2692,
|
111 |
-
"eval_samples_per_second": 4.622,
|
112 |
-
"eval_steps_per_second": 0.578,
|
113 |
-
"step": 120
|
114 |
-
},
|
115 |
-
{
|
116 |
-
"epoch": 0.12,
|
117 |
-
"learning_rate": 2.99178284305241e-06,
|
118 |
-
"loss": 1.4241,
|
119 |
-
"step": 130
|
120 |
-
},
|
121 |
-
{
|
122 |
-
"epoch": 0.13,
|
123 |
-
"learning_rate": 2.9854021031123555e-06,
|
124 |
-
"loss": 1.4904,
|
125 |
-
"step": 140
|
126 |
-
},
|
127 |
-
{
|
128 |
-
"epoch": 0.14,
|
129 |
-
"learning_rate": 2.9772116295183124e-06,
|
130 |
-
"loss": 1.5349,
|
131 |
-
"step": 150
|
132 |
-
},
|
133 |
-
{
|
134 |
-
"epoch": 0.14,
|
135 |
-
"eval_loss": 1.3558812141418457,
|
136 |
-
"eval_runtime": 43.2358,
|
137 |
-
"eval_samples_per_second": 4.626,
|
138 |
-
"eval_steps_per_second": 0.578,
|
139 |
-
"step": 150
|
140 |
-
},
|
141 |
-
{
|
142 |
-
"epoch": 0.15,
|
143 |
-
"learning_rate": 2.9672214011007086e-06,
|
144 |
-
"loss": 1.1703,
|
145 |
-
"step": 160
|
146 |
-
},
|
147 |
-
{
|
148 |
-
"epoch": 0.16,
|
149 |
-
"learning_rate": 2.9554435894139947e-06,
|
150 |
-
"loss": 1.2204,
|
151 |
-
"step": 170
|
152 |
-
},
|
153 |
-
{
|
154 |
-
"epoch": 0.17,
|
155 |
-
"learning_rate": 2.9418925439074784e-06,
|
156 |
-
"loss": 1.2134,
|
157 |
-
"step": 180
|
158 |
-
},
|
159 |
-
{
|
160 |
-
"epoch": 0.17,
|
161 |
-
"eval_loss": 1.2288929224014282,
|
162 |
-
"eval_runtime": 43.282,
|
163 |
-
"eval_samples_per_second": 4.621,
|
164 |
-
"eval_steps_per_second": 0.578,
|
165 |
-
"step": 180
|
166 |
-
},
|
167 |
-
{
|
168 |
-
"epoch": 0.18,
|
169 |
-
"learning_rate": 2.9265847744427307e-06,
|
170 |
-
"loss": 1.2081,
|
171 |
-
"step": 190
|
172 |
-
},
|
173 |
-
{
|
174 |
-
"epoch": 0.19,
|
175 |
-
"learning_rate": 2.9095389311788626e-06,
|
176 |
-
"loss": 1.2196,
|
177 |
-
"step": 200
|
178 |
-
},
|
179 |
-
{
|
180 |
-
"epoch": 0.19,
|
181 |
-
"learning_rate": 2.8907757818501814e-06,
|
182 |
-
"loss": 1.083,
|
183 |
-
"step": 210
|
184 |
-
},
|
185 |
-
{
|
186 |
-
"epoch": 0.19,
|
187 |
-
"eval_loss": 1.079976201057434,
|
188 |
-
"eval_runtime": 43.2803,
|
189 |
-
"eval_samples_per_second": 4.621,
|
190 |
-
"eval_steps_per_second": 0.578,
|
191 |
-
"step": 210
|
192 |
-
},
|
193 |
-
{
|
194 |
-
"epoch": 0.2,
|
195 |
-
"learning_rate": 2.8703181864639013e-06,
|
196 |
-
"loss": 1.0504,
|
197 |
-
"step": 220
|
198 |
-
},
|
199 |
-
{
|
200 |
-
"epoch": 0.21,
|
201 |
-
"learning_rate": 2.8481910694487506e-06,
|
202 |
-
"loss": 0.993,
|
203 |
-
"step": 230
|
204 |
-
},
|
205 |
-
{
|
206 |
-
"epoch": 0.22,
|
207 |
-
"learning_rate": 2.8244213892883906e-06,
|
208 |
-
"loss": 0.9624,
|
209 |
-
"step": 240
|
210 |
-
},
|
211 |
-
{
|
212 |
-
"epoch": 0.22,
|
213 |
-
"eval_loss": 0.938306450843811,
|
214 |
-
"eval_runtime": 43.3163,
|
215 |
-
"eval_samples_per_second": 4.617,
|
216 |
-
"eval_steps_per_second": 0.577,
|
217 |
-
"step": 240
|
218 |
-
},
|
219 |
-
{
|
220 |
-
"epoch": 0.23,
|
221 |
-
"learning_rate": 2.7990381056766585e-06,
|
222 |
-
"loss": 0.8176,
|
223 |
-
"step": 250
|
224 |
-
},
|
225 |
-
{
|
226 |
-
"epoch": 0.24,
|
227 |
-
"learning_rate": 2.772072144234639e-06,
|
228 |
-
"loss": 0.8797,
|
229 |
-
"step": 260
|
230 |
-
},
|
231 |
-
{
|
232 |
-
"epoch": 0.25,
|
233 |
-
"learning_rate": 2.7435563588325624e-06,
|
234 |
-
"loss": 0.8584,
|
235 |
-
"step": 270
|
236 |
-
},
|
237 |
-
{
|
238 |
-
"epoch": 0.25,
|
239 |
-
"eval_loss": 0.8031389713287354,
|
240 |
-
"eval_runtime": 43.324,
|
241 |
-
"eval_samples_per_second": 4.616,
|
242 |
-
"eval_steps_per_second": 0.577,
|
243 |
-
"step": 270
|
244 |
-
},
|
245 |
-
{
|
246 |
-
"epoch": 0.26,
|
247 |
-
"learning_rate": 2.713525491562421e-06,
|
248 |
-
"loss": 0.7539,
|
249 |
-
"step": 280
|
250 |
-
},
|
251 |
-
{
|
252 |
-
"epoch": 0.27,
|
253 |
-
"learning_rate": 2.6820161304100827e-06,
|
254 |
-
"loss": 0.6914,
|
255 |
-
"step": 290
|
256 |
-
},
|
257 |
-
{
|
258 |
-
"epoch": 0.28,
|
259 |
-
"learning_rate": 2.652425285390285e-06,
|
260 |
-
"loss": 0.5904,
|
261 |
-
"step": 300
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"epoch": 0.28,
|
265 |
-
"eval_loss": 0.711719810962677,
|
266 |
-
"eval_runtime": 43.2643,
|
267 |
-
"eval_samples_per_second": 4.623,
|
268 |
-
"eval_steps_per_second": 0.578,
|
269 |
-
"step": 300
|
270 |
-
},
|
271 |
-
{
|
272 |
-
"epoch": 0.29,
|
273 |
-
"learning_rate": 2.6182139995242933e-06,
|
274 |
-
"loss": 0.8539,
|
275 |
-
"step": 310
|
276 |
-
},
|
277 |
-
{
|
278 |
-
"epoch": 0.3,
|
279 |
-
"learning_rate": 2.5826403421475435e-06,
|
280 |
-
"loss": 0.8114,
|
281 |
-
"step": 320
|
282 |
-
},
|
283 |
-
{
|
284 |
-
"epoch": 0.31,
|
285 |
-
"learning_rate": 2.545747654281847e-06,
|
286 |
-
"loss": 0.6674,
|
287 |
-
"step": 330
|
288 |
-
},
|
289 |
-
{
|
290 |
-
"epoch": 0.31,
|
291 |
-
"eval_loss": 0.6477487683296204,
|
292 |
-
"eval_runtime": 43.294,
|
293 |
-
"eval_samples_per_second": 4.62,
|
294 |
-
"eval_steps_per_second": 0.577,
|
295 |
-
"step": 330
|
296 |
-
},
|
297 |
-
{
|
298 |
-
"epoch": 0.31,
|
299 |
-
"learning_rate": 2.5075808839844854e-06,
|
300 |
-
"loss": 0.6056,
|
301 |
-
"step": 340
|
302 |
-
},
|
303 |
-
{
|
304 |
-
"epoch": 0.32,
|
305 |
-
"learning_rate": 2.468186531585926e-06,
|
306 |
-
"loss": 0.5021,
|
307 |
-
"step": 350
|
308 |
-
},
|
309 |
-
{
|
310 |
-
"epoch": 0.33,
|
311 |
-
"learning_rate": 2.427612593036331e-06,
|
312 |
-
"loss": 0.7264,
|
313 |
-
"step": 360
|
314 |
-
},
|
315 |
-
{
|
316 |
-
"epoch": 0.33,
|
317 |
-
"eval_loss": 0.593954861164093,
|
318 |
-
"eval_runtime": 43.3205,
|
319 |
-
"eval_samples_per_second": 4.617,
|
320 |
-
"eval_steps_per_second": 0.577,
|
321 |
-
"step": 360
|
322 |
-
},
|
323 |
-
{
|
324 |
-
"epoch": 0.34,
|
325 |
-
"learning_rate": 2.385908501429888e-06,
|
326 |
-
"loss": 0.6218,
|
327 |
-
"step": 370
|
328 |
-
},
|
329 |
-
{
|
330 |
-
"epoch": 0.35,
|
331 |
-
"learning_rate": 2.343125066778196e-06,
|
332 |
-
"loss": 0.5625,
|
333 |
-
"step": 380
|
334 |
-
},
|
335 |
-
{
|
336 |
-
"epoch": 0.36,
|
337 |
-
"learning_rate": 2.299314414106095e-06,
|
338 |
-
"loss": 0.5172,
|
339 |
-
"step": 390
|
340 |
-
},
|
341 |
-
{
|
342 |
-
"epoch": 0.36,
|
343 |
-
"eval_loss": 0.5455488562583923,
|
344 |
-
"eval_runtime": 43.2928,
|
345 |
-
"eval_samples_per_second": 4.62,
|
346 |
-
"eval_steps_per_second": 0.577,
|
347 |
-
"step": 390
|
348 |
-
},
|
349 |
-
{
|
350 |
-
"epoch": 0.37,
|
351 |
-
"learning_rate": 2.2545299199453527e-06,
|
352 |
-
"loss": 0.4426,
|
353 |
-
"step": 400
|
354 |
-
},
|
355 |
-
{
|
356 |
-
"epoch": 0.38,
|
357 |
-
"learning_rate": 2.2088261473035813e-06,
|
358 |
-
"loss": 0.6936,
|
359 |
-
"step": 410
|
360 |
-
},
|
361 |
-
{
|
362 |
-
"epoch": 0.39,
|
363 |
-
"learning_rate": 2.162258779187618e-06,
|
364 |
-
"loss": 0.572,
|
365 |
-
"step": 420
|
366 |
-
},
|
367 |
-
{
|
368 |
-
"epoch": 0.39,
|
369 |
-
"eval_loss": 0.5148348212242126,
|
370 |
-
"eval_runtime": 43.32,
|
371 |
-
"eval_samples_per_second": 4.617,
|
372 |
-
"eval_steps_per_second": 0.577,
|
373 |
-
"step": 420
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"epoch": 0.4,
|
377 |
-
"learning_rate": 2.1148845507623592e-06,
|
378 |
-
"loss": 0.5241,
|
379 |
-
"step": 430
|
380 |
-
},
|
381 |
-
{
|
382 |
-
"epoch": 0.41,
|
383 |
-
"learning_rate": 2.0667611802277007e-06,
|
384 |
-
"loss": 0.4678,
|
385 |
-
"step": 440
|
386 |
-
},
|
387 |
-
{
|
388 |
-
"epoch": 0.42,
|
389 |
-
"learning_rate": 2.017947298497802e-06,
|
390 |
-
"loss": 0.4499,
|
391 |
-
"step": 450
|
392 |
-
},
|
393 |
-
{
|
394 |
-
"epoch": 0.42,
|
395 |
-
"eval_loss": 0.4825447201728821,
|
396 |
-
"eval_runtime": 43.2939,
|
397 |
-
"eval_samples_per_second": 4.62,
|
398 |
-
"eval_steps_per_second": 0.577,
|
399 |
-
"step": 450
|
400 |
-
},
|
401 |
-
{
|
402 |
-
"epoch": 0.43,
|
403 |
-
"learning_rate": 1.968502377768349e-06,
|
404 |
-
"loss": 0.5878,
|
405 |
-
"step": 460
|
406 |
-
},
|
407 |
-
{
|
408 |
-
"epoch": 0.44,
|
409 |
-
"learning_rate": 1.918486659058844e-06,
|
410 |
-
"loss": 0.4392,
|
411 |
-
"step": 470
|
412 |
-
},
|
413 |
-
{
|
414 |
-
"epoch": 0.44,
|
415 |
-
"learning_rate": 1.867961078818204e-06,
|
416 |
-
"loss": 0.4849,
|
417 |
-
"step": 480
|
418 |
-
},
|
419 |
-
{
|
420 |
-
"epoch": 0.44,
|
421 |
-
"eval_loss": 0.45478785037994385,
|
422 |
-
"eval_runtime": 43.3084,
|
423 |
-
"eval_samples_per_second": 4.618,
|
424 |
-
"eval_steps_per_second": 0.577,
|
425 |
-
"step": 480
|
426 |
-
},
|
427 |
-
{
|
428 |
-
"epoch": 0.45,
|
429 |
-
"learning_rate": 1.8169871946830832e-06,
|
430 |
-
"loss": 0.4713,
|
431 |
-
"step": 490
|
432 |
-
},
|
433 |
-
{
|
434 |
-
"epoch": 0.46,
|
435 |
-
"learning_rate": 1.7656271104793753e-06,
|
436 |
-
"loss": 0.3371,
|
437 |
-
"step": 500
|
438 |
-
},
|
439 |
-
{
|
440 |
-
"epoch": 0.47,
|
441 |
-
"learning_rate": 1.7139434005582677e-06,
|
442 |
-
"loss": 0.6713,
|
443 |
-
"step": 510
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 0.47,
|
447 |
-
"eval_loss": 0.43661826848983765,
|
448 |
-
"eval_runtime": 43.3338,
|
449 |
-
"eval_samples_per_second": 4.615,
|
450 |
-
"eval_steps_per_second": 0.577,
|
451 |
-
"step": 510
|
452 |
-
},
|
453 |
-
{
|
454 |
-
"epoch": 0.48,
|
455 |
-
"learning_rate": 1.6619990335590342e-06,
|
456 |
-
"loss": 0.4761,
|
457 |
-
"step": 520
|
458 |
-
},
|
459 |
-
{
|
460 |
-
"epoch": 0.49,
|
461 |
-
"learning_rate": 1.6098572956914476e-06,
|
462 |
-
"loss": 0.3853,
|
463 |
-
"step": 530
|
464 |
-
},
|
465 |
-
{
|
466 |
-
"epoch": 0.5,
|
467 |
-
"learning_rate": 1.55758171363128e-06,
|
468 |
-
"loss": 0.3786,
|
469 |
-
"step": 540
|
470 |
-
},
|
471 |
-
{
|
472 |
-
"epoch": 0.5,
|
473 |
-
"eval_loss": 0.4211544692516327,
|
474 |
-
"eval_runtime": 43.3208,
|
475 |
-
"eval_samples_per_second": 4.617,
|
476 |
-
"eval_steps_per_second": 0.577,
|
477 |
-
"step": 540
|
478 |
-
},
|
479 |
-
{
|
480 |
-
"epoch": 0.51,
|
481 |
-
"learning_rate": 1.5052359771228356e-06,
|
482 |
-
"loss": 0.3292,
|
483 |
-
"step": 550
|
484 |
-
},
|
485 |
-
{
|
486 |
-
"epoch": 0.52,
|
487 |
-
"learning_rate": 1.4528838613828075e-06,
|
488 |
-
"loss": 0.5014,
|
489 |
-
"step": 560
|
490 |
-
},
|
491 |
-
{
|
492 |
-
"epoch": 0.53,
|
493 |
-
"learning_rate": 1.4005891494000002e-06,
|
494 |
-
"loss": 0.4742,
|
495 |
-
"step": 570
|
496 |
-
},
|
497 |
-
{
|
498 |
-
"epoch": 0.53,
|
499 |
-
"eval_loss": 0.4091000258922577,
|
500 |
-
"eval_runtime": 43.3335,
|
501 |
-
"eval_samples_per_second": 4.615,
|
502 |
-
"eval_steps_per_second": 0.577,
|
503 |
-
"step": 570
|
504 |
-
},
|
505 |
-
{
|
506 |
-
"epoch": 0.54,
|
507 |
-
"learning_rate": 1.3484155542255805e-06,
|
508 |
-
"loss": 0.4352,
|
509 |
-
"step": 580
|
510 |
-
},
|
511 |
-
{
|
512 |
-
"epoch": 0.55,
|
513 |
-
"learning_rate": 1.2964266413485436e-06,
|
514 |
-
"loss": 0.375,
|
515 |
-
"step": 590
|
516 |
-
},
|
517 |
-
{
|
518 |
-
"epoch": 0.56,
|
519 |
-
"learning_rate": 1.2446857512509515e-06,
|
520 |
-
"loss": 0.2914,
|
521 |
-
"step": 600
|
522 |
-
},
|
523 |
-
{
|
524 |
-
"epoch": 0.56,
|
525 |
-
"eval_loss": 0.40144798159599304,
|
526 |
-
"eval_runtime": 43.3188,
|
527 |
-
"eval_samples_per_second": 4.617,
|
528 |
-
"eval_steps_per_second": 0.577,
|
529 |
-
"step": 600
|
530 |
-
},
|
531 |
-
{
|
532 |
-
"epoch": 0.56,
|
533 |
-
"learning_rate": 1.1932559222373146e-06,
|
534 |
-
"loss": 0.437,
|
535 |
-
"step": 610
|
536 |
-
},
|
537 |
-
{
|
538 |
-
"epoch": 0.57,
|
539 |
-
"learning_rate": 1.142199813632129e-06,
|
540 |
-
"loss": 0.435,
|
541 |
-
"step": 620
|
542 |
-
},
|
543 |
-
{
|
544 |
-
"epoch": 0.58,
|
545 |
-
"learning_rate": 1.0915796294391385e-06,
|
546 |
-
"loss": 0.4561,
|
547 |
-
"step": 630
|
548 |
-
},
|
549 |
-
{
|
550 |
-
"epoch": 0.58,
|
551 |
-
"eval_loss": 0.39555278420448303,
|
552 |
-
"eval_runtime": 43.303,
|
553 |
-
"eval_samples_per_second": 4.619,
|
554 |
-
"eval_steps_per_second": 0.577,
|
555 |
-
"step": 630
|
556 |
-
},
|
557 |
-
{
|
558 |
-
"epoch": 0.59,
|
559 |
-
"learning_rate": 1.0414570425553416e-06,
|
560 |
-
"loss": 0.4328,
|
561 |
-
"step": 640
|
562 |
-
},
|
563 |
-
{
|
564 |
-
"epoch": 0.6,
|
565 |
-
"learning_rate": 9.918931196320629e-07,
|
566 |
-
"loss": 0.3112,
|
567 |
-
"step": 650
|
568 |
-
},
|
569 |
-
{
|
570 |
-
"epoch": 0.61,
|
571 |
-
"learning_rate": 9.429482466746482e-07,
|
572 |
-
"loss": 0.464,
|
573 |
-
"step": 660
|
574 |
-
},
|
575 |
-
{
|
576 |
-
"epoch": 0.61,
|
577 |
-
"eval_loss": 0.3911471962928772,
|
578 |
-
"eval_runtime": 43.2973,
|
579 |
-
"eval_samples_per_second": 4.619,
|
580 |
-
"eval_steps_per_second": 0.577,
|
581 |
-
"step": 660
|
582 |
-
},
|
583 |
-
{
|
584 |
-
"epoch": 0.62,
|
585 |
-
"learning_rate": 8.946820554714148e-07,
|
586 |
-
"loss": 0.3314,
|
587 |
-
"step": 670
|
588 |
-
},
|
589 |
-
{
|
590 |
-
"epoch": 0.63,
|
591 |
-
"learning_rate": 8.471533509415089e-07,
|
592 |
-
"loss": 0.3463,
|
593 |
-
"step": 680
|
594 |
-
},
|
595 |
-
{
|
596 |
-
"epoch": 0.64,
|
597 |
-
"learning_rate": 8.004200394901634e-07,
|
598 |
-
"loss": 0.3222,
|
599 |
-
"step": 690
|
600 |
-
},
|
601 |
-
{
|
602 |
-
"epoch": 0.64,
|
603 |
-
"eval_loss": 0.3882828652858734,
|
604 |
-
"eval_runtime": 43.2999,
|
605 |
-
"eval_samples_per_second": 4.619,
|
606 |
-
"eval_steps_per_second": 0.577,
|
607 |
-
"step": 690
|
608 |
-
},
|
609 |
-
{
|
610 |
-
"epoch": 0.65,
|
611 |
-
"learning_rate": 7.54539058458667e-07,
|
612 |
-
"loss": 0.2882,
|
613 |
-
"step": 700
|
614 |
-
},
|
615 |
-
{
|
616 |
-
"epoch": 0.66,
|
617 |
-
"learning_rate": 7.095663067549837e-07,
|
618 |
-
"loss": 0.4216,
|
619 |
-
"step": 710
|
620 |
-
},
|
621 |
-
{
|
622 |
-
"epoch": 0.67,
|
623 |
-
"learning_rate": 6.655565767495428e-07,
|
624 |
-
"loss": 0.4166,
|
625 |
-
"step": 720
|
626 |
-
},
|
627 |
-
{
|
628 |
-
"epoch": 0.67,
|
629 |
-
"eval_loss": 0.38488155603408813,
|
630 |
-
"eval_runtime": 43.3338,
|
631 |
-
"eval_samples_per_second": 4.615,
|
632 |
-
"eval_steps_per_second": 0.577,
|
633 |
-
"step": 720
|
634 |
-
},
|
635 |
-
{
|
636 |
-
"epoch": 0.68,
|
637 |
-
"learning_rate": 6.225634875191768e-07,
|
638 |
-
"loss": 0.4709,
|
639 |
-
"step": 730
|
640 |
-
},
|
641 |
-
{
|
642 |
-
"epoch": 0.69,
|
643 |
-
"learning_rate": 5.806394195205356e-07,
|
644 |
-
"loss": 0.4041,
|
645 |
-
"step": 740
|
646 |
-
},
|
647 |
-
{
|
648 |
-
"epoch": 0.69,
|
649 |
-
"learning_rate": 5.398354507725665e-07,
|
650 |
-
"loss": 0.2599,
|
651 |
-
"step": 750
|
652 |
-
},
|
653 |
-
{
|
654 |
-
"epoch": 0.69,
|
655 |
-
"eval_loss": 0.3818848431110382,
|
656 |
-
"eval_runtime": 43.2854,
|
657 |
-
"eval_samples_per_second": 4.62,
|
658 |
-
"eval_steps_per_second": 0.578,
|
659 |
-
"step": 750
|
660 |
-
},
|
661 |
-
{
|
662 |
-
"epoch": 0.7,
|
663 |
-
"learning_rate": 5.002012946258214e-07,
|
664 |
-
"loss": 0.4712,
|
665 |
-
"step": 760
|
666 |
-
},
|
667 |
-
{
|
668 |
-
"epoch": 0.71,
|
669 |
-
"learning_rate": 4.6178523919439e-07,
|
670 |
-
"loss": 0.4283,
|
671 |
-
"step": 770
|
672 |
-
},
|
673 |
-
{
|
674 |
-
"epoch": 0.72,
|
675 |
-
"learning_rate": 4.246340885242759e-07,
|
676 |
-
"loss": 0.3783,
|
677 |
-
"step": 780
|
678 |
-
},
|
679 |
-
{
|
680 |
-
"epoch": 0.72,
|
681 |
-
"eval_loss": 0.37969982624053955,
|
682 |
-
"eval_runtime": 43.3044,
|
683 |
-
"eval_samples_per_second": 4.618,
|
684 |
-
"eval_steps_per_second": 0.577,
|
685 |
-
"step": 780
|
686 |
-
},
|
687 |
-
{
|
688 |
-
"epoch": 0.73,
|
689 |
-
"learning_rate": 3.88793105569875e-07,
|
690 |
-
"loss": 0.4053,
|
691 |
-
"step": 790
|
692 |
-
},
|
693 |
-
{
|
694 |
-
"epoch": 0.74,
|
695 |
-
"learning_rate": 3.5430595704803714e-07,
|
696 |
-
"loss": 0.2247,
|
697 |
-
"step": 800
|
698 |
-
},
|
699 |
-
{
|
700 |
-
"epoch": 0.75,
|
701 |
-
"learning_rate": 3.2121466023689703e-07,
|
702 |
-
"loss": 0.4951,
|
703 |
-
"step": 810
|
704 |
-
},
|
705 |
-
{
|
706 |
-
"epoch": 0.75,
|
707 |
-
"eval_loss": 0.3787403106689453,
|
708 |
-
"eval_runtime": 43.3483,
|
709 |
-
"eval_samples_per_second": 4.614,
|
710 |
-
"eval_steps_per_second": 0.577,
|
711 |
-
"step": 810
|
712 |
-
},
|
713 |
-
{
|
714 |
-
"epoch": 0.76,
|
715 |
-
"learning_rate": 2.8955953178429745e-07,
|
716 |
-
"loss": 0.4129,
|
717 |
-
"step": 820
|
718 |
-
},
|
719 |
-
{
|
720 |
-
"epoch": 0.77,
|
721 |
-
"learning_rate": 2.593791385881571e-07,
|
722 |
-
"loss": 0.4215,
|
723 |
-
"step": 830
|
724 |
-
},
|
725 |
-
{
|
726 |
-
"epoch": 0.78,
|
727 |
-
"learning_rate": 2.3071025080865416e-07,
|
728 |
-
"loss": 0.3674,
|
729 |
-
"step": 840
|
730 |
-
},
|
731 |
-
{
|
732 |
-
"epoch": 0.78,
|
733 |
-
"eval_loss": 0.3782441020011902,
|
734 |
-
"eval_runtime": 43.3332,
|
735 |
-
"eval_samples_per_second": 4.615,
|
736 |
-
"eval_steps_per_second": 0.577,
|
737 |
-
"step": 840
|
738 |
-
},
|
739 |
-
{
|
740 |
-
"epoch": 0.79,
|
741 |
-
"learning_rate": 2.0358779706944303e-07,
|
742 |
-
"loss": 0.238,
|
743 |
-
"step": 850
|
744 |
-
},
|
745 |
-
{
|
746 |
-
"epoch": 0.8,
|
747 |
-
"learning_rate": 1.7804482190251177e-07,
|
748 |
-
"loss": 0.5652,
|
749 |
-
"step": 860
|
750 |
-
},
|
751 |
-
{
|
752 |
-
"epoch": 0.81,
|
753 |
-
"learning_rate": 1.5411244548850746e-07,
|
754 |
-
"loss": 0.408,
|
755 |
-
"step": 870
|
756 |
-
},
|
757 |
-
{
|
758 |
-
"epoch": 0.81,
|
759 |
-
"eval_loss": 0.3777380883693695,
|
760 |
-
"eval_runtime": 43.3364,
|
761 |
-
"eval_samples_per_second": 4.615,
|
762 |
-
"eval_steps_per_second": 0.577,
|
763 |
-
"step": 870
|
764 |
-
},
|
765 |
-
{
|
766 |
-
"epoch": 0.81,
|
767 |
-
"learning_rate": 1.3181982574159058e-07,
|
768 |
-
"loss": 0.3653,
|
769 |
-
"step": 880
|
770 |
-
},
|
771 |
-
{
|
772 |
-
"epoch": 0.82,
|
773 |
-
"learning_rate": 1.111941227850079e-07,
|
774 |
-
"loss": 0.326,
|
775 |
-
"step": 890
|
776 |
-
},
|
777 |
-
{
|
778 |
-
"epoch": 0.83,
|
779 |
-
"learning_rate": 9.226046586066611e-08,
|
780 |
-
"loss": 0.256,
|
781 |
-
"step": 900
|
782 |
-
},
|
783 |
-
{
|
784 |
-
"epoch": 0.83,
|
785 |
-
"eval_loss": 0.3771674633026123,
|
786 |
-
"eval_runtime": 43.2958,
|
787 |
-
"eval_samples_per_second": 4.619,
|
788 |
-
"eval_steps_per_second": 0.577,
|
789 |
-
"step": 900
|
790 |
-
},
|
791 |
-
{
|
792 |
-
"epoch": 0.84,
|
793 |
-
"learning_rate": 7.504192271302146e-08,
|
794 |
-
"loss": 0.5621,
|
795 |
-
"step": 910
|
796 |
-
},
|
797 |
-
{
|
798 |
-
"epoch": 0.85,
|
799 |
-
"learning_rate": 5.9559471484585404e-08,
|
800 |
-
"loss": 0.3322,
|
801 |
-
"step": 920
|
802 |
-
},
|
803 |
-
{
|
804 |
-
"epoch": 0.86,
|
805 |
-
"learning_rate": 4.583197515729171e-08,
|
806 |
-
"loss": 0.3913,
|
807 |
-
"step": 930
|
808 |
-
},
|
809 |
-
{
|
810 |
-
"epoch": 0.86,
|
811 |
-
"eval_loss": 0.3770001530647278,
|
812 |
-
"eval_runtime": 43.3108,
|
813 |
-
"eval_samples_per_second": 4.618,
|
814 |
-
"eval_steps_per_second": 0.577,
|
815 |
-
"step": 930
|
816 |
-
},
|
817 |
-
{
|
818 |
-
"epoch": 0.87,
|
819 |
-
"learning_rate": 3.387615857085618e-08,
|
820 |
-
"loss": 0.396,
|
821 |
-
"step": 940
|
822 |
-
},
|
823 |
-
{
|
824 |
-
"epoch": 0.88,
|
825 |
-
"learning_rate": 2.370658804613718e-08,
|
826 |
-
"loss": 0.2624,
|
827 |
-
"step": 950
|
828 |
-
},
|
829 |
-
{
|
830 |
-
"epoch": 0.89,
|
831 |
-
"learning_rate": 1.5335653638316516e-08,
|
832 |
-
"loss": 0.5314,
|
833 |
-
"step": 960
|
834 |
-
},
|
835 |
-
{
|
836 |
-
"epoch": 0.89,
|
837 |
-
"eval_loss": 0.3768998980522156,
|
838 |
-
"eval_runtime": 43.3212,
|
839 |
-
"eval_samples_per_second": 4.617,
|
840 |
-
"eval_steps_per_second": 0.577,
|
841 |
-
"step": 960
|
842 |
-
},
|
843 |
-
{
|
844 |
-
"epoch": 0.9,
|
845 |
-
"learning_rate": 8.77355404152691e-09,
|
846 |
-
"loss": 0.3471,
|
847 |
-
"step": 970
|
848 |
-
},
|
849 |
-
{
|
850 |
-
"epoch": 0.91,
|
851 |
-
"learning_rate": 4.028284163312857e-09,
|
852 |
-
"loss": 0.4668,
|
853 |
-
"step": 980
|
854 |
-
},
|
855 |
-
{
|
856 |
-
"epoch": 0.92,
|
857 |
-
"learning_rate": 1.1056253840682762e-09,
|
858 |
-
"loss": 0.4386,
|
859 |
-
"step": 990
|
860 |
-
},
|
861 |
-
{
|
862 |
-
"epoch": 0.92,
|
863 |
-
"eval_loss": 0.37686625123023987,
|
864 |
-
"eval_runtime": 43.494,
|
865 |
-
"eval_samples_per_second": 4.598,
|
866 |
-
"eval_steps_per_second": 0.575,
|
867 |
-
"step": 990
|
868 |
-
}
|
869 |
-
],
|
870 |
-
"logging_steps": 10,
|
871 |
-
"max_steps": 1000,
|
872 |
-
"num_input_tokens_seen": 0,
|
873 |
-
"num_train_epochs": 1,
|
874 |
-
"save_steps": 30,
|
875 |
-
"total_flos": 4.354481553518592e+16,
|
876 |
-
"train_batch_size": 1,
|
877 |
-
"trial_name": null,
|
878 |
-
"trial_params": null
|
879 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|