MHGanainy/gpt2-xl-lora-multi-6
Browse files- README.md +2 -0
- all_results.json +10 -10
- eval_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +241 -458
README.md
CHANGED
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# gpt2-xl-lora-multi-6
|
16 |
|
17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
15 |
# gpt2-xl-lora-multi-6
|
16 |
|
17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.4480
|
20 |
|
21 |
## Model description
|
22 |
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_loss": 2.
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second": 0.
|
7 |
-
"perplexity":
|
8 |
-
"total_flos":
|
9 |
-
"train_loss": 2.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 3.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 2.448012590408325,
|
4 |
+
"eval_runtime": 1408.7239,
|
5 |
+
"eval_samples_per_second": 8.454,
|
6 |
+
"eval_steps_per_second": 0.529,
|
7 |
+
"perplexity": 11.56533879845621,
|
8 |
+
"total_flos": 8.45892909419987e+17,
|
9 |
+
"train_loss": 2.683517217184325,
|
10 |
+
"train_runtime": 1637.9851,
|
11 |
+
"train_samples_per_second": 56.701,
|
12 |
+
"train_steps_per_second": 3.544
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_loss": 2.
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second": 0.
|
7 |
-
"perplexity":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 2.448012590408325,
|
4 |
+
"eval_runtime": 1408.7239,
|
5 |
+
"eval_samples_per_second": 8.454,
|
6 |
+
"eval_steps_per_second": 0.529,
|
7 |
+
"perplexity": 11.56533879845621
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 2.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 3.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"total_flos": 8.45892909419987e+17,
|
4 |
+
"train_loss": 2.683517217184325,
|
5 |
+
"train_runtime": 1637.9851,
|
6 |
+
"train_samples_per_second": 56.701,
|
7 |
+
"train_steps_per_second": 3.544
|
8 |
}
|
trainer_state.json
CHANGED
@@ -3,646 +3,429 @@
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
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": 0.
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 2.
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm": 0.
|
21 |
-
"learning_rate":
|
22 |
-
"loss": 2.
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm": 0.
|
28 |
-
"learning_rate":
|
29 |
-
"loss": 2.
|
30 |
"step": 300
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 0.
|
34 |
-
"grad_norm": 0.
|
35 |
-
"learning_rate": 1.
|
36 |
-
"loss": 2.
|
37 |
"step": 400
|
38 |
},
|
39 |
{
|
40 |
-
"epoch": 0.
|
41 |
-
"grad_norm": 0.
|
42 |
-
"learning_rate":
|
43 |
-
"loss": 2.
|
44 |
"step": 500
|
45 |
},
|
46 |
{
|
47 |
-
"epoch": 0.
|
48 |
-
"grad_norm": 0.
|
49 |
-
"learning_rate":
|
50 |
-
"loss": 2.
|
51 |
"step": 600
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 0.
|
55 |
-
"grad_norm": 0.
|
56 |
-
"learning_rate":
|
57 |
-
"loss": 2.
|
58 |
"step": 700
|
59 |
},
|
60 |
{
|
61 |
-
"epoch": 0.
|
62 |
-
"grad_norm": 0.
|
63 |
-
"learning_rate":
|
64 |
-
"loss": 2.
|
65 |
"step": 800
|
66 |
},
|
67 |
{
|
68 |
-
"epoch": 0.
|
69 |
-
"grad_norm": 0.
|
70 |
-
"learning_rate":
|
71 |
-
"loss": 2.
|
72 |
"step": 900
|
73 |
},
|
74 |
{
|
75 |
-
"epoch": 0.
|
76 |
-
"grad_norm": 0.
|
77 |
-
"learning_rate":
|
78 |
-
"loss": 2.
|
79 |
"step": 1000
|
80 |
},
|
81 |
{
|
82 |
-
"epoch": 0.
|
83 |
-
"grad_norm": 0.
|
84 |
-
"learning_rate":
|
85 |
-
"loss": 2.
|
86 |
"step": 1100
|
87 |
},
|
88 |
{
|
89 |
-
"epoch": 0.
|
90 |
-
"grad_norm": 0.
|
91 |
-
"learning_rate":
|
92 |
-
"loss": 2.
|
93 |
"step": 1200
|
94 |
},
|
95 |
{
|
96 |
-
"epoch": 0.
|
97 |
-
"grad_norm": 0.
|
98 |
-
"learning_rate":
|
99 |
-
"loss": 2.
|
100 |
"step": 1300
|
101 |
},
|
102 |
{
|
103 |
-
"epoch": 0.
|
104 |
-
"grad_norm": 0.
|
105 |
-
"learning_rate":
|
106 |
-
"loss": 2.
|
107 |
"step": 1400
|
108 |
},
|
109 |
{
|
110 |
-
"epoch": 0.
|
111 |
-
"grad_norm": 0.
|
112 |
-
"learning_rate":
|
113 |
-
"loss": 2.
|
114 |
"step": 1500
|
115 |
},
|
116 |
{
|
117 |
-
"epoch": 0.
|
118 |
-
"grad_norm": 0.
|
119 |
-
"learning_rate":
|
120 |
-
"loss": 2.
|
121 |
"step": 1600
|
122 |
},
|
123 |
{
|
124 |
-
"epoch": 0.
|
125 |
-
"grad_norm": 0.
|
126 |
-
"learning_rate":
|
127 |
-
"loss": 2.
|
128 |
"step": 1700
|
129 |
},
|
130 |
{
|
131 |
-
"epoch": 0.
|
132 |
-
"grad_norm": 0.
|
133 |
-
"learning_rate":
|
134 |
-
"loss": 2.
|
135 |
"step": 1800
|
136 |
},
|
137 |
{
|
138 |
-
"epoch": 0.
|
139 |
-
"grad_norm": 0.
|
140 |
-
"learning_rate":
|
141 |
-
"loss": 2.
|
142 |
"step": 1900
|
143 |
},
|
144 |
{
|
145 |
-
"epoch": 0.
|
146 |
-
"grad_norm": 0.
|
147 |
-
"learning_rate":
|
148 |
-
"loss": 2.
|
149 |
"step": 2000
|
150 |
},
|
151 |
{
|
152 |
-
"epoch": 0.
|
153 |
-
"grad_norm": 0.
|
154 |
-
"learning_rate":
|
155 |
-
"loss": 2.
|
156 |
"step": 2100
|
157 |
},
|
158 |
{
|
159 |
-
"epoch": 0.
|
160 |
-
"grad_norm": 0.
|
161 |
-
"learning_rate":
|
162 |
-
"loss": 2.
|
163 |
"step": 2200
|
164 |
},
|
165 |
{
|
166 |
-
"epoch": 0.
|
167 |
-
"grad_norm": 0.
|
168 |
-
"learning_rate":
|
169 |
-
"loss": 2.
|
170 |
"step": 2300
|
171 |
},
|
172 |
{
|
173 |
-
"epoch": 0.
|
174 |
-
"grad_norm": 0.
|
175 |
-
"learning_rate":
|
176 |
-
"loss": 2.
|
177 |
"step": 2400
|
178 |
},
|
179 |
{
|
180 |
-
"epoch": 0.
|
181 |
-
"grad_norm": 0.
|
182 |
-
"learning_rate":
|
183 |
-
"loss": 2.
|
184 |
"step": 2500
|
185 |
},
|
186 |
{
|
187 |
-
"epoch": 0.
|
188 |
-
"grad_norm": 0.
|
189 |
-
"learning_rate":
|
190 |
-
"loss": 2.
|
191 |
"step": 2600
|
192 |
},
|
193 |
{
|
194 |
-
"epoch": 0.
|
195 |
-
"grad_norm": 0.
|
196 |
-
"learning_rate":
|
197 |
-
"loss": 2.
|
198 |
"step": 2700
|
199 |
},
|
200 |
{
|
201 |
-
"epoch": 0.
|
202 |
-
"grad_norm": 0.
|
203 |
-
"learning_rate":
|
204 |
-
"loss": 2.
|
205 |
"step": 2800
|
206 |
},
|
207 |
{
|
208 |
-
"epoch": 0.
|
209 |
-
"grad_norm": 0.
|
210 |
-
"learning_rate":
|
211 |
-
"loss": 2.
|
212 |
"step": 2900
|
213 |
},
|
214 |
{
|
215 |
-
"epoch": 0.
|
216 |
-
"grad_norm": 0.
|
217 |
-
"learning_rate":
|
218 |
-
"loss": 2.
|
219 |
"step": 3000
|
220 |
},
|
221 |
{
|
222 |
-
"epoch": 0.
|
223 |
-
"grad_norm": 0.
|
224 |
-
"learning_rate":
|
225 |
-
"loss": 2.
|
226 |
"step": 3100
|
227 |
},
|
228 |
{
|
229 |
-
"epoch": 0.
|
230 |
-
"grad_norm": 0.
|
231 |
-
"learning_rate":
|
232 |
-
"loss": 2.
|
233 |
"step": 3200
|
234 |
},
|
235 |
{
|
236 |
-
"epoch": 0.
|
237 |
-
"grad_norm": 0.
|
238 |
-
"learning_rate":
|
239 |
-
"loss": 2.
|
240 |
"step": 3300
|
241 |
},
|
242 |
{
|
243 |
-
"epoch": 0.
|
244 |
-
"grad_norm": 0.
|
245 |
-
"learning_rate":
|
246 |
-
"loss": 2.
|
247 |
"step": 3400
|
248 |
},
|
249 |
{
|
250 |
-
"epoch": 0.
|
251 |
-
"grad_norm": 0.
|
252 |
-
"learning_rate":
|
253 |
-
"loss": 2.
|
254 |
"step": 3500
|
255 |
},
|
256 |
{
|
257 |
-
"epoch": 0.
|
258 |
-
"grad_norm": 0.
|
259 |
-
"learning_rate": 1.
|
260 |
-
"loss": 2.
|
261 |
"step": 3600
|
262 |
},
|
263 |
{
|
264 |
-
"epoch": 0.
|
265 |
-
"grad_norm": 0.
|
266 |
-
"learning_rate": 1.
|
267 |
-
"loss": 2.
|
268 |
"step": 3700
|
269 |
},
|
270 |
{
|
271 |
-
"epoch": 0.
|
272 |
-
"grad_norm": 0.
|
273 |
-
"learning_rate": 1.
|
274 |
-
"loss": 2.
|
275 |
"step": 3800
|
276 |
},
|
277 |
{
|
278 |
-
"epoch": 0.
|
279 |
-
"grad_norm": 0.
|
280 |
-
"learning_rate": 1.
|
281 |
-
"loss": 2.
|
282 |
"step": 3900
|
283 |
},
|
284 |
{
|
285 |
-
"epoch": 0.
|
286 |
-
"grad_norm": 0.
|
287 |
-
"learning_rate": 1.
|
288 |
-
"loss": 2.
|
289 |
"step": 4000
|
290 |
},
|
291 |
{
|
292 |
-
"epoch": 0.
|
293 |
-
"grad_norm": 0.
|
294 |
-
"learning_rate": 1.
|
295 |
-
"loss": 2.
|
296 |
"step": 4100
|
297 |
},
|
298 |
{
|
299 |
-
"epoch": 0.
|
300 |
-
"grad_norm": 0.
|
301 |
-
"learning_rate": 1.
|
302 |
-
"loss": 2.
|
303 |
"step": 4200
|
304 |
},
|
305 |
{
|
306 |
-
"epoch": 0.
|
307 |
-
"grad_norm": 0.
|
308 |
-
"learning_rate": 1.
|
309 |
-
"loss": 2.
|
310 |
"step": 4300
|
311 |
},
|
312 |
{
|
313 |
-
"epoch": 0.
|
314 |
-
"grad_norm": 0.
|
315 |
-
"learning_rate": 1.
|
316 |
-
"loss": 2.
|
317 |
"step": 4400
|
318 |
},
|
319 |
{
|
320 |
-
"epoch": 0.
|
321 |
-
"grad_norm": 0.
|
322 |
-
"learning_rate": 1.
|
323 |
-
"loss": 2.
|
324 |
"step": 4500
|
325 |
},
|
326 |
{
|
327 |
-
"epoch": 0.
|
328 |
-
"grad_norm": 0.
|
329 |
-
"learning_rate": 1.
|
330 |
-
"loss": 2.
|
331 |
"step": 4600
|
332 |
},
|
333 |
{
|
334 |
-
"epoch": 0.
|
335 |
-
"grad_norm": 0.
|
336 |
-
"learning_rate": 1.
|
337 |
-
"loss": 2.
|
338 |
"step": 4700
|
339 |
},
|
340 |
{
|
341 |
-
"epoch": 0.
|
342 |
-
"grad_norm": 0.
|
343 |
-
"learning_rate": 1.
|
344 |
-
"loss": 2.
|
345 |
"step": 4800
|
346 |
},
|
347 |
{
|
348 |
-
"epoch": 0.
|
349 |
-
"grad_norm": 0.
|
350 |
-
"learning_rate": 1.
|
351 |
-
"loss": 2.
|
352 |
"step": 4900
|
353 |
},
|
354 |
{
|
355 |
-
"epoch": 0.
|
356 |
-
"grad_norm": 0.
|
357 |
-
"learning_rate": 1.
|
358 |
-
"loss": 2.
|
359 |
"step": 5000
|
360 |
},
|
361 |
{
|
362 |
-
"epoch": 0.
|
363 |
-
"grad_norm": 0.
|
364 |
-
"learning_rate": 1.
|
365 |
-
"loss": 2.
|
366 |
"step": 5100
|
367 |
},
|
368 |
{
|
369 |
-
"epoch": 0.
|
370 |
-
"grad_norm": 0.
|
371 |
-
"learning_rate": 1.
|
372 |
-
"loss": 2.
|
373 |
"step": 5200
|
374 |
},
|
375 |
{
|
376 |
-
"epoch": 0.
|
377 |
-
"grad_norm": 0.
|
378 |
-
"learning_rate":
|
379 |
-
"loss": 2.
|
380 |
"step": 5300
|
381 |
},
|
382 |
{
|
383 |
-
"epoch": 0.
|
384 |
-
"grad_norm": 0.
|
385 |
-
"learning_rate":
|
386 |
-
"loss": 2.
|
387 |
"step": 5400
|
388 |
},
|
389 |
{
|
390 |
-
"epoch": 0.
|
391 |
-
"grad_norm": 0.
|
392 |
-
"learning_rate":
|
393 |
-
"loss": 2.
|
394 |
"step": 5500
|
395 |
},
|
396 |
{
|
397 |
-
"epoch": 0.
|
398 |
-
"grad_norm": 0.
|
399 |
-
"learning_rate": 1.
|
400 |
-
"loss": 2.
|
401 |
"step": 5600
|
402 |
},
|
403 |
{
|
404 |
-
"epoch": 0.
|
405 |
-
"grad_norm": 0.
|
406 |
-
"learning_rate":
|
407 |
-
"loss": 2.
|
408 |
"step": 5700
|
409 |
},
|
410 |
{
|
411 |
-
"epoch": 0.
|
412 |
-
"grad_norm": 0.
|
413 |
-
"learning_rate":
|
414 |
-
"loss": 2.
|
415 |
"step": 5800
|
416 |
},
|
417 |
-
{
|
418 |
-
"epoch": 0.6573816155988857,
|
419 |
-
"grad_norm": 0.4182547628879547,
|
420 |
-
"learning_rate": 1.6436829642011422e-05,
|
421 |
-
"loss": 2.227,
|
422 |
-
"step": 5900
|
423 |
-
},
|
424 |
-
{
|
425 |
-
"epoch": 0.6685236768802229,
|
426 |
-
"grad_norm": 0.4616607129573822,
|
427 |
-
"learning_rate": 1.6715419974926873e-05,
|
428 |
-
"loss": 2.223,
|
429 |
-
"step": 6000
|
430 |
-
},
|
431 |
-
{
|
432 |
-
"epoch": 0.6796657381615598,
|
433 |
-
"grad_norm": 0.4605095386505127,
|
434 |
-
"learning_rate": 1.6994010307842318e-05,
|
435 |
-
"loss": 2.229,
|
436 |
-
"step": 6100
|
437 |
-
},
|
438 |
-
{
|
439 |
-
"epoch": 0.6908077994428969,
|
440 |
-
"grad_norm": 0.48064395785331726,
|
441 |
-
"learning_rate": 1.7272600640757766e-05,
|
442 |
-
"loss": 2.2285,
|
443 |
-
"step": 6200
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 0.7019498607242339,
|
447 |
-
"grad_norm": 0.45375484228134155,
|
448 |
-
"learning_rate": 1.7551190973673214e-05,
|
449 |
-
"loss": 2.231,
|
450 |
-
"step": 6300
|
451 |
-
},
|
452 |
-
{
|
453 |
-
"epoch": 0.713091922005571,
|
454 |
-
"grad_norm": 0.4386723041534424,
|
455 |
-
"learning_rate": 1.7829781306588662e-05,
|
456 |
-
"loss": 2.2295,
|
457 |
-
"step": 6400
|
458 |
-
},
|
459 |
-
{
|
460 |
-
"epoch": 0.724233983286908,
|
461 |
-
"grad_norm": 0.4519370198249817,
|
462 |
-
"learning_rate": 1.810837163950411e-05,
|
463 |
-
"loss": 2.2185,
|
464 |
-
"step": 6500
|
465 |
-
},
|
466 |
-
{
|
467 |
-
"epoch": 0.7353760445682451,
|
468 |
-
"grad_norm": 0.45770174264907837,
|
469 |
-
"learning_rate": 1.8386961972419558e-05,
|
470 |
-
"loss": 2.2146,
|
471 |
-
"step": 6600
|
472 |
-
},
|
473 |
-
{
|
474 |
-
"epoch": 0.7465181058495822,
|
475 |
-
"grad_norm": 0.46970096230506897,
|
476 |
-
"learning_rate": 1.8665552305335006e-05,
|
477 |
-
"loss": 2.2268,
|
478 |
-
"step": 6700
|
479 |
-
},
|
480 |
-
{
|
481 |
-
"epoch": 0.7576601671309192,
|
482 |
-
"grad_norm": 0.4301040768623352,
|
483 |
-
"learning_rate": 1.8944142638250454e-05,
|
484 |
-
"loss": 2.2186,
|
485 |
-
"step": 6800
|
486 |
-
},
|
487 |
-
{
|
488 |
-
"epoch": 0.7688022284122563,
|
489 |
-
"grad_norm": 0.49275335669517517,
|
490 |
-
"learning_rate": 1.9222732971165902e-05,
|
491 |
-
"loss": 2.2143,
|
492 |
-
"step": 6900
|
493 |
-
},
|
494 |
-
{
|
495 |
-
"epoch": 0.7799442896935933,
|
496 |
-
"grad_norm": 0.4531406760215759,
|
497 |
-
"learning_rate": 1.950132330408135e-05,
|
498 |
-
"loss": 2.2087,
|
499 |
-
"step": 7000
|
500 |
-
},
|
501 |
-
{
|
502 |
-
"epoch": 0.7910863509749304,
|
503 |
-
"grad_norm": 0.44058841466903687,
|
504 |
-
"learning_rate": 1.97799136369968e-05,
|
505 |
-
"loss": 2.2081,
|
506 |
-
"step": 7100
|
507 |
-
},
|
508 |
-
{
|
509 |
-
"epoch": 0.8022284122562674,
|
510 |
-
"grad_norm": 0.4620118737220764,
|
511 |
-
"learning_rate": 1.9993253992196043e-05,
|
512 |
-
"loss": 2.2029,
|
513 |
-
"step": 7200
|
514 |
-
},
|
515 |
-
{
|
516 |
-
"epoch": 0.8133704735376045,
|
517 |
-
"grad_norm": 0.4749448299407959,
|
518 |
-
"learning_rate": 1.9776845355951603e-05,
|
519 |
-
"loss": 2.1974,
|
520 |
-
"step": 7300
|
521 |
-
},
|
522 |
-
{
|
523 |
-
"epoch": 0.8245125348189415,
|
524 |
-
"grad_norm": 0.4482609033584595,
|
525 |
-
"learning_rate": 1.9262050899616325e-05,
|
526 |
-
"loss": 2.2229,
|
527 |
-
"step": 7400
|
528 |
-
},
|
529 |
-
{
|
530 |
-
"epoch": 0.8356545961002786,
|
531 |
-
"grad_norm": 0.4689159095287323,
|
532 |
-
"learning_rate": 1.8464581965697866e-05,
|
533 |
-
"loss": 2.2081,
|
534 |
-
"step": 7500
|
535 |
-
},
|
536 |
-
{
|
537 |
-
"epoch": 0.8467966573816156,
|
538 |
-
"grad_norm": 0.4448583126068115,
|
539 |
-
"learning_rate": 1.7408777020560473e-05,
|
540 |
-
"loss": 2.2181,
|
541 |
-
"step": 7600
|
542 |
-
},
|
543 |
-
{
|
544 |
-
"epoch": 0.8579387186629527,
|
545 |
-
"grad_norm": 0.513080894947052,
|
546 |
-
"learning_rate": 1.6126858853144854e-05,
|
547 |
-
"loss": 2.2045,
|
548 |
-
"step": 7700
|
549 |
-
},
|
550 |
-
{
|
551 |
-
"epoch": 0.8690807799442897,
|
552 |
-
"grad_norm": 0.4850214421749115,
|
553 |
-
"learning_rate": 1.465795114698568e-05,
|
554 |
-
"loss": 2.1966,
|
555 |
-
"step": 7800
|
556 |
-
},
|
557 |
-
{
|
558 |
-
"epoch": 0.8802228412256268,
|
559 |
-
"grad_norm": 0.5757237672805786,
|
560 |
-
"learning_rate": 1.3046884439396632e-05,
|
561 |
-
"loss": 2.2019,
|
562 |
-
"step": 7900
|
563 |
-
},
|
564 |
-
{
|
565 |
-
"epoch": 0.8913649025069638,
|
566 |
-
"grad_norm": 0.48911547660827637,
|
567 |
-
"learning_rate": 1.1342827909521198e-05,
|
568 |
-
"loss": 2.1994,
|
569 |
-
"step": 8000
|
570 |
-
},
|
571 |
-
{
|
572 |
-
"epoch": 0.9025069637883009,
|
573 |
-
"grad_norm": 0.5143416523933411,
|
574 |
-
"learning_rate": 9.597788752588108e-06,
|
575 |
-
"loss": 2.207,
|
576 |
-
"step": 8100
|
577 |
-
},
|
578 |
-
{
|
579 |
-
"epoch": 0.9136490250696379,
|
580 |
-
"grad_norm": 0.483064204454422,
|
581 |
-
"learning_rate": 7.882117054290375e-06,
|
582 |
-
"loss": 2.1971,
|
583 |
-
"step": 8200
|
584 |
-
},
|
585 |
-
{
|
586 |
-
"epoch": 0.924791086350975,
|
587 |
-
"grad_norm": 0.4610692262649536,
|
588 |
-
"learning_rate": 6.213603769467132e-06,
|
589 |
-
"loss": 2.1977,
|
590 |
-
"step": 8300
|
591 |
-
},
|
592 |
-
{
|
593 |
-
"epoch": 0.935933147632312,
|
594 |
-
"grad_norm": 0.50405353307724,
|
595 |
-
"learning_rate": 4.660649942045826e-06,
|
596 |
-
"loss": 2.1955,
|
597 |
-
"step": 8400
|
598 |
-
},
|
599 |
-
{
|
600 |
-
"epoch": 0.947075208913649,
|
601 |
-
"grad_norm": 0.47849225997924805,
|
602 |
-
"learning_rate": 3.27065116687201e-06,
|
603 |
-
"loss": 2.1906,
|
604 |
-
"step": 8500
|
605 |
-
},
|
606 |
-
{
|
607 |
-
"epoch": 0.958217270194986,
|
608 |
-
"grad_norm": 0.49040549993515015,
|
609 |
-
"learning_rate": 2.0860297089355943e-06,
|
610 |
-
"loss": 2.1875,
|
611 |
-
"step": 8600
|
612 |
-
},
|
613 |
-
{
|
614 |
-
"epoch": 0.9693593314763231,
|
615 |
-
"grad_norm": 0.49369877576828003,
|
616 |
-
"learning_rate": 1.1429397910307794e-06,
|
617 |
-
"loss": 2.2054,
|
618 |
-
"step": 8700
|
619 |
-
},
|
620 |
-
{
|
621 |
-
"epoch": 0.9805013927576601,
|
622 |
-
"grad_norm": 0.5104972124099731,
|
623 |
-
"learning_rate": 4.701641798198353e-07,
|
624 |
-
"loss": 2.2121,
|
625 |
-
"step": 8800
|
626 |
-
},
|
627 |
-
{
|
628 |
-
"epoch": 0.9916434540389972,
|
629 |
-
"grad_norm": 0.48128950595855713,
|
630 |
-
"learning_rate": 8.823574609897134e-08,
|
631 |
-
"loss": 2.1928,
|
632 |
-
"step": 8900
|
633 |
-
},
|
634 |
{
|
635 |
"epoch": 1.0,
|
636 |
-
"step":
|
637 |
-
"total_flos":
|
638 |
-
"train_loss": 2.
|
639 |
-
"train_runtime":
|
640 |
-
"train_samples_per_second":
|
641 |
-
"train_steps_per_second": 3.
|
642 |
}
|
643 |
],
|
644 |
"logging_steps": 100,
|
645 |
-
"max_steps":
|
646 |
"num_input_tokens_seen": 0,
|
647 |
"num_train_epochs": 1,
|
648 |
"save_steps": 500,
|
@@ -658,7 +441,7 @@
|
|
658 |
"attributes": {}
|
659 |
}
|
660 |
},
|
661 |
-
"total_flos":
|
662 |
"train_batch_size": 2,
|
663 |
"trial_name": null,
|
664 |
"trial_params": null
|
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 5805,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.017226528854435832,
|
13 |
+
"grad_norm": 0.04875866696238518,
|
14 |
+
"learning_rate": 4.307559767391773e-07,
|
15 |
+
"loss": 2.816,
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.034453057708871665,
|
20 |
+
"grad_norm": 0.04928815737366676,
|
21 |
+
"learning_rate": 8.615119534783546e-07,
|
22 |
+
"loss": 2.8077,
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.05167958656330749,
|
27 |
+
"grad_norm": 0.05480952933430672,
|
28 |
+
"learning_rate": 1.292267930217532e-06,
|
29 |
+
"loss": 2.8162,
|
30 |
"step": 300
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.06890611541774333,
|
34 |
+
"grad_norm": 0.06494510173797607,
|
35 |
+
"learning_rate": 1.7230239069567093e-06,
|
36 |
+
"loss": 2.8237,
|
37 |
"step": 400
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 0.08613264427217916,
|
41 |
+
"grad_norm": 0.08336891233921051,
|
42 |
+
"learning_rate": 2.1537798836958863e-06,
|
43 |
+
"loss": 2.7987,
|
44 |
"step": 500
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.10335917312661498,
|
48 |
+
"grad_norm": 0.09097711741924286,
|
49 |
+
"learning_rate": 2.584535860435064e-06,
|
50 |
+
"loss": 2.7894,
|
51 |
"step": 600
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.12058570198105081,
|
55 |
+
"grad_norm": 0.11103380471467972,
|
56 |
+
"learning_rate": 3.015291837174241e-06,
|
57 |
+
"loss": 2.7909,
|
58 |
"step": 700
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 0.13781223083548666,
|
62 |
+
"grad_norm": 0.11578191071748734,
|
63 |
+
"learning_rate": 3.4460478139134186e-06,
|
64 |
+
"loss": 2.7922,
|
65 |
"step": 800
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 0.15503875968992248,
|
69 |
+
"grad_norm": 0.1395414024591446,
|
70 |
+
"learning_rate": 3.876803790652596e-06,
|
71 |
+
"loss": 2.7704,
|
72 |
"step": 900
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 0.17226528854435832,
|
76 |
+
"grad_norm": 0.1293153464794159,
|
77 |
+
"learning_rate": 4.3075597673917726e-06,
|
78 |
+
"loss": 2.7549,
|
79 |
"step": 1000
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 0.18949181739879414,
|
83 |
+
"grad_norm": 0.13815675675868988,
|
84 |
+
"learning_rate": 4.73831574413095e-06,
|
85 |
+
"loss": 2.7386,
|
86 |
"step": 1100
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 0.20671834625322996,
|
90 |
+
"grad_norm": 0.15647341310977936,
|
91 |
+
"learning_rate": 5.169071720870128e-06,
|
92 |
+
"loss": 2.7453,
|
93 |
"step": 1200
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 0.2239448751076658,
|
97 |
+
"grad_norm": 0.17875690758228302,
|
98 |
+
"learning_rate": 5.599827697609305e-06,
|
99 |
+
"loss": 2.7357,
|
100 |
"step": 1300
|
101 |
},
|
102 |
{
|
103 |
+
"epoch": 0.24117140396210163,
|
104 |
+
"grad_norm": 0.16741064190864563,
|
105 |
+
"learning_rate": 6.030583674348482e-06,
|
106 |
+
"loss": 2.739,
|
107 |
"step": 1400
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 0.25839793281653745,
|
111 |
+
"grad_norm": 0.17629371583461761,
|
112 |
+
"learning_rate": 6.461339651087659e-06,
|
113 |
+
"loss": 2.7257,
|
114 |
"step": 1500
|
115 |
},
|
116 |
{
|
117 |
+
"epoch": 0.2756244616709733,
|
118 |
+
"grad_norm": 0.18484149873256683,
|
119 |
+
"learning_rate": 6.892095627826837e-06,
|
120 |
+
"loss": 2.712,
|
121 |
"step": 1600
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 0.29285099052540914,
|
125 |
+
"grad_norm": 0.18326900899410248,
|
126 |
+
"learning_rate": 7.322851604566014e-06,
|
127 |
+
"loss": 2.7207,
|
128 |
"step": 1700
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 0.31007751937984496,
|
132 |
+
"grad_norm": 0.20282337069511414,
|
133 |
+
"learning_rate": 7.753607581305192e-06,
|
134 |
+
"loss": 2.7264,
|
135 |
"step": 1800
|
136 |
},
|
137 |
{
|
138 |
+
"epoch": 0.3273040482342808,
|
139 |
+
"grad_norm": 0.19705314934253693,
|
140 |
+
"learning_rate": 8.184363558044369e-06,
|
141 |
+
"loss": 2.7107,
|
142 |
"step": 1900
|
143 |
},
|
144 |
{
|
145 |
+
"epoch": 0.34453057708871665,
|
146 |
+
"grad_norm": 0.2224486768245697,
|
147 |
+
"learning_rate": 8.615119534783545e-06,
|
148 |
+
"loss": 2.6999,
|
149 |
"step": 2000
|
150 |
},
|
151 |
{
|
152 |
+
"epoch": 0.36175710594315247,
|
153 |
+
"grad_norm": 0.21177536249160767,
|
154 |
+
"learning_rate": 9.045875511522723e-06,
|
155 |
+
"loss": 2.7055,
|
156 |
"step": 2100
|
157 |
},
|
158 |
{
|
159 |
+
"epoch": 0.3789836347975883,
|
160 |
+
"grad_norm": 0.21247607469558716,
|
161 |
+
"learning_rate": 9.4766314882619e-06,
|
162 |
+
"loss": 2.6962,
|
163 |
"step": 2200
|
164 |
},
|
165 |
{
|
166 |
+
"epoch": 0.3962101636520241,
|
167 |
+
"grad_norm": 0.2235407829284668,
|
168 |
+
"learning_rate": 9.907387465001078e-06,
|
169 |
+
"loss": 2.6898,
|
170 |
"step": 2300
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 0.4134366925064599,
|
174 |
+
"grad_norm": 0.22821404039859772,
|
175 |
+
"learning_rate": 1.0338143441740256e-05,
|
176 |
+
"loss": 2.6896,
|
177 |
"step": 2400
|
178 |
},
|
179 |
{
|
180 |
+
"epoch": 0.4306632213608958,
|
181 |
+
"grad_norm": 0.21626809239387512,
|
182 |
+
"learning_rate": 1.0768899418479433e-05,
|
183 |
+
"loss": 2.6859,
|
184 |
"step": 2500
|
185 |
},
|
186 |
{
|
187 |
+
"epoch": 0.4478897502153316,
|
188 |
+
"grad_norm": 0.2285173088312149,
|
189 |
+
"learning_rate": 1.119965539521861e-05,
|
190 |
+
"loss": 2.6636,
|
191 |
"step": 2600
|
192 |
},
|
193 |
{
|
194 |
+
"epoch": 0.46511627906976744,
|
195 |
+
"grad_norm": 0.2364313304424286,
|
196 |
+
"learning_rate": 1.1630411371957786e-05,
|
197 |
+
"loss": 2.6726,
|
198 |
"step": 2700
|
199 |
},
|
200 |
{
|
201 |
+
"epoch": 0.48234280792420325,
|
202 |
+
"grad_norm": 0.2359386384487152,
|
203 |
+
"learning_rate": 1.2061167348696965e-05,
|
204 |
+
"loss": 2.6635,
|
205 |
"step": 2800
|
206 |
},
|
207 |
{
|
208 |
+
"epoch": 0.49956933677863913,
|
209 |
+
"grad_norm": 0.2400447577238083,
|
210 |
+
"learning_rate": 1.2491923325436141e-05,
|
211 |
+
"loss": 2.6934,
|
212 |
"step": 2900
|
213 |
},
|
214 |
{
|
215 |
+
"epoch": 0.5167958656330749,
|
216 |
+
"grad_norm": 0.24956579506397247,
|
217 |
+
"learning_rate": 1.2922679302175318e-05,
|
218 |
+
"loss": 2.6663,
|
219 |
"step": 3000
|
220 |
},
|
221 |
{
|
222 |
+
"epoch": 0.5340223944875108,
|
223 |
+
"grad_norm": 0.24709786474704742,
|
224 |
+
"learning_rate": 1.3353435278914494e-05,
|
225 |
+
"loss": 2.6408,
|
226 |
"step": 3100
|
227 |
},
|
228 |
{
|
229 |
+
"epoch": 0.5512489233419466,
|
230 |
+
"grad_norm": 0.2572828233242035,
|
231 |
+
"learning_rate": 1.3784191255653674e-05,
|
232 |
+
"loss": 2.6621,
|
233 |
"step": 3200
|
234 |
},
|
235 |
{
|
236 |
+
"epoch": 0.5684754521963824,
|
237 |
+
"grad_norm": 0.26790568232536316,
|
238 |
+
"learning_rate": 1.421494723239285e-05,
|
239 |
+
"loss": 2.6388,
|
240 |
"step": 3300
|
241 |
},
|
242 |
{
|
243 |
+
"epoch": 0.5857019810508183,
|
244 |
+
"grad_norm": 0.2591148912906647,
|
245 |
+
"learning_rate": 1.4645703209132027e-05,
|
246 |
+
"loss": 2.6415,
|
247 |
"step": 3400
|
248 |
},
|
249 |
{
|
250 |
+
"epoch": 0.602928509905254,
|
251 |
+
"grad_norm": 0.2609754800796509,
|
252 |
+
"learning_rate": 1.5076459185871206e-05,
|
253 |
+
"loss": 2.6588,
|
254 |
"step": 3500
|
255 |
},
|
256 |
{
|
257 |
+
"epoch": 0.6201550387596899,
|
258 |
+
"grad_norm": 0.2639792859554291,
|
259 |
+
"learning_rate": 1.5507215162610384e-05,
|
260 |
+
"loss": 2.6533,
|
261 |
"step": 3600
|
262 |
},
|
263 |
{
|
264 |
+
"epoch": 0.6373815676141258,
|
265 |
+
"grad_norm": 0.2771030366420746,
|
266 |
+
"learning_rate": 1.593797113934956e-05,
|
267 |
+
"loss": 2.6316,
|
268 |
"step": 3700
|
269 |
},
|
270 |
{
|
271 |
+
"epoch": 0.6546080964685616,
|
272 |
+
"grad_norm": 0.2596473693847656,
|
273 |
+
"learning_rate": 1.6368727116088737e-05,
|
274 |
+
"loss": 2.6474,
|
275 |
"step": 3800
|
276 |
},
|
277 |
{
|
278 |
+
"epoch": 0.6718346253229974,
|
279 |
+
"grad_norm": 0.2842521369457245,
|
280 |
+
"learning_rate": 1.6799483092827914e-05,
|
281 |
+
"loss": 2.6475,
|
282 |
"step": 3900
|
283 |
},
|
284 |
{
|
285 |
+
"epoch": 0.6890611541774333,
|
286 |
+
"grad_norm": 0.282993346452713,
|
287 |
+
"learning_rate": 1.723023906956709e-05,
|
288 |
+
"loss": 2.6391,
|
289 |
"step": 4000
|
290 |
},
|
291 |
{
|
292 |
+
"epoch": 0.7062876830318691,
|
293 |
+
"grad_norm": 0.29125678539276123,
|
294 |
+
"learning_rate": 1.766099504630627e-05,
|
295 |
+
"loss": 2.6246,
|
296 |
"step": 4100
|
297 |
},
|
298 |
{
|
299 |
+
"epoch": 0.7235142118863049,
|
300 |
+
"grad_norm": 0.2812328338623047,
|
301 |
+
"learning_rate": 1.8091751023045447e-05,
|
302 |
+
"loss": 2.6469,
|
303 |
"step": 4200
|
304 |
},
|
305 |
{
|
306 |
+
"epoch": 0.7407407407407407,
|
307 |
+
"grad_norm": 0.2858037054538727,
|
308 |
+
"learning_rate": 1.8522506999784623e-05,
|
309 |
+
"loss": 2.6348,
|
310 |
"step": 4300
|
311 |
},
|
312 |
{
|
313 |
+
"epoch": 0.7579672695951766,
|
314 |
+
"grad_norm": 0.30100327730178833,
|
315 |
+
"learning_rate": 1.89532629765238e-05,
|
316 |
+
"loss": 2.6315,
|
317 |
"step": 4400
|
318 |
},
|
319 |
{
|
320 |
+
"epoch": 0.7751937984496124,
|
321 |
+
"grad_norm": 0.28023988008499146,
|
322 |
+
"learning_rate": 1.9384018953262976e-05,
|
323 |
+
"loss": 2.6244,
|
324 |
"step": 4500
|
325 |
},
|
326 |
{
|
327 |
+
"epoch": 0.7924203273040482,
|
328 |
+
"grad_norm": 0.2947770953178406,
|
329 |
+
"learning_rate": 1.9814774930002156e-05,
|
330 |
+
"loss": 2.6277,
|
331 |
"step": 4600
|
332 |
},
|
333 |
{
|
334 |
+
"epoch": 0.8096468561584841,
|
335 |
+
"grad_norm": 0.30242860317230225,
|
336 |
+
"learning_rate": 1.9881492033537068e-05,
|
337 |
+
"loss": 2.6132,
|
338 |
"step": 4700
|
339 |
},
|
340 |
{
|
341 |
+
"epoch": 0.8268733850129198,
|
342 |
+
"grad_norm": 0.2965434789657593,
|
343 |
+
"learning_rate": 1.9112585857815527e-05,
|
344 |
+
"loss": 2.6114,
|
345 |
"step": 4800
|
346 |
},
|
347 |
{
|
348 |
+
"epoch": 0.8440999138673557,
|
349 |
+
"grad_norm": 0.2951013743877411,
|
350 |
+
"learning_rate": 1.7681642907588395e-05,
|
351 |
+
"loss": 2.6349,
|
352 |
"step": 4900
|
353 |
},
|
354 |
{
|
355 |
+
"epoch": 0.8613264427217916,
|
356 |
+
"grad_norm": 0.34424757957458496,
|
357 |
+
"learning_rate": 1.5692622352080662e-05,
|
358 |
+
"loss": 2.6065,
|
359 |
"step": 5000
|
360 |
},
|
361 |
{
|
362 |
+
"epoch": 0.8785529715762274,
|
363 |
+
"grad_norm": 0.283710241317749,
|
364 |
+
"learning_rate": 1.329002815246645e-05,
|
365 |
+
"loss": 2.6098,
|
366 |
"step": 5100
|
367 |
},
|
368 |
{
|
369 |
+
"epoch": 0.8957795004306632,
|
370 |
+
"grad_norm": 0.28349170088768005,
|
371 |
+
"learning_rate": 1.064841073155404e-05,
|
372 |
+
"loss": 2.618,
|
373 |
"step": 5200
|
374 |
},
|
375 |
{
|
376 |
+
"epoch": 0.9130060292850991,
|
377 |
+
"grad_norm": 0.31287553906440735,
|
378 |
+
"learning_rate": 7.95968574359416e-06,
|
379 |
+
"loss": 2.603,
|
380 |
"step": 5300
|
381 |
},
|
382 |
{
|
383 |
+
"epoch": 0.9302325581395349,
|
384 |
+
"grad_norm": 0.2843669652938843,
|
385 |
+
"learning_rate": 5.419191245899586e-06,
|
386 |
+
"loss": 2.6192,
|
387 |
"step": 5400
|
388 |
},
|
389 |
{
|
390 |
+
"epoch": 0.9474590869939707,
|
391 |
+
"grad_norm": 0.2816653847694397,
|
392 |
+
"learning_rate": 3.211496230098576e-06,
|
393 |
+
"loss": 2.6142,
|
394 |
"step": 5500
|
395 |
},
|
396 |
{
|
397 |
+
"epoch": 0.9646856158484065,
|
398 |
+
"grad_norm": 0.30356064438819885,
|
399 |
+
"learning_rate": 1.496991534769564e-06,
|
400 |
+
"loss": 2.6198,
|
401 |
"step": 5600
|
402 |
},
|
403 |
{
|
404 |
+
"epoch": 0.9819121447028424,
|
405 |
+
"grad_norm": 0.27873966097831726,
|
406 |
+
"learning_rate": 4.0023732056077235e-07,
|
407 |
+
"loss": 2.6062,
|
408 |
"step": 5700
|
409 |
},
|
410 |
{
|
411 |
+
"epoch": 0.9991386735572783,
|
412 |
+
"grad_norm": 0.3346691429615021,
|
413 |
+
"learning_rate": 9.136732052228426e-10,
|
414 |
+
"loss": 2.6072,
|
415 |
"step": 5800
|
416 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
417 |
{
|
418 |
"epoch": 1.0,
|
419 |
+
"step": 5805,
|
420 |
+
"total_flos": 8.45892909419987e+17,
|
421 |
+
"train_loss": 2.683517217184325,
|
422 |
+
"train_runtime": 1637.9851,
|
423 |
+
"train_samples_per_second": 56.701,
|
424 |
+
"train_steps_per_second": 3.544
|
425 |
}
|
426 |
],
|
427 |
"logging_steps": 100,
|
428 |
+
"max_steps": 5805,
|
429 |
"num_input_tokens_seen": 0,
|
430 |
"num_train_epochs": 1,
|
431 |
"save_steps": 500,
|
|
|
441 |
"attributes": {}
|
442 |
}
|
443 |
},
|
444 |
+
"total_flos": 8.45892909419987e+17,
|
445 |
"train_batch_size": 2,
|
446 |
"trial_name": null,
|
447 |
"trial_params": null
|