JEdward7777
commited on
Commit
•
9f4ff4f
1
Parent(s):
3169fac
End of training
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- runs/Jan05_13-26-49_78b464702e4c/events.out.tfevents.1672929710.78b464702e4c.573.2 +3 -0
- train_results.json +5 -5
- trainer_state.json +393 -393
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch": 59.
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 4.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"total_flos": 8.
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second": 8.
|
12 |
"train_steps_per_second": 0.057
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 59.84,
|
3 |
+
"eval_accuracy": 0.9846153846153847,
|
4 |
+
"eval_loss": 0.1295621246099472,
|
5 |
+
"eval_runtime": 4.3947,
|
6 |
+
"eval_samples_per_second": 14.791,
|
7 |
+
"eval_steps_per_second": 0.683,
|
8 |
+
"total_flos": 8.648855308501955e+17,
|
9 |
+
"train_loss": 0.577343902985255,
|
10 |
+
"train_runtime": 4213.9216,
|
11 |
+
"train_samples_per_second": 8.273,
|
12 |
"train_steps_per_second": 0.057
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 59.
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 4.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 59.84,
|
3 |
+
"eval_accuracy": 0.9846153846153847,
|
4 |
+
"eval_loss": 0.1295621246099472,
|
5 |
+
"eval_runtime": 4.3947,
|
6 |
+
"eval_samples_per_second": 14.791,
|
7 |
+
"eval_steps_per_second": 0.683
|
8 |
}
|
runs/Jan05_13-26-49_78b464702e4c/events.out.tfevents.1672929710.78b464702e4c.573.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf84a9cee06528ecf79659bde56b701c98d8e8a6a52cf3659e0abcbe033c4b70
|
3 |
+
size 363
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 59.
|
3 |
-
"total_flos": 8.
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 8.
|
7 |
"train_steps_per_second": 0.057
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 59.84,
|
3 |
+
"total_flos": 8.648855308501955e+17,
|
4 |
+
"train_loss": 0.577343902985255,
|
5 |
+
"train_runtime": 4213.9216,
|
6 |
+
"train_samples_per_second": 8.273,
|
7 |
"train_steps_per_second": 0.057
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,637 +1,637 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "delivery_truck_classification/checkpoint-
|
4 |
-
"epoch": 59.
|
5 |
"global_step": 240,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch": 0.
|
12 |
-
"eval_accuracy": 0.
|
13 |
-
"eval_loss":
|
14 |
-
"eval_runtime": 4.
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second": 0.
|
17 |
"step": 4
|
18 |
},
|
19 |
{
|
20 |
-
"epoch": 1.
|
21 |
-
"eval_accuracy": 0.
|
22 |
-
"eval_loss": 1.
|
23 |
-
"eval_runtime":
|
24 |
-
"eval_samples_per_second": 12.
|
25 |
-
"eval_steps_per_second": 0.
|
26 |
"step": 8
|
27 |
},
|
28 |
{
|
29 |
-
"epoch": 2.
|
30 |
-
"eval_accuracy": 0.
|
31 |
-
"eval_loss": 1.
|
32 |
-
"eval_runtime": 4.
|
33 |
-
"eval_samples_per_second":
|
34 |
-
"eval_steps_per_second": 0.
|
35 |
"step": 12
|
36 |
},
|
37 |
{
|
38 |
-
"epoch": 3.
|
39 |
-
"eval_accuracy": 0.
|
40 |
-
"eval_loss": 1.
|
41 |
-
"eval_runtime": 4.
|
42 |
-
"eval_samples_per_second":
|
43 |
-
"eval_steps_per_second": 0.
|
44 |
"step": 16
|
45 |
},
|
46 |
{
|
47 |
-
"epoch": 4.
|
48 |
"learning_rate": 4.166666666666667e-05,
|
49 |
-
"loss": 1.
|
50 |
"step": 20
|
51 |
},
|
52 |
{
|
53 |
-
"epoch": 4.
|
54 |
-
"eval_accuracy": 0.
|
55 |
-
"eval_loss": 1.
|
56 |
-
"eval_runtime": 4.
|
57 |
-
"eval_samples_per_second":
|
58 |
-
"eval_steps_per_second": 0.
|
59 |
"step": 20
|
60 |
},
|
61 |
{
|
62 |
-
"epoch": 5.
|
63 |
-
"eval_accuracy": 0.
|
64 |
-
"eval_loss": 1.
|
65 |
-
"eval_runtime": 4.
|
66 |
-
"eval_samples_per_second":
|
67 |
-
"eval_steps_per_second": 0.
|
68 |
"step": 24
|
69 |
},
|
70 |
{
|
71 |
-
"epoch": 6.
|
72 |
-
"eval_accuracy": 0.
|
73 |
-
"eval_loss": 0.
|
74 |
-
"eval_runtime": 4.
|
75 |
-
"eval_samples_per_second": 15.
|
76 |
-
"eval_steps_per_second": 0.
|
77 |
"step": 28
|
78 |
},
|
79 |
{
|
80 |
-
"epoch": 7.
|
81 |
-
"eval_accuracy": 0.
|
82 |
-
"eval_loss": 0.
|
83 |
-
"eval_runtime": 4.
|
84 |
-
"eval_samples_per_second": 13.
|
85 |
-
"eval_steps_per_second": 0.
|
86 |
"step": 32
|
87 |
},
|
88 |
{
|
89 |
-
"epoch": 8.
|
90 |
-
"eval_accuracy": 0.
|
91 |
-
"eval_loss": 0.
|
92 |
-
"eval_runtime": 4.
|
93 |
-
"eval_samples_per_second":
|
94 |
-
"eval_steps_per_second": 0.
|
95 |
"step": 36
|
96 |
},
|
97 |
{
|
98 |
-
"epoch": 9.
|
99 |
"learning_rate": 4.62962962962963e-05,
|
100 |
-
"loss": 1.
|
101 |
"step": 40
|
102 |
},
|
103 |
{
|
104 |
-
"epoch": 9.
|
105 |
-
"eval_accuracy": 0.
|
106 |
-
"eval_loss": 0.
|
107 |
-
"eval_runtime": 4.
|
108 |
-
"eval_samples_per_second": 13.
|
109 |
-
"eval_steps_per_second": 0.
|
110 |
"step": 40
|
111 |
},
|
112 |
{
|
113 |
-
"epoch": 10.
|
114 |
-
"eval_accuracy": 0.
|
115 |
-
"eval_loss": 0.
|
116 |
-
"eval_runtime": 4.
|
117 |
-
"eval_samples_per_second": 15.
|
118 |
-
"eval_steps_per_second": 0.
|
119 |
"step": 44
|
120 |
},
|
121 |
{
|
122 |
-
"epoch": 11.
|
123 |
-
"eval_accuracy": 0.
|
124 |
-
"eval_loss": 0.
|
125 |
-
"eval_runtime": 4.
|
126 |
-
"eval_samples_per_second":
|
127 |
-
"eval_steps_per_second": 0.
|
128 |
"step": 48
|
129 |
},
|
130 |
{
|
131 |
-
"epoch": 12.
|
132 |
-
"eval_accuracy": 0.
|
133 |
-
"eval_loss": 0.
|
134 |
-
"eval_runtime": 4.
|
135 |
-
"eval_samples_per_second": 14.
|
136 |
-
"eval_steps_per_second": 0.
|
137 |
"step": 52
|
138 |
},
|
139 |
{
|
140 |
-
"epoch": 13.
|
141 |
-
"eval_accuracy": 0.
|
142 |
-
"eval_loss": 0.
|
143 |
-
"eval_runtime": 4.
|
144 |
-
"eval_samples_per_second":
|
145 |
-
"eval_steps_per_second": 0.
|
146 |
"step": 56
|
147 |
},
|
148 |
{
|
149 |
-
"epoch": 14.
|
150 |
"learning_rate": 4.166666666666667e-05,
|
151 |
-
"loss": 0.
|
152 |
"step": 60
|
153 |
},
|
154 |
{
|
155 |
-
"epoch": 14.
|
156 |
-
"eval_accuracy": 0.
|
157 |
-
"eval_loss": 0.
|
158 |
-
"eval_runtime": 4.
|
159 |
-
"eval_samples_per_second": 15.
|
160 |
-
"eval_steps_per_second": 0.
|
161 |
"step": 60
|
162 |
},
|
163 |
{
|
164 |
-
"epoch": 15.
|
165 |
-
"eval_accuracy": 0.
|
166 |
-
"eval_loss": 0.
|
167 |
-
"eval_runtime": 4.
|
168 |
-
"eval_samples_per_second":
|
169 |
-
"eval_steps_per_second": 0.
|
170 |
"step": 64
|
171 |
},
|
172 |
{
|
173 |
-
"epoch": 16.
|
174 |
-
"eval_accuracy": 0.
|
175 |
-
"eval_loss": 0.
|
176 |
-
"eval_runtime": 4.
|
177 |
-
"eval_samples_per_second": 15.
|
178 |
-
"eval_steps_per_second": 0.
|
179 |
"step": 68
|
180 |
},
|
181 |
{
|
182 |
-
"epoch": 17.
|
183 |
-
"eval_accuracy": 0.
|
184 |
-
"eval_loss": 0.
|
185 |
-
"eval_runtime": 4.
|
186 |
-
"eval_samples_per_second":
|
187 |
-
"eval_steps_per_second": 0.
|
188 |
"step": 72
|
189 |
},
|
190 |
{
|
191 |
-
"epoch": 18.
|
192 |
-
"eval_accuracy": 0.
|
193 |
-
"eval_loss": 0.
|
194 |
-
"eval_runtime": 4.
|
195 |
-
"eval_samples_per_second": 15.
|
196 |
-
"eval_steps_per_second": 0.
|
197 |
"step": 76
|
198 |
},
|
199 |
{
|
200 |
-
"epoch": 19.
|
201 |
"learning_rate": 3.7037037037037037e-05,
|
202 |
-
"loss": 0.
|
203 |
"step": 80
|
204 |
},
|
205 |
{
|
206 |
-
"epoch": 19.
|
207 |
-
"eval_accuracy": 0.
|
208 |
-
"eval_loss": 0.
|
209 |
-
"eval_runtime": 4.
|
210 |
-
"eval_samples_per_second":
|
211 |
-
"eval_steps_per_second": 0.
|
212 |
"step": 80
|
213 |
},
|
214 |
{
|
215 |
-
"epoch": 20.
|
216 |
-
"eval_accuracy": 0.
|
217 |
-
"eval_loss": 0.
|
218 |
-
"eval_runtime": 4.
|
219 |
-
"eval_samples_per_second": 15.
|
220 |
-
"eval_steps_per_second": 0.
|
221 |
"step": 84
|
222 |
},
|
223 |
{
|
224 |
-
"epoch": 21.
|
225 |
-
"eval_accuracy": 0.
|
226 |
-
"eval_loss": 0.
|
227 |
-
"eval_runtime":
|
228 |
-
"eval_samples_per_second":
|
229 |
-
"eval_steps_per_second": 0.
|
230 |
"step": 88
|
231 |
},
|
232 |
{
|
233 |
-
"epoch": 22.
|
234 |
-
"eval_accuracy": 0.
|
235 |
-
"eval_loss": 0.
|
236 |
-
"eval_runtime": 4.
|
237 |
-
"eval_samples_per_second": 15.
|
238 |
-
"eval_steps_per_second": 0.
|
239 |
"step": 92
|
240 |
},
|
241 |
{
|
242 |
-
"epoch": 23.
|
243 |
-
"eval_accuracy": 0.
|
244 |
-
"eval_loss": 0.
|
245 |
-
"eval_runtime": 4.
|
246 |
-
"eval_samples_per_second": 13.
|
247 |
-
"eval_steps_per_second": 0.
|
248 |
"step": 96
|
249 |
},
|
250 |
{
|
251 |
-
"epoch": 24.
|
252 |
"learning_rate": 3.240740740740741e-05,
|
253 |
-
"loss": 0.
|
254 |
"step": 100
|
255 |
},
|
256 |
{
|
257 |
-
"epoch": 24.
|
258 |
-
"eval_accuracy": 0.
|
259 |
-
"eval_loss": 0.
|
260 |
-
"eval_runtime": 4.
|
261 |
-
"eval_samples_per_second": 15.
|
262 |
-
"eval_steps_per_second": 0.
|
263 |
"step": 100
|
264 |
},
|
265 |
{
|
266 |
-
"epoch": 25.
|
267 |
-
"eval_accuracy": 0.
|
268 |
-
"eval_loss": 0.
|
269 |
-
"eval_runtime": 4.
|
270 |
-
"eval_samples_per_second":
|
271 |
-
"eval_steps_per_second": 0.
|
272 |
"step": 104
|
273 |
},
|
274 |
{
|
275 |
-
"epoch": 26.
|
276 |
-
"eval_accuracy": 0.
|
277 |
-
"eval_loss": 0.
|
278 |
-
"eval_runtime": 4.
|
279 |
-
"eval_samples_per_second":
|
280 |
-
"eval_steps_per_second": 0.
|
281 |
"step": 108
|
282 |
},
|
283 |
{
|
284 |
-
"epoch": 27.
|
285 |
-
"eval_accuracy": 0.
|
286 |
-
"eval_loss": 0.
|
287 |
-
"eval_runtime": 4.
|
288 |
-
"eval_samples_per_second":
|
289 |
-
"eval_steps_per_second": 0.
|
290 |
"step": 112
|
291 |
},
|
292 |
{
|
293 |
-
"epoch": 28.
|
294 |
-
"eval_accuracy": 0.
|
295 |
-
"eval_loss": 0.
|
296 |
-
"eval_runtime": 4.
|
297 |
-
"eval_samples_per_second": 15.
|
298 |
-
"eval_steps_per_second": 0.
|
299 |
"step": 116
|
300 |
},
|
301 |
{
|
302 |
-
"epoch": 29.
|
303 |
"learning_rate": 2.777777777777778e-05,
|
304 |
-
"loss": 0.
|
305 |
"step": 120
|
306 |
},
|
307 |
{
|
308 |
-
"epoch": 29.
|
309 |
-
"eval_accuracy": 0.
|
310 |
-
"eval_loss": 0.
|
311 |
-
"eval_runtime": 4.
|
312 |
-
"eval_samples_per_second":
|
313 |
-
"eval_steps_per_second": 0.
|
314 |
"step": 120
|
315 |
},
|
316 |
{
|
317 |
-
"epoch": 30.
|
318 |
-
"eval_accuracy": 0.
|
319 |
-
"eval_loss": 0.
|
320 |
-
"eval_runtime": 4.
|
321 |
-
"eval_samples_per_second": 15.
|
322 |
-
"eval_steps_per_second": 0.
|
323 |
"step": 124
|
324 |
},
|
325 |
{
|
326 |
-
"epoch": 31.
|
327 |
-
"eval_accuracy": 0.
|
328 |
-
"eval_loss": 0.
|
329 |
-
"eval_runtime": 4.
|
330 |
-
"eval_samples_per_second": 13.
|
331 |
-
"eval_steps_per_second": 0.
|
332 |
"step": 128
|
333 |
},
|
334 |
{
|
335 |
-
"epoch": 32.
|
336 |
-
"eval_accuracy": 0.
|
337 |
-
"eval_loss": 0.
|
338 |
-
"eval_runtime": 4.
|
339 |
-
"eval_samples_per_second": 15.
|
340 |
-
"eval_steps_per_second": 0.
|
341 |
"step": 132
|
342 |
},
|
343 |
{
|
344 |
-
"epoch": 33.
|
345 |
-
"eval_accuracy": 0.
|
346 |
-
"eval_loss": 0.
|
347 |
-
"eval_runtime": 4.
|
348 |
-
"eval_samples_per_second":
|
349 |
-
"eval_steps_per_second": 0.
|
350 |
"step": 136
|
351 |
},
|
352 |
{
|
353 |
-
"epoch": 34.
|
354 |
"learning_rate": 2.314814814814815e-05,
|
355 |
-
"loss": 0.
|
356 |
"step": 140
|
357 |
},
|
358 |
{
|
359 |
-
"epoch": 34.
|
360 |
-
"eval_accuracy": 0.
|
361 |
-
"eval_loss": 0.
|
362 |
-
"eval_runtime": 4.
|
363 |
-
"eval_samples_per_second":
|
364 |
-
"eval_steps_per_second": 0.
|
365 |
"step": 140
|
366 |
},
|
367 |
{
|
368 |
-
"epoch": 35.
|
369 |
-
"eval_accuracy": 0.
|
370 |
-
"eval_loss": 0.
|
371 |
-
"eval_runtime":
|
372 |
-
"eval_samples_per_second":
|
373 |
-
"eval_steps_per_second": 0.
|
374 |
"step": 144
|
375 |
},
|
376 |
{
|
377 |
-
"epoch": 36.
|
378 |
-
"eval_accuracy": 0.
|
379 |
-
"eval_loss": 0.
|
380 |
-
"eval_runtime": 4.
|
381 |
-
"eval_samples_per_second": 15.
|
382 |
-
"eval_steps_per_second": 0.
|
383 |
"step": 148
|
384 |
},
|
385 |
{
|
386 |
-
"epoch": 37.
|
387 |
-
"eval_accuracy": 0.
|
388 |
-
"eval_loss": 0.
|
389 |
-
"eval_runtime": 4.
|
390 |
-
"eval_samples_per_second":
|
391 |
-
"eval_steps_per_second": 0.
|
392 |
"step": 152
|
393 |
},
|
394 |
{
|
395 |
-
"epoch": 38.
|
396 |
-
"eval_accuracy": 0.
|
397 |
-
"eval_loss": 0.
|
398 |
-
"eval_runtime": 4.
|
399 |
-
"eval_samples_per_second":
|
400 |
-
"eval_steps_per_second": 0.
|
401 |
"step": 156
|
402 |
},
|
403 |
{
|
404 |
-
"epoch": 39.
|
405 |
"learning_rate": 1.8518518518518518e-05,
|
406 |
-
"loss": 0.
|
407 |
"step": 160
|
408 |
},
|
409 |
{
|
410 |
-
"epoch": 39.
|
411 |
-
"eval_accuracy": 0.
|
412 |
-
"eval_loss": 0.
|
413 |
-
"eval_runtime": 4.
|
414 |
-
"eval_samples_per_second": 13.
|
415 |
-
"eval_steps_per_second": 0.
|
416 |
"step": 160
|
417 |
},
|
418 |
{
|
419 |
-
"epoch": 40.
|
420 |
-
"eval_accuracy": 0.
|
421 |
-
"eval_loss": 0.
|
422 |
-
"eval_runtime": 4.
|
423 |
-
"eval_samples_per_second": 15.
|
424 |
-
"eval_steps_per_second": 0.
|
425 |
"step": 164
|
426 |
},
|
427 |
{
|
428 |
-
"epoch": 41.
|
429 |
-
"eval_accuracy": 0.
|
430 |
-
"eval_loss": 0.
|
431 |
-
"eval_runtime": 4.
|
432 |
-
"eval_samples_per_second": 13.
|
433 |
-
"eval_steps_per_second": 0.
|
434 |
"step": 168
|
435 |
},
|
436 |
{
|
437 |
-
"epoch": 42.
|
438 |
-
"eval_accuracy": 0.
|
439 |
-
"eval_loss": 0.
|
440 |
-
"eval_runtime": 4.
|
441 |
-
"eval_samples_per_second":
|
442 |
-
"eval_steps_per_second": 0.
|
443 |
"step": 172
|
444 |
},
|
445 |
{
|
446 |
-
"epoch": 43.
|
447 |
-
"eval_accuracy": 0.
|
448 |
-
"eval_loss": 0.
|
449 |
-
"eval_runtime": 4.
|
450 |
-
"eval_samples_per_second": 13.
|
451 |
-
"eval_steps_per_second": 0.
|
452 |
"step": 176
|
453 |
},
|
454 |
{
|
455 |
-
"epoch": 44.
|
456 |
"learning_rate": 1.388888888888889e-05,
|
457 |
-
"loss": 0.
|
458 |
"step": 180
|
459 |
},
|
460 |
{
|
461 |
-
"epoch": 44.
|
462 |
-
"eval_accuracy": 0.
|
463 |
-
"eval_loss": 0.
|
464 |
-
"eval_runtime": 4.
|
465 |
-
"eval_samples_per_second": 14.
|
466 |
-
"eval_steps_per_second": 0.
|
467 |
"step": 180
|
468 |
},
|
469 |
{
|
470 |
-
"epoch": 45.
|
471 |
-
"eval_accuracy": 0.
|
472 |
-
"eval_loss": 0.
|
473 |
-
"eval_runtime": 4.
|
474 |
-
"eval_samples_per_second":
|
475 |
-
"eval_steps_per_second": 0.
|
476 |
"step": 184
|
477 |
},
|
478 |
{
|
479 |
-
"epoch": 46.
|
480 |
-
"eval_accuracy": 0.
|
481 |
-
"eval_loss": 0.
|
482 |
-
"eval_runtime": 4.
|
483 |
-
"eval_samples_per_second":
|
484 |
-
"eval_steps_per_second": 0.
|
485 |
"step": 188
|
486 |
},
|
487 |
{
|
488 |
-
"epoch": 47.
|
489 |
-
"eval_accuracy": 0.
|
490 |
-
"eval_loss": 0.
|
491 |
-
"eval_runtime": 4.
|
492 |
-
"eval_samples_per_second": 13.
|
493 |
-
"eval_steps_per_second": 0.
|
494 |
"step": 192
|
495 |
},
|
496 |
{
|
497 |
-
"epoch": 48.
|
498 |
-
"eval_accuracy": 0.
|
499 |
-
"eval_loss": 0.
|
500 |
-
"eval_runtime": 4.
|
501 |
-
"eval_samples_per_second": 15.
|
502 |
-
"eval_steps_per_second": 0.
|
503 |
"step": 196
|
504 |
},
|
505 |
{
|
506 |
-
"epoch": 49.
|
507 |
"learning_rate": 9.259259259259259e-06,
|
508 |
-
"loss": 0.
|
509 |
"step": 200
|
510 |
},
|
511 |
{
|
512 |
-
"epoch": 49.
|
513 |
-
"eval_accuracy": 0.
|
514 |
-
"eval_loss": 0.
|
515 |
-
"eval_runtime": 4.
|
516 |
-
"eval_samples_per_second":
|
517 |
-
"eval_steps_per_second": 0.
|
518 |
"step": 200
|
519 |
},
|
520 |
{
|
521 |
-
"epoch": 50.
|
522 |
-
"eval_accuracy": 0.
|
523 |
-
"eval_loss": 0.
|
524 |
-
"eval_runtime": 4.
|
525 |
-
"eval_samples_per_second":
|
526 |
-
"eval_steps_per_second": 0.
|
527 |
"step": 204
|
528 |
},
|
529 |
{
|
530 |
-
"epoch": 51.
|
531 |
-
"eval_accuracy": 0.
|
532 |
-
"eval_loss": 0.
|
533 |
-
"eval_runtime": 4.
|
534 |
-
"eval_samples_per_second":
|
535 |
-
"eval_steps_per_second": 0.
|
536 |
"step": 208
|
537 |
},
|
538 |
{
|
539 |
-
"epoch": 52.
|
540 |
-
"eval_accuracy": 0.
|
541 |
-
"eval_loss": 0.
|
542 |
-
"eval_runtime": 4.
|
543 |
-
"eval_samples_per_second":
|
544 |
-
"eval_steps_per_second": 0.
|
545 |
"step": 212
|
546 |
},
|
547 |
{
|
548 |
-
"epoch": 53.
|
549 |
-
"eval_accuracy": 0.
|
550 |
-
"eval_loss": 0.
|
551 |
-
"eval_runtime": 4.
|
552 |
-
"eval_samples_per_second": 13.
|
553 |
-
"eval_steps_per_second": 0.
|
554 |
"step": 216
|
555 |
},
|
556 |
{
|
557 |
-
"epoch": 54.
|
558 |
"learning_rate": 4.6296296296296296e-06,
|
559 |
-
"loss": 0.
|
560 |
"step": 220
|
561 |
},
|
562 |
{
|
563 |
-
"epoch": 54.
|
564 |
-
"eval_accuracy": 0.
|
565 |
-
"eval_loss": 0.
|
566 |
-
"eval_runtime": 4.
|
567 |
-
"eval_samples_per_second": 15.
|
568 |
-
"eval_steps_per_second": 0.
|
569 |
"step": 220
|
570 |
},
|
571 |
{
|
572 |
-
"epoch": 55.
|
573 |
-
"eval_accuracy": 0.
|
574 |
-
"eval_loss": 0.
|
575 |
-
"eval_runtime": 4.
|
576 |
-
"eval_samples_per_second":
|
577 |
-
"eval_steps_per_second": 0.
|
578 |
"step": 224
|
579 |
},
|
580 |
{
|
581 |
-
"epoch": 56.
|
582 |
-
"eval_accuracy": 0.
|
583 |
-
"eval_loss": 0.
|
584 |
-
"eval_runtime": 4.
|
585 |
-
"eval_samples_per_second": 15.
|
586 |
-
"eval_steps_per_second": 0.
|
587 |
"step": 228
|
588 |
},
|
589 |
{
|
590 |
-
"epoch": 57.
|
591 |
-
"eval_accuracy": 0.
|
592 |
-
"eval_loss": 0.
|
593 |
-
"eval_runtime": 4.
|
594 |
-
"eval_samples_per_second":
|
595 |
-
"eval_steps_per_second": 0.
|
596 |
"step": 232
|
597 |
},
|
598 |
{
|
599 |
-
"epoch": 58.
|
600 |
-
"eval_accuracy": 0.
|
601 |
-
"eval_loss": 0.
|
602 |
-
"eval_runtime": 4.
|
603 |
-
"eval_samples_per_second":
|
604 |
-
"eval_steps_per_second": 0.
|
605 |
"step": 236
|
606 |
},
|
607 |
{
|
608 |
-
"epoch": 59.
|
609 |
"learning_rate": 0.0,
|
610 |
-
"loss": 0.
|
611 |
"step": 240
|
612 |
},
|
613 |
{
|
614 |
-
"epoch": 59.
|
615 |
-
"eval_accuracy": 0.
|
616 |
-
"eval_loss": 0.
|
617 |
-
"eval_runtime": 4.
|
618 |
-
"eval_samples_per_second": 13.
|
619 |
-
"eval_steps_per_second": 0.
|
620 |
"step": 240
|
621 |
},
|
622 |
{
|
623 |
-
"epoch": 59.
|
624 |
"step": 240,
|
625 |
-
"total_flos": 8.
|
626 |
-
"train_loss": 0.
|
627 |
-
"train_runtime":
|
628 |
-
"train_samples_per_second": 8.
|
629 |
"train_steps_per_second": 0.057
|
630 |
}
|
631 |
],
|
632 |
"max_steps": 240,
|
633 |
"num_train_epochs": 60,
|
634 |
-
"total_flos": 8.
|
635 |
"trial_name": null,
|
636 |
"trial_params": null
|
637 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9846153846153847,
|
3 |
+
"best_model_checkpoint": "delivery_truck_classification/checkpoint-104",
|
4 |
+
"epoch": 59.8421052631579,
|
5 |
"global_step": 240,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.84,
|
12 |
+
"eval_accuracy": 0.3230769230769231,
|
13 |
+
"eval_loss": 1.819914698600769,
|
14 |
+
"eval_runtime": 4.4893,
|
15 |
+
"eval_samples_per_second": 14.479,
|
16 |
+
"eval_steps_per_second": 0.668,
|
17 |
"step": 4
|
18 |
},
|
19 |
{
|
20 |
+
"epoch": 1.84,
|
21 |
+
"eval_accuracy": 0.4153846153846154,
|
22 |
+
"eval_loss": 1.7274595499038696,
|
23 |
+
"eval_runtime": 5.1038,
|
24 |
+
"eval_samples_per_second": 12.736,
|
25 |
+
"eval_steps_per_second": 0.588,
|
26 |
"step": 8
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 2.84,
|
30 |
+
"eval_accuracy": 0.46153846153846156,
|
31 |
+
"eval_loss": 1.628129005432129,
|
32 |
+
"eval_runtime": 4.4017,
|
33 |
+
"eval_samples_per_second": 14.767,
|
34 |
+
"eval_steps_per_second": 0.682,
|
35 |
"step": 12
|
36 |
},
|
37 |
{
|
38 |
+
"epoch": 3.84,
|
39 |
+
"eval_accuracy": 0.46153846153846156,
|
40 |
+
"eval_loss": 1.5271515846252441,
|
41 |
+
"eval_runtime": 4.7528,
|
42 |
+
"eval_samples_per_second": 13.676,
|
43 |
+
"eval_steps_per_second": 0.631,
|
44 |
"step": 16
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 4.84,
|
48 |
"learning_rate": 4.166666666666667e-05,
|
49 |
+
"loss": 1.9537,
|
50 |
"step": 20
|
51 |
},
|
52 |
{
|
53 |
+
"epoch": 4.84,
|
54 |
+
"eval_accuracy": 0.5076923076923077,
|
55 |
+
"eval_loss": 1.3667770624160767,
|
56 |
+
"eval_runtime": 4.3866,
|
57 |
+
"eval_samples_per_second": 14.818,
|
58 |
+
"eval_steps_per_second": 0.684,
|
59 |
"step": 20
|
60 |
},
|
61 |
{
|
62 |
+
"epoch": 5.84,
|
63 |
+
"eval_accuracy": 0.6,
|
64 |
+
"eval_loss": 1.0963521003723145,
|
65 |
+
"eval_runtime": 4.7064,
|
66 |
+
"eval_samples_per_second": 13.811,
|
67 |
+
"eval_steps_per_second": 0.637,
|
68 |
"step": 24
|
69 |
},
|
70 |
{
|
71 |
+
"epoch": 6.84,
|
72 |
+
"eval_accuracy": 0.7846153846153846,
|
73 |
+
"eval_loss": 0.7691364884376526,
|
74 |
+
"eval_runtime": 4.2153,
|
75 |
+
"eval_samples_per_second": 15.42,
|
76 |
+
"eval_steps_per_second": 0.712,
|
77 |
"step": 28
|
78 |
},
|
79 |
{
|
80 |
+
"epoch": 7.84,
|
81 |
+
"eval_accuracy": 0.8307692307692308,
|
82 |
+
"eval_loss": 0.6369762420654297,
|
83 |
+
"eval_runtime": 4.7258,
|
84 |
+
"eval_samples_per_second": 13.754,
|
85 |
+
"eval_steps_per_second": 0.635,
|
86 |
"step": 32
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 8.84,
|
90 |
+
"eval_accuracy": 0.9076923076923077,
|
91 |
+
"eval_loss": 0.4328678548336029,
|
92 |
+
"eval_runtime": 4.7157,
|
93 |
+
"eval_samples_per_second": 13.784,
|
94 |
+
"eval_steps_per_second": 0.636,
|
95 |
"step": 36
|
96 |
},
|
97 |
{
|
98 |
+
"epoch": 9.84,
|
99 |
"learning_rate": 4.62962962962963e-05,
|
100 |
+
"loss": 1.0682,
|
101 |
"step": 40
|
102 |
},
|
103 |
{
|
104 |
+
"epoch": 9.84,
|
105 |
+
"eval_accuracy": 0.9076923076923077,
|
106 |
+
"eval_loss": 0.3517535626888275,
|
107 |
+
"eval_runtime": 4.7127,
|
108 |
+
"eval_samples_per_second": 13.792,
|
109 |
+
"eval_steps_per_second": 0.637,
|
110 |
"step": 40
|
111 |
},
|
112 |
{
|
113 |
+
"epoch": 10.84,
|
114 |
+
"eval_accuracy": 0.8923076923076924,
|
115 |
+
"eval_loss": 0.3229323625564575,
|
116 |
+
"eval_runtime": 4.2434,
|
117 |
+
"eval_samples_per_second": 15.318,
|
118 |
+
"eval_steps_per_second": 0.707,
|
119 |
"step": 44
|
120 |
},
|
121 |
{
|
122 |
+
"epoch": 11.84,
|
123 |
+
"eval_accuracy": 0.9384615384615385,
|
124 |
+
"eval_loss": 0.2324085831642151,
|
125 |
+
"eval_runtime": 4.734,
|
126 |
+
"eval_samples_per_second": 13.731,
|
127 |
+
"eval_steps_per_second": 0.634,
|
128 |
"step": 48
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 12.84,
|
132 |
+
"eval_accuracy": 0.9384615384615385,
|
133 |
+
"eval_loss": 0.23686641454696655,
|
134 |
+
"eval_runtime": 4.3354,
|
135 |
+
"eval_samples_per_second": 14.993,
|
136 |
+
"eval_steps_per_second": 0.692,
|
137 |
"step": 52
|
138 |
},
|
139 |
{
|
140 |
+
"epoch": 13.84,
|
141 |
+
"eval_accuracy": 0.9384615384615385,
|
142 |
+
"eval_loss": 0.21190524101257324,
|
143 |
+
"eval_runtime": 4.793,
|
144 |
+
"eval_samples_per_second": 13.561,
|
145 |
+
"eval_steps_per_second": 0.626,
|
146 |
"step": 56
|
147 |
},
|
148 |
{
|
149 |
+
"epoch": 14.84,
|
150 |
"learning_rate": 4.166666666666667e-05,
|
151 |
+
"loss": 0.6335,
|
152 |
"step": 60
|
153 |
},
|
154 |
{
|
155 |
+
"epoch": 14.84,
|
156 |
+
"eval_accuracy": 0.9384615384615385,
|
157 |
+
"eval_loss": 0.18046662211418152,
|
158 |
+
"eval_runtime": 4.2602,
|
159 |
+
"eval_samples_per_second": 15.257,
|
160 |
+
"eval_steps_per_second": 0.704,
|
161 |
"step": 60
|
162 |
},
|
163 |
{
|
164 |
+
"epoch": 15.84,
|
165 |
+
"eval_accuracy": 0.9076923076923077,
|
166 |
+
"eval_loss": 0.21350829303264618,
|
167 |
+
"eval_runtime": 4.7427,
|
168 |
+
"eval_samples_per_second": 13.705,
|
169 |
+
"eval_steps_per_second": 0.633,
|
170 |
"step": 64
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 16.84,
|
174 |
+
"eval_accuracy": 0.9230769230769231,
|
175 |
+
"eval_loss": 0.1889328807592392,
|
176 |
+
"eval_runtime": 4.2616,
|
177 |
+
"eval_samples_per_second": 15.253,
|
178 |
+
"eval_steps_per_second": 0.704,
|
179 |
"step": 68
|
180 |
},
|
181 |
{
|
182 |
+
"epoch": 17.84,
|
183 |
+
"eval_accuracy": 0.9538461538461539,
|
184 |
+
"eval_loss": 0.16009008884429932,
|
185 |
+
"eval_runtime": 4.7629,
|
186 |
+
"eval_samples_per_second": 13.647,
|
187 |
+
"eval_steps_per_second": 0.63,
|
188 |
"step": 72
|
189 |
},
|
190 |
{
|
191 |
+
"epoch": 18.84,
|
192 |
+
"eval_accuracy": 0.9692307692307692,
|
193 |
+
"eval_loss": 0.14124387502670288,
|
194 |
+
"eval_runtime": 4.3251,
|
195 |
+
"eval_samples_per_second": 15.029,
|
196 |
+
"eval_steps_per_second": 0.694,
|
197 |
"step": 76
|
198 |
},
|
199 |
{
|
200 |
+
"epoch": 19.84,
|
201 |
"learning_rate": 3.7037037037037037e-05,
|
202 |
+
"loss": 0.5133,
|
203 |
"step": 80
|
204 |
},
|
205 |
{
|
206 |
+
"epoch": 19.84,
|
207 |
+
"eval_accuracy": 0.9538461538461539,
|
208 |
+
"eval_loss": 0.14968368411064148,
|
209 |
+
"eval_runtime": 4.7085,
|
210 |
+
"eval_samples_per_second": 13.805,
|
211 |
+
"eval_steps_per_second": 0.637,
|
212 |
"step": 80
|
213 |
},
|
214 |
{
|
215 |
+
"epoch": 20.84,
|
216 |
+
"eval_accuracy": 0.9538461538461539,
|
217 |
+
"eval_loss": 0.15449711680412292,
|
218 |
+
"eval_runtime": 4.2803,
|
219 |
+
"eval_samples_per_second": 15.186,
|
220 |
+
"eval_steps_per_second": 0.701,
|
221 |
"step": 84
|
222 |
},
|
223 |
{
|
224 |
+
"epoch": 21.84,
|
225 |
+
"eval_accuracy": 0.9538461538461539,
|
226 |
+
"eval_loss": 0.12975920736789703,
|
227 |
+
"eval_runtime": 6.2107,
|
228 |
+
"eval_samples_per_second": 10.466,
|
229 |
+
"eval_steps_per_second": 0.483,
|
230 |
"step": 88
|
231 |
},
|
232 |
{
|
233 |
+
"epoch": 22.84,
|
234 |
+
"eval_accuracy": 0.9538461538461539,
|
235 |
+
"eval_loss": 0.14153267443180084,
|
236 |
+
"eval_runtime": 4.2538,
|
237 |
+
"eval_samples_per_second": 15.28,
|
238 |
+
"eval_steps_per_second": 0.705,
|
239 |
"step": 92
|
240 |
},
|
241 |
{
|
242 |
+
"epoch": 23.84,
|
243 |
+
"eval_accuracy": 0.9230769230769231,
|
244 |
+
"eval_loss": 0.16845214366912842,
|
245 |
+
"eval_runtime": 4.6805,
|
246 |
+
"eval_samples_per_second": 13.888,
|
247 |
+
"eval_steps_per_second": 0.641,
|
248 |
"step": 96
|
249 |
},
|
250 |
{
|
251 |
+
"epoch": 24.84,
|
252 |
"learning_rate": 3.240740740740741e-05,
|
253 |
+
"loss": 0.4383,
|
254 |
"step": 100
|
255 |
},
|
256 |
{
|
257 |
+
"epoch": 24.84,
|
258 |
+
"eval_accuracy": 0.9384615384615385,
|
259 |
+
"eval_loss": 0.13808518648147583,
|
260 |
+
"eval_runtime": 4.2829,
|
261 |
+
"eval_samples_per_second": 15.177,
|
262 |
+
"eval_steps_per_second": 0.7,
|
263 |
"step": 100
|
264 |
},
|
265 |
{
|
266 |
+
"epoch": 25.84,
|
267 |
+
"eval_accuracy": 0.9846153846153847,
|
268 |
+
"eval_loss": 0.1295621246099472,
|
269 |
+
"eval_runtime": 4.717,
|
270 |
+
"eval_samples_per_second": 13.78,
|
271 |
+
"eval_steps_per_second": 0.636,
|
272 |
"step": 104
|
273 |
},
|
274 |
{
|
275 |
+
"epoch": 26.84,
|
276 |
+
"eval_accuracy": 0.9538461538461539,
|
277 |
+
"eval_loss": 0.1106828972697258,
|
278 |
+
"eval_runtime": 4.4246,
|
279 |
+
"eval_samples_per_second": 14.691,
|
280 |
+
"eval_steps_per_second": 0.678,
|
281 |
"step": 108
|
282 |
},
|
283 |
{
|
284 |
+
"epoch": 27.84,
|
285 |
+
"eval_accuracy": 0.9384615384615385,
|
286 |
+
"eval_loss": 0.12369797378778458,
|
287 |
+
"eval_runtime": 4.7653,
|
288 |
+
"eval_samples_per_second": 13.64,
|
289 |
+
"eval_steps_per_second": 0.63,
|
290 |
"step": 112
|
291 |
},
|
292 |
{
|
293 |
+
"epoch": 28.84,
|
294 |
+
"eval_accuracy": 0.9538461538461539,
|
295 |
+
"eval_loss": 0.1366400122642517,
|
296 |
+
"eval_runtime": 4.3203,
|
297 |
+
"eval_samples_per_second": 15.045,
|
298 |
+
"eval_steps_per_second": 0.694,
|
299 |
"step": 116
|
300 |
},
|
301 |
{
|
302 |
+
"epoch": 29.84,
|
303 |
"learning_rate": 2.777777777777778e-05,
|
304 |
+
"loss": 0.4149,
|
305 |
"step": 120
|
306 |
},
|
307 |
{
|
308 |
+
"epoch": 29.84,
|
309 |
+
"eval_accuracy": 0.9692307692307692,
|
310 |
+
"eval_loss": 0.13494354486465454,
|
311 |
+
"eval_runtime": 4.6686,
|
312 |
+
"eval_samples_per_second": 13.923,
|
313 |
+
"eval_steps_per_second": 0.643,
|
314 |
"step": 120
|
315 |
},
|
316 |
{
|
317 |
+
"epoch": 30.84,
|
318 |
+
"eval_accuracy": 0.9846153846153847,
|
319 |
+
"eval_loss": 0.10458508133888245,
|
320 |
+
"eval_runtime": 4.2843,
|
321 |
+
"eval_samples_per_second": 15.172,
|
322 |
+
"eval_steps_per_second": 0.7,
|
323 |
"step": 124
|
324 |
},
|
325 |
{
|
326 |
+
"epoch": 31.84,
|
327 |
+
"eval_accuracy": 0.9846153846153847,
|
328 |
+
"eval_loss": 0.0881725624203682,
|
329 |
+
"eval_runtime": 4.7053,
|
330 |
+
"eval_samples_per_second": 13.814,
|
331 |
+
"eval_steps_per_second": 0.638,
|
332 |
"step": 128
|
333 |
},
|
334 |
{
|
335 |
+
"epoch": 32.84,
|
336 |
+
"eval_accuracy": 0.9846153846153847,
|
337 |
+
"eval_loss": 0.10219049453735352,
|
338 |
+
"eval_runtime": 4.3211,
|
339 |
+
"eval_samples_per_second": 15.042,
|
340 |
+
"eval_steps_per_second": 0.694,
|
341 |
"step": 132
|
342 |
},
|
343 |
{
|
344 |
+
"epoch": 33.84,
|
345 |
+
"eval_accuracy": 0.9692307692307692,
|
346 |
+
"eval_loss": 0.12066025286912918,
|
347 |
+
"eval_runtime": 4.8023,
|
348 |
+
"eval_samples_per_second": 13.535,
|
349 |
+
"eval_steps_per_second": 0.625,
|
350 |
"step": 136
|
351 |
},
|
352 |
{
|
353 |
+
"epoch": 34.84,
|
354 |
"learning_rate": 2.314814814814815e-05,
|
355 |
+
"loss": 0.3657,
|
356 |
"step": 140
|
357 |
},
|
358 |
{
|
359 |
+
"epoch": 34.84,
|
360 |
+
"eval_accuracy": 0.9538461538461539,
|
361 |
+
"eval_loss": 0.11678420007228851,
|
362 |
+
"eval_runtime": 4.4027,
|
363 |
+
"eval_samples_per_second": 14.764,
|
364 |
+
"eval_steps_per_second": 0.681,
|
365 |
"step": 140
|
366 |
},
|
367 |
{
|
368 |
+
"epoch": 35.84,
|
369 |
+
"eval_accuracy": 0.9846153846153847,
|
370 |
+
"eval_loss": 0.09219826757907867,
|
371 |
+
"eval_runtime": 6.9593,
|
372 |
+
"eval_samples_per_second": 9.34,
|
373 |
+
"eval_steps_per_second": 0.431,
|
374 |
"step": 144
|
375 |
},
|
376 |
{
|
377 |
+
"epoch": 36.84,
|
378 |
+
"eval_accuracy": 0.9846153846153847,
|
379 |
+
"eval_loss": 0.09314019978046417,
|
380 |
+
"eval_runtime": 4.3,
|
381 |
+
"eval_samples_per_second": 15.116,
|
382 |
+
"eval_steps_per_second": 0.698,
|
383 |
"step": 148
|
384 |
},
|
385 |
{
|
386 |
+
"epoch": 37.84,
|
387 |
+
"eval_accuracy": 0.9692307692307692,
|
388 |
+
"eval_loss": 0.10055378824472427,
|
389 |
+
"eval_runtime": 4.7227,
|
390 |
+
"eval_samples_per_second": 13.763,
|
391 |
+
"eval_steps_per_second": 0.635,
|
392 |
"step": 152
|
393 |
},
|
394 |
{
|
395 |
+
"epoch": 38.84,
|
396 |
+
"eval_accuracy": 0.9692307692307692,
|
397 |
+
"eval_loss": 0.09866410493850708,
|
398 |
+
"eval_runtime": 4.3725,
|
399 |
+
"eval_samples_per_second": 14.866,
|
400 |
+
"eval_steps_per_second": 0.686,
|
401 |
"step": 156
|
402 |
},
|
403 |
{
|
404 |
+
"epoch": 39.84,
|
405 |
"learning_rate": 1.8518518518518518e-05,
|
406 |
+
"loss": 0.3294,
|
407 |
"step": 160
|
408 |
},
|
409 |
{
|
410 |
+
"epoch": 39.84,
|
411 |
+
"eval_accuracy": 0.9692307692307692,
|
412 |
+
"eval_loss": 0.11275947839021683,
|
413 |
+
"eval_runtime": 4.6903,
|
414 |
+
"eval_samples_per_second": 13.858,
|
415 |
+
"eval_steps_per_second": 0.64,
|
416 |
"step": 160
|
417 |
},
|
418 |
{
|
419 |
+
"epoch": 40.84,
|
420 |
+
"eval_accuracy": 0.9538461538461539,
|
421 |
+
"eval_loss": 0.11520560085773468,
|
422 |
+
"eval_runtime": 4.3303,
|
423 |
+
"eval_samples_per_second": 15.01,
|
424 |
+
"eval_steps_per_second": 0.693,
|
425 |
"step": 164
|
426 |
},
|
427 |
{
|
428 |
+
"epoch": 41.84,
|
429 |
+
"eval_accuracy": 0.9538461538461539,
|
430 |
+
"eval_loss": 0.09974207729101181,
|
431 |
+
"eval_runtime": 4.7259,
|
432 |
+
"eval_samples_per_second": 13.754,
|
433 |
+
"eval_steps_per_second": 0.635,
|
434 |
"step": 168
|
435 |
},
|
436 |
{
|
437 |
+
"epoch": 42.84,
|
438 |
+
"eval_accuracy": 0.9692307692307692,
|
439 |
+
"eval_loss": 0.09684933722019196,
|
440 |
+
"eval_runtime": 4.3525,
|
441 |
+
"eval_samples_per_second": 14.934,
|
442 |
+
"eval_steps_per_second": 0.689,
|
443 |
"step": 172
|
444 |
},
|
445 |
{
|
446 |
+
"epoch": 43.84,
|
447 |
+
"eval_accuracy": 0.9846153846153847,
|
448 |
+
"eval_loss": 0.08187751471996307,
|
449 |
+
"eval_runtime": 4.6538,
|
450 |
+
"eval_samples_per_second": 13.967,
|
451 |
+
"eval_steps_per_second": 0.645,
|
452 |
"step": 176
|
453 |
},
|
454 |
{
|
455 |
+
"epoch": 44.84,
|
456 |
"learning_rate": 1.388888888888889e-05,
|
457 |
+
"loss": 0.3198,
|
458 |
"step": 180
|
459 |
},
|
460 |
{
|
461 |
+
"epoch": 44.84,
|
462 |
+
"eval_accuracy": 0.9846153846153847,
|
463 |
+
"eval_loss": 0.07292691618204117,
|
464 |
+
"eval_runtime": 4.3483,
|
465 |
+
"eval_samples_per_second": 14.948,
|
466 |
+
"eval_steps_per_second": 0.69,
|
467 |
"step": 180
|
468 |
},
|
469 |
{
|
470 |
+
"epoch": 45.84,
|
471 |
+
"eval_accuracy": 0.9846153846153847,
|
472 |
+
"eval_loss": 0.07438476383686066,
|
473 |
+
"eval_runtime": 4.8323,
|
474 |
+
"eval_samples_per_second": 13.451,
|
475 |
+
"eval_steps_per_second": 0.621,
|
476 |
"step": 184
|
477 |
},
|
478 |
{
|
479 |
+
"epoch": 46.84,
|
480 |
+
"eval_accuracy": 0.9692307692307692,
|
481 |
+
"eval_loss": 0.09510225057601929,
|
482 |
+
"eval_runtime": 4.3498,
|
483 |
+
"eval_samples_per_second": 14.943,
|
484 |
+
"eval_steps_per_second": 0.69,
|
485 |
"step": 188
|
486 |
},
|
487 |
{
|
488 |
+
"epoch": 47.84,
|
489 |
+
"eval_accuracy": 0.9692307692307692,
|
490 |
+
"eval_loss": 0.09657642990350723,
|
491 |
+
"eval_runtime": 4.7293,
|
492 |
+
"eval_samples_per_second": 13.744,
|
493 |
+
"eval_steps_per_second": 0.634,
|
494 |
"step": 192
|
495 |
},
|
496 |
{
|
497 |
+
"epoch": 48.84,
|
498 |
+
"eval_accuracy": 0.9846153846153847,
|
499 |
+
"eval_loss": 0.08329986035823822,
|
500 |
+
"eval_runtime": 4.2989,
|
501 |
+
"eval_samples_per_second": 15.12,
|
502 |
+
"eval_steps_per_second": 0.698,
|
503 |
"step": 196
|
504 |
},
|
505 |
{
|
506 |
+
"epoch": 49.84,
|
507 |
"learning_rate": 9.259259259259259e-06,
|
508 |
+
"loss": 0.2936,
|
509 |
"step": 200
|
510 |
},
|
511 |
{
|
512 |
+
"epoch": 49.84,
|
513 |
+
"eval_accuracy": 0.9846153846153847,
|
514 |
+
"eval_loss": 0.06941184401512146,
|
515 |
+
"eval_runtime": 4.7066,
|
516 |
+
"eval_samples_per_second": 13.811,
|
517 |
+
"eval_steps_per_second": 0.637,
|
518 |
"step": 200
|
519 |
},
|
520 |
{
|
521 |
+
"epoch": 50.84,
|
522 |
+
"eval_accuracy": 0.9846153846153847,
|
523 |
+
"eval_loss": 0.06908843666315079,
|
524 |
+
"eval_runtime": 4.3338,
|
525 |
+
"eval_samples_per_second": 14.999,
|
526 |
+
"eval_steps_per_second": 0.692,
|
527 |
"step": 204
|
528 |
},
|
529 |
{
|
530 |
+
"epoch": 51.84,
|
531 |
+
"eval_accuracy": 0.9846153846153847,
|
532 |
+
"eval_loss": 0.0735919326543808,
|
533 |
+
"eval_runtime": 4.7155,
|
534 |
+
"eval_samples_per_second": 13.784,
|
535 |
+
"eval_steps_per_second": 0.636,
|
536 |
"step": 208
|
537 |
},
|
538 |
{
|
539 |
+
"epoch": 52.84,
|
540 |
+
"eval_accuracy": 0.9692307692307692,
|
541 |
+
"eval_loss": 0.08048100024461746,
|
542 |
+
"eval_runtime": 4.337,
|
543 |
+
"eval_samples_per_second": 14.987,
|
544 |
+
"eval_steps_per_second": 0.692,
|
545 |
"step": 212
|
546 |
},
|
547 |
{
|
548 |
+
"epoch": 53.84,
|
549 |
+
"eval_accuracy": 0.9846153846153847,
|
550 |
+
"eval_loss": 0.08007017523050308,
|
551 |
+
"eval_runtime": 4.765,
|
552 |
+
"eval_samples_per_second": 13.641,
|
553 |
+
"eval_steps_per_second": 0.63,
|
554 |
"step": 216
|
555 |
},
|
556 |
{
|
557 |
+
"epoch": 54.84,
|
558 |
"learning_rate": 4.6296296296296296e-06,
|
559 |
+
"loss": 0.3127,
|
560 |
"step": 220
|
561 |
},
|
562 |
{
|
563 |
+
"epoch": 54.84,
|
564 |
+
"eval_accuracy": 0.9846153846153847,
|
565 |
+
"eval_loss": 0.0826273187994957,
|
566 |
+
"eval_runtime": 4.2934,
|
567 |
+
"eval_samples_per_second": 15.139,
|
568 |
+
"eval_steps_per_second": 0.699,
|
569 |
"step": 220
|
570 |
},
|
571 |
{
|
572 |
+
"epoch": 55.84,
|
573 |
+
"eval_accuracy": 0.9692307692307692,
|
574 |
+
"eval_loss": 0.08565446734428406,
|
575 |
+
"eval_runtime": 4.7099,
|
576 |
+
"eval_samples_per_second": 13.801,
|
577 |
+
"eval_steps_per_second": 0.637,
|
578 |
"step": 224
|
579 |
},
|
580 |
{
|
581 |
+
"epoch": 56.84,
|
582 |
+
"eval_accuracy": 0.9846153846153847,
|
583 |
+
"eval_loss": 0.0864274650812149,
|
584 |
+
"eval_runtime": 4.246,
|
585 |
+
"eval_samples_per_second": 15.309,
|
586 |
+
"eval_steps_per_second": 0.707,
|
587 |
"step": 228
|
588 |
},
|
589 |
{
|
590 |
+
"epoch": 57.84,
|
591 |
+
"eval_accuracy": 0.9846153846153847,
|
592 |
+
"eval_loss": 0.08776658028364182,
|
593 |
+
"eval_runtime": 4.758,
|
594 |
+
"eval_samples_per_second": 13.661,
|
595 |
+
"eval_steps_per_second": 0.631,
|
596 |
"step": 232
|
597 |
},
|
598 |
{
|
599 |
+
"epoch": 58.84,
|
600 |
+
"eval_accuracy": 0.9846153846153847,
|
601 |
+
"eval_loss": 0.08772400766611099,
|
602 |
+
"eval_runtime": 4.2874,
|
603 |
+
"eval_samples_per_second": 15.161,
|
604 |
+
"eval_steps_per_second": 0.7,
|
605 |
"step": 236
|
606 |
},
|
607 |
{
|
608 |
+
"epoch": 59.84,
|
609 |
"learning_rate": 0.0,
|
610 |
+
"loss": 0.285,
|
611 |
"step": 240
|
612 |
},
|
613 |
{
|
614 |
+
"epoch": 59.84,
|
615 |
+
"eval_accuracy": 0.9846153846153847,
|
616 |
+
"eval_loss": 0.08735792338848114,
|
617 |
+
"eval_runtime": 4.7501,
|
618 |
+
"eval_samples_per_second": 13.684,
|
619 |
+
"eval_steps_per_second": 0.632,
|
620 |
"step": 240
|
621 |
},
|
622 |
{
|
623 |
+
"epoch": 59.84,
|
624 |
"step": 240,
|
625 |
+
"total_flos": 8.648855308501955e+17,
|
626 |
+
"train_loss": 0.577343902985255,
|
627 |
+
"train_runtime": 4213.9216,
|
628 |
+
"train_samples_per_second": 8.273,
|
629 |
"train_steps_per_second": 0.057
|
630 |
}
|
631 |
],
|
632 |
"max_steps": 240,
|
633 |
"num_train_epochs": 60,
|
634 |
+
"total_flos": 8.648855308501955e+17,
|
635 |
"trial_name": null,
|
636 |
"trial_params": null
|
637 |
}
|