JEdward7777
commited on
Commit
•
7fb93c7
1
Parent(s):
adcc6fe
End of training
Browse files- all_results.json +9 -9
- eval_results.json +4 -4
- runs/Oct24_13-49-06_8582a94b2abd/events.out.tfevents.1666621505.8582a94b2abd.75.2 +3 -0
- train_results.json +5 -5
- trainer_state.json +213 -213
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 39.86,
|
3 |
"eval_accuracy": 1.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 3.
|
6 |
-
"eval_samples_per_second": 14.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"total_flos": 4.
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 39.86,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.04471803084015846,
|
5 |
+
"eval_runtime": 3.4855,
|
6 |
+
"eval_samples_per_second": 14.058,
|
7 |
+
"eval_steps_per_second": 0.574,
|
8 |
+
"total_flos": 4.283662751949128e+17,
|
9 |
+
"train_loss": 0.5828357299168905,
|
10 |
+
"train_runtime": 1853.5405,
|
11 |
+
"train_samples_per_second": 9.323,
|
12 |
+
"train_steps_per_second": 0.065
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 39.86,
|
3 |
"eval_accuracy": 1.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 3.
|
6 |
-
"eval_samples_per_second": 14.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 39.86,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.04471803084015846,
|
5 |
+
"eval_runtime": 3.4855,
|
6 |
+
"eval_samples_per_second": 14.058,
|
7 |
+
"eval_steps_per_second": 0.574
|
8 |
}
|
runs/Oct24_13-49-06_8582a94b2abd/events.out.tfevents.1666621505.8582a94b2abd.75.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07926b9e10cd0c815963fb82432b5a6754568f45a6dde40b66527c0deffbeddc
|
3 |
+
size 357
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 39.86,
|
3 |
-
"total_flos": 4.
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 39.86,
|
3 |
+
"total_flos": 4.283662751949128e+17,
|
4 |
+
"train_loss": 0.5828357299168905,
|
5 |
+
"train_runtime": 1853.5405,
|
6 |
+
"train_samples_per_second": 9.323,
|
7 |
+
"train_steps_per_second": 0.065
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"best_metric": 1.0,
|
3 |
-
"best_model_checkpoint": "delivery_truck_classification/checkpoint-
|
4 |
"epoch": 39.857142857142854,
|
5 |
"global_step": 120,
|
6 |
"is_hyper_param_search": false,
|
@@ -9,413 +9,413 @@
|
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.86,
|
12 |
-
"eval_accuracy":
|
13 |
-
"eval_loss":
|
14 |
-
"eval_runtime": 3.
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second": 0.
|
17 |
"step": 3
|
18 |
},
|
19 |
{
|
20 |
"epoch": 1.86,
|
21 |
-
"eval_accuracy":
|
22 |
-
"eval_loss":
|
23 |
-
"eval_runtime": 3.
|
24 |
-
"eval_samples_per_second": 12.
|
25 |
-
"eval_steps_per_second": 0.
|
26 |
"step": 6
|
27 |
},
|
28 |
{
|
29 |
"epoch": 2.86,
|
30 |
-
"eval_accuracy": 0.
|
31 |
-
"eval_loss":
|
32 |
-
"eval_runtime": 3.
|
33 |
-
"eval_samples_per_second": 13.
|
34 |
-
"eval_steps_per_second": 0.
|
35 |
"step": 9
|
36 |
},
|
37 |
{
|
38 |
"epoch": 3.86,
|
39 |
-
"eval_accuracy":
|
40 |
-
"eval_loss":
|
41 |
-
"eval_runtime": 3.
|
42 |
-
"eval_samples_per_second":
|
43 |
-
"eval_steps_per_second": 0.
|
44 |
"step": 12
|
45 |
},
|
46 |
{
|
47 |
"epoch": 4.86,
|
48 |
-
"eval_accuracy": 0.
|
49 |
-
"eval_loss": 0.
|
50 |
-
"eval_runtime": 3.
|
51 |
-
"eval_samples_per_second":
|
52 |
-
"eval_steps_per_second": 0.
|
53 |
"step": 15
|
54 |
},
|
55 |
{
|
56 |
"epoch": 5.86,
|
57 |
-
"eval_accuracy": 0.
|
58 |
-
"eval_loss": 0.
|
59 |
-
"eval_runtime": 3.
|
60 |
-
"eval_samples_per_second": 13.
|
61 |
-
"eval_steps_per_second": 0.
|
62 |
"step": 18
|
63 |
},
|
64 |
{
|
65 |
"epoch": 6.57,
|
66 |
"learning_rate": 4.62962962962963e-05,
|
67 |
-
"loss":
|
68 |
"step": 20
|
69 |
},
|
70 |
{
|
71 |
"epoch": 6.86,
|
72 |
-
"eval_accuracy": 0.
|
73 |
-
"eval_loss": 0.
|
74 |
-
"eval_runtime": 3.
|
75 |
-
"eval_samples_per_second":
|
76 |
-
"eval_steps_per_second": 0.
|
77 |
"step": 21
|
78 |
},
|
79 |
{
|
80 |
"epoch": 7.86,
|
81 |
-
"eval_accuracy":
|
82 |
-
"eval_loss": 0.
|
83 |
-
"eval_runtime": 3.
|
84 |
-
"eval_samples_per_second":
|
85 |
-
"eval_steps_per_second": 0.
|
86 |
"step": 24
|
87 |
},
|
88 |
{
|
89 |
"epoch": 8.86,
|
90 |
-
"eval_accuracy": 0.
|
91 |
-
"eval_loss": 0.
|
92 |
-
"eval_runtime": 3.
|
93 |
-
"eval_samples_per_second":
|
94 |
-
"eval_steps_per_second": 0.
|
95 |
"step": 27
|
96 |
},
|
97 |
{
|
98 |
"epoch": 9.86,
|
99 |
-
"eval_accuracy": 0.
|
100 |
-
"eval_loss": 0.
|
101 |
-
"eval_runtime": 3.
|
102 |
-
"eval_samples_per_second":
|
103 |
-
"eval_steps_per_second": 0.
|
104 |
"step": 30
|
105 |
},
|
106 |
{
|
107 |
"epoch": 10.86,
|
108 |
-
"eval_accuracy": 0.
|
109 |
-
"eval_loss": 0.
|
110 |
-
"eval_runtime": 3.
|
111 |
-
"eval_samples_per_second": 13.
|
112 |
-
"eval_steps_per_second": 0.
|
113 |
"step": 33
|
114 |
},
|
115 |
{
|
116 |
"epoch": 11.86,
|
117 |
-
"eval_accuracy":
|
118 |
-
"eval_loss": 0.
|
119 |
-
"eval_runtime": 3.
|
120 |
-
"eval_samples_per_second":
|
121 |
-
"eval_steps_per_second": 0.
|
122 |
"step": 36
|
123 |
},
|
124 |
{
|
125 |
"epoch": 12.86,
|
126 |
-
"eval_accuracy":
|
127 |
-
"eval_loss": 0.
|
128 |
-
"eval_runtime": 3.
|
129 |
-
"eval_samples_per_second":
|
130 |
-
"eval_steps_per_second": 0.
|
131 |
"step": 39
|
132 |
},
|
133 |
{
|
134 |
"epoch": 13.29,
|
135 |
"learning_rate": 3.7037037037037037e-05,
|
136 |
-
"loss": 0.
|
137 |
"step": 40
|
138 |
},
|
139 |
{
|
140 |
"epoch": 13.86,
|
141 |
-
"eval_accuracy":
|
142 |
-
"eval_loss": 0.
|
143 |
-
"eval_runtime": 3.
|
144 |
-
"eval_samples_per_second": 13.
|
145 |
-
"eval_steps_per_second": 0.
|
146 |
"step": 42
|
147 |
},
|
148 |
{
|
149 |
"epoch": 14.86,
|
150 |
-
"eval_accuracy": 0.
|
151 |
-
"eval_loss": 0.
|
152 |
-
"eval_runtime": 3.
|
153 |
-
"eval_samples_per_second":
|
154 |
-
"eval_steps_per_second": 0.
|
155 |
"step": 45
|
156 |
},
|
157 |
{
|
158 |
"epoch": 15.86,
|
159 |
-
"eval_accuracy": 0.
|
160 |
-
"eval_loss": 0.
|
161 |
-
"eval_runtime": 3.
|
162 |
-
"eval_samples_per_second":
|
163 |
-
"eval_steps_per_second": 0.
|
164 |
"step": 48
|
165 |
},
|
166 |
{
|
167 |
"epoch": 16.86,
|
168 |
-
"eval_accuracy": 0.
|
169 |
-
"eval_loss": 0.
|
170 |
-
"eval_runtime": 3.
|
171 |
-
"eval_samples_per_second": 13.
|
172 |
-
"eval_steps_per_second": 0.
|
173 |
"step": 51
|
174 |
},
|
175 |
{
|
176 |
"epoch": 17.86,
|
177 |
-
"eval_accuracy": 0.
|
178 |
-
"eval_loss": 0.
|
179 |
-
"eval_runtime": 3.
|
180 |
-
"eval_samples_per_second": 13.
|
181 |
-
"eval_steps_per_second": 0.
|
182 |
"step": 54
|
183 |
},
|
184 |
{
|
185 |
"epoch": 18.86,
|
186 |
-
"eval_accuracy": 0.
|
187 |
-
"eval_loss": 0.
|
188 |
-
"eval_runtime": 3.
|
189 |
-
"eval_samples_per_second":
|
190 |
-
"eval_steps_per_second": 0.
|
191 |
"step": 57
|
192 |
},
|
193 |
{
|
194 |
"epoch": 19.86,
|
195 |
"learning_rate": 2.777777777777778e-05,
|
196 |
-
"loss": 0.
|
197 |
"step": 60
|
198 |
},
|
199 |
{
|
200 |
"epoch": 19.86,
|
201 |
-
"eval_accuracy": 0.
|
202 |
-
"eval_loss": 0.
|
203 |
-
"eval_runtime":
|
204 |
-
"eval_samples_per_second":
|
205 |
-
"eval_steps_per_second": 0.
|
206 |
"step": 60
|
207 |
},
|
208 |
{
|
209 |
"epoch": 20.86,
|
210 |
-
"eval_accuracy": 0.
|
211 |
-
"eval_loss": 0.
|
212 |
-
"eval_runtime": 3.
|
213 |
-
"eval_samples_per_second": 13.
|
214 |
-
"eval_steps_per_second": 0.
|
215 |
"step": 63
|
216 |
},
|
217 |
{
|
218 |
"epoch": 21.86,
|
219 |
-
"eval_accuracy": 0.
|
220 |
-
"eval_loss": 0.
|
221 |
-
"eval_runtime": 3.
|
222 |
-
"eval_samples_per_second": 14.
|
223 |
-
"eval_steps_per_second": 0.
|
224 |
"step": 66
|
225 |
},
|
226 |
{
|
227 |
"epoch": 22.86,
|
228 |
-
"eval_accuracy": 0.
|
229 |
-
"eval_loss": 0.
|
230 |
-
"eval_runtime": 3.
|
231 |
-
"eval_samples_per_second":
|
232 |
-
"eval_steps_per_second": 0.
|
233 |
"step": 69
|
234 |
},
|
235 |
{
|
236 |
"epoch": 23.86,
|
237 |
-
"eval_accuracy": 0.
|
238 |
-
"eval_loss": 0.
|
239 |
-
"eval_runtime": 3.
|
240 |
-
"eval_samples_per_second":
|
241 |
-
"eval_steps_per_second": 0.
|
242 |
"step": 72
|
243 |
},
|
244 |
{
|
245 |
"epoch": 24.86,
|
246 |
-
"eval_accuracy": 0.
|
247 |
-
"eval_loss": 0.
|
248 |
-
"eval_runtime": 3.
|
249 |
-
"eval_samples_per_second":
|
250 |
-
"eval_steps_per_second": 0.
|
251 |
"step": 75
|
252 |
},
|
253 |
{
|
254 |
"epoch": 25.86,
|
255 |
-
"eval_accuracy": 0.
|
256 |
-
"eval_loss": 0.
|
257 |
-
"eval_runtime": 3.
|
258 |
-
"eval_samples_per_second": 13.
|
259 |
-
"eval_steps_per_second": 0.
|
260 |
"step": 78
|
261 |
},
|
262 |
{
|
263 |
"epoch": 26.57,
|
264 |
"learning_rate": 1.8518518518518518e-05,
|
265 |
-
"loss": 0.
|
266 |
"step": 80
|
267 |
},
|
268 |
{
|
269 |
"epoch": 26.86,
|
270 |
-
"eval_accuracy": 0.
|
271 |
-
"eval_loss": 0.
|
272 |
-
"eval_runtime": 3.
|
273 |
-
"eval_samples_per_second":
|
274 |
-
"eval_steps_per_second": 0.
|
275 |
"step": 81
|
276 |
},
|
277 |
{
|
278 |
"epoch": 27.86,
|
279 |
-
"eval_accuracy": 0.
|
280 |
-
"eval_loss": 0.
|
281 |
-
"eval_runtime": 3.
|
282 |
-
"eval_samples_per_second":
|
283 |
-
"eval_steps_per_second": 0.
|
284 |
"step": 84
|
285 |
},
|
286 |
{
|
287 |
"epoch": 28.86,
|
288 |
-
"eval_accuracy": 0.
|
289 |
-
"eval_loss": 0.
|
290 |
-
"eval_runtime": 3.
|
291 |
-
"eval_samples_per_second": 13.
|
292 |
-
"eval_steps_per_second": 0.
|
293 |
"step": 87
|
294 |
},
|
295 |
{
|
296 |
"epoch": 29.86,
|
297 |
-
"eval_accuracy": 0.
|
298 |
-
"eval_loss": 0.
|
299 |
-
"eval_runtime": 3.
|
300 |
-
"eval_samples_per_second": 13.
|
301 |
-
"eval_steps_per_second": 0.
|
302 |
"step": 90
|
303 |
},
|
304 |
{
|
305 |
"epoch": 30.86,
|
306 |
-
"eval_accuracy": 0
|
307 |
-
"eval_loss": 0.
|
308 |
-
"eval_runtime": 3.
|
309 |
-
"eval_samples_per_second": 14.
|
310 |
-
"eval_steps_per_second": 0.
|
311 |
"step": 93
|
312 |
},
|
313 |
{
|
314 |
"epoch": 31.86,
|
315 |
-
"eval_accuracy": 0
|
316 |
-
"eval_loss": 0.
|
317 |
-
"eval_runtime": 3.
|
318 |
-
"eval_samples_per_second":
|
319 |
-
"eval_steps_per_second": 0.
|
320 |
"step": 96
|
321 |
},
|
322 |
{
|
323 |
"epoch": 32.86,
|
324 |
-
"eval_accuracy": 0
|
325 |
-
"eval_loss": 0.
|
326 |
-
"eval_runtime": 3.
|
327 |
-
"eval_samples_per_second": 13.
|
328 |
-
"eval_steps_per_second": 0.
|
329 |
"step": 99
|
330 |
},
|
331 |
{
|
332 |
"epoch": 33.29,
|
333 |
"learning_rate": 9.259259259259259e-06,
|
334 |
-
"loss": 0.
|
335 |
"step": 100
|
336 |
},
|
337 |
{
|
338 |
"epoch": 33.86,
|
339 |
-
"eval_accuracy": 0
|
340 |
-
"eval_loss": 0.
|
341 |
-
"eval_runtime": 3.
|
342 |
-
"eval_samples_per_second":
|
343 |
-
"eval_steps_per_second": 0.
|
344 |
"step": 102
|
345 |
},
|
346 |
{
|
347 |
"epoch": 34.86,
|
348 |
-
"eval_accuracy": 0
|
349 |
-
"eval_loss": 0.
|
350 |
-
"eval_runtime": 3.
|
351 |
-
"eval_samples_per_second":
|
352 |
-
"eval_steps_per_second": 0.
|
353 |
"step": 105
|
354 |
},
|
355 |
{
|
356 |
"epoch": 35.86,
|
357 |
-
"eval_accuracy": 0.
|
358 |
-
"eval_loss": 0.
|
359 |
-
"eval_runtime": 3.
|
360 |
-
"eval_samples_per_second":
|
361 |
-
"eval_steps_per_second": 0.
|
362 |
"step": 108
|
363 |
},
|
364 |
{
|
365 |
"epoch": 36.86,
|
366 |
-
"eval_accuracy": 0.
|
367 |
-
"eval_loss": 0.
|
368 |
-
"eval_runtime": 3.
|
369 |
-
"eval_samples_per_second":
|
370 |
-
"eval_steps_per_second": 0.
|
371 |
"step": 111
|
372 |
},
|
373 |
{
|
374 |
"epoch": 37.86,
|
375 |
-
"eval_accuracy": 0.
|
376 |
-
"eval_loss": 0.
|
377 |
-
"eval_runtime": 3.
|
378 |
-
"eval_samples_per_second": 13.
|
379 |
-
"eval_steps_per_second": 0.
|
380 |
"step": 114
|
381 |
},
|
382 |
{
|
383 |
"epoch": 38.86,
|
384 |
-
"eval_accuracy": 0.
|
385 |
-
"eval_loss": 0.
|
386 |
-
"eval_runtime": 3.
|
387 |
-
"eval_samples_per_second":
|
388 |
-
"eval_steps_per_second": 0.
|
389 |
"step": 117
|
390 |
},
|
391 |
{
|
392 |
"epoch": 39.86,
|
393 |
"learning_rate": 0.0,
|
394 |
-
"loss": 0.
|
395 |
"step": 120
|
396 |
},
|
397 |
{
|
398 |
"epoch": 39.86,
|
399 |
-
"eval_accuracy": 0.
|
400 |
-
"eval_loss": 0.
|
401 |
-
"eval_runtime": 3.
|
402 |
-
"eval_samples_per_second":
|
403 |
-
"eval_steps_per_second": 0.
|
404 |
"step": 120
|
405 |
},
|
406 |
{
|
407 |
"epoch": 39.86,
|
408 |
"step": 120,
|
409 |
-
"total_flos": 4.
|
410 |
-
"train_loss": 0.
|
411 |
-
"train_runtime":
|
412 |
-
"train_samples_per_second":
|
413 |
-
"train_steps_per_second": 0.
|
414 |
}
|
415 |
],
|
416 |
"max_steps": 120,
|
417 |
"num_train_epochs": 40,
|
418 |
-
"total_flos": 4.
|
419 |
"trial_name": null,
|
420 |
"trial_params": null
|
421 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.0,
|
3 |
+
"best_model_checkpoint": "delivery_truck_classification/checkpoint-93",
|
4 |
"epoch": 39.857142857142854,
|
5 |
"global_step": 120,
|
6 |
"is_hyper_param_search": false,
|
|
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.86,
|
12 |
+
"eval_accuracy": 0.22448979591836735,
|
13 |
+
"eval_loss": 1.7165862321853638,
|
14 |
+
"eval_runtime": 3.3593,
|
15 |
+
"eval_samples_per_second": 14.586,
|
16 |
+
"eval_steps_per_second": 0.595,
|
17 |
"step": 3
|
18 |
},
|
19 |
{
|
20 |
"epoch": 1.86,
|
21 |
+
"eval_accuracy": 0.40816326530612246,
|
22 |
+
"eval_loss": 1.5815682411193848,
|
23 |
+
"eval_runtime": 3.8537,
|
24 |
+
"eval_samples_per_second": 12.715,
|
25 |
+
"eval_steps_per_second": 0.519,
|
26 |
"step": 6
|
27 |
},
|
28 |
{
|
29 |
"epoch": 2.86,
|
30 |
+
"eval_accuracy": 0.5510204081632653,
|
31 |
+
"eval_loss": 1.4084097146987915,
|
32 |
+
"eval_runtime": 3.6101,
|
33 |
+
"eval_samples_per_second": 13.573,
|
34 |
+
"eval_steps_per_second": 0.554,
|
35 |
"step": 9
|
36 |
},
|
37 |
{
|
38 |
"epoch": 3.86,
|
39 |
+
"eval_accuracy": 0.6326530612244898,
|
40 |
+
"eval_loss": 1.1761205196380615,
|
41 |
+
"eval_runtime": 3.605,
|
42 |
+
"eval_samples_per_second": 13.592,
|
43 |
+
"eval_steps_per_second": 0.555,
|
44 |
"step": 12
|
45 |
},
|
46 |
{
|
47 |
"epoch": 4.86,
|
48 |
+
"eval_accuracy": 0.7346938775510204,
|
49 |
+
"eval_loss": 0.924461841583252,
|
50 |
+
"eval_runtime": 3.397,
|
51 |
+
"eval_samples_per_second": 14.424,
|
52 |
+
"eval_steps_per_second": 0.589,
|
53 |
"step": 15
|
54 |
},
|
55 |
{
|
56 |
"epoch": 5.86,
|
57 |
+
"eval_accuracy": 0.7959183673469388,
|
58 |
+
"eval_loss": 0.6986315250396729,
|
59 |
+
"eval_runtime": 3.6429,
|
60 |
+
"eval_samples_per_second": 13.451,
|
61 |
+
"eval_steps_per_second": 0.549,
|
62 |
"step": 18
|
63 |
},
|
64 |
{
|
65 |
"epoch": 6.57,
|
66 |
"learning_rate": 4.62962962962963e-05,
|
67 |
+
"loss": 1.608,
|
68 |
"step": 20
|
69 |
},
|
70 |
{
|
71 |
"epoch": 6.86,
|
72 |
+
"eval_accuracy": 0.8367346938775511,
|
73 |
+
"eval_loss": 0.5158075094223022,
|
74 |
+
"eval_runtime": 3.6761,
|
75 |
+
"eval_samples_per_second": 13.329,
|
76 |
+
"eval_steps_per_second": 0.544,
|
77 |
"step": 21
|
78 |
},
|
79 |
{
|
80 |
"epoch": 7.86,
|
81 |
+
"eval_accuracy": 0.8775510204081632,
|
82 |
+
"eval_loss": 0.37532907724380493,
|
83 |
+
"eval_runtime": 3.6821,
|
84 |
+
"eval_samples_per_second": 13.308,
|
85 |
+
"eval_steps_per_second": 0.543,
|
86 |
"step": 24
|
87 |
},
|
88 |
{
|
89 |
"epoch": 8.86,
|
90 |
+
"eval_accuracy": 0.8979591836734694,
|
91 |
+
"eval_loss": 0.30922260880470276,
|
92 |
+
"eval_runtime": 3.4322,
|
93 |
+
"eval_samples_per_second": 14.276,
|
94 |
+
"eval_steps_per_second": 0.583,
|
95 |
"step": 27
|
96 |
},
|
97 |
{
|
98 |
"epoch": 9.86,
|
99 |
+
"eval_accuracy": 0.9387755102040817,
|
100 |
+
"eval_loss": 0.2584000825881958,
|
101 |
+
"eval_runtime": 3.7632,
|
102 |
+
"eval_samples_per_second": 13.021,
|
103 |
+
"eval_steps_per_second": 0.531,
|
104 |
"step": 30
|
105 |
},
|
106 |
{
|
107 |
"epoch": 10.86,
|
108 |
+
"eval_accuracy": 0.9183673469387755,
|
109 |
+
"eval_loss": 0.2158631533384323,
|
110 |
+
"eval_runtime": 3.7248,
|
111 |
+
"eval_samples_per_second": 13.155,
|
112 |
+
"eval_steps_per_second": 0.537,
|
113 |
"step": 33
|
114 |
},
|
115 |
{
|
116 |
"epoch": 11.86,
|
117 |
+
"eval_accuracy": 0.9591836734693877,
|
118 |
+
"eval_loss": 0.19079165160655975,
|
119 |
+
"eval_runtime": 3.4555,
|
120 |
+
"eval_samples_per_second": 14.18,
|
121 |
+
"eval_steps_per_second": 0.579,
|
122 |
"step": 36
|
123 |
},
|
124 |
{
|
125 |
"epoch": 12.86,
|
126 |
+
"eval_accuracy": 0.9591836734693877,
|
127 |
+
"eval_loss": 0.1801912933588028,
|
128 |
+
"eval_runtime": 3.6849,
|
129 |
+
"eval_samples_per_second": 13.298,
|
130 |
+
"eval_steps_per_second": 0.543,
|
131 |
"step": 39
|
132 |
},
|
133 |
{
|
134 |
"epoch": 13.29,
|
135 |
"learning_rate": 3.7037037037037037e-05,
|
136 |
+
"loss": 0.6473,
|
137 |
"step": 40
|
138 |
},
|
139 |
{
|
140 |
"epoch": 13.86,
|
141 |
+
"eval_accuracy": 0.9591836734693877,
|
142 |
+
"eval_loss": 0.16818924248218536,
|
143 |
+
"eval_runtime": 3.6554,
|
144 |
+
"eval_samples_per_second": 13.405,
|
145 |
+
"eval_steps_per_second": 0.547,
|
146 |
"step": 42
|
147 |
},
|
148 |
{
|
149 |
"epoch": 14.86,
|
150 |
+
"eval_accuracy": 0.9591836734693877,
|
151 |
+
"eval_loss": 0.15600401163101196,
|
152 |
+
"eval_runtime": 3.4217,
|
153 |
+
"eval_samples_per_second": 14.32,
|
154 |
+
"eval_steps_per_second": 0.585,
|
155 |
"step": 45
|
156 |
},
|
157 |
{
|
158 |
"epoch": 15.86,
|
159 |
+
"eval_accuracy": 0.9591836734693877,
|
160 |
+
"eval_loss": 0.13216617703437805,
|
161 |
+
"eval_runtime": 3.736,
|
162 |
+
"eval_samples_per_second": 13.116,
|
163 |
+
"eval_steps_per_second": 0.535,
|
164 |
"step": 48
|
165 |
},
|
166 |
{
|
167 |
"epoch": 16.86,
|
168 |
+
"eval_accuracy": 0.9591836734693877,
|
169 |
+
"eval_loss": 0.11014676839113235,
|
170 |
+
"eval_runtime": 3.6145,
|
171 |
+
"eval_samples_per_second": 13.557,
|
172 |
+
"eval_steps_per_second": 0.553,
|
173 |
"step": 51
|
174 |
},
|
175 |
{
|
176 |
"epoch": 17.86,
|
177 |
+
"eval_accuracy": 0.9591836734693877,
|
178 |
+
"eval_loss": 0.0938219353556633,
|
179 |
+
"eval_runtime": 3.6148,
|
180 |
+
"eval_samples_per_second": 13.555,
|
181 |
+
"eval_steps_per_second": 0.553,
|
182 |
"step": 54
|
183 |
},
|
184 |
{
|
185 |
"epoch": 18.86,
|
186 |
+
"eval_accuracy": 0.9795918367346939,
|
187 |
+
"eval_loss": 0.08886948227882385,
|
188 |
+
"eval_runtime": 3.3763,
|
189 |
+
"eval_samples_per_second": 14.513,
|
190 |
+
"eval_steps_per_second": 0.592,
|
191 |
"step": 57
|
192 |
},
|
193 |
{
|
194 |
"epoch": 19.86,
|
195 |
"learning_rate": 2.777777777777778e-05,
|
196 |
+
"loss": 0.3855,
|
197 |
"step": 60
|
198 |
},
|
199 |
{
|
200 |
"epoch": 19.86,
|
201 |
+
"eval_accuracy": 0.9795918367346939,
|
202 |
+
"eval_loss": 0.10251900553703308,
|
203 |
+
"eval_runtime": 3.6959,
|
204 |
+
"eval_samples_per_second": 13.258,
|
205 |
+
"eval_steps_per_second": 0.541,
|
206 |
"step": 60
|
207 |
},
|
208 |
{
|
209 |
"epoch": 20.86,
|
210 |
+
"eval_accuracy": 0.9795918367346939,
|
211 |
+
"eval_loss": 0.09841162711381912,
|
212 |
+
"eval_runtime": 3.6698,
|
213 |
+
"eval_samples_per_second": 13.352,
|
214 |
+
"eval_steps_per_second": 0.545,
|
215 |
"step": 63
|
216 |
},
|
217 |
{
|
218 |
"epoch": 21.86,
|
219 |
+
"eval_accuracy": 0.9591836734693877,
|
220 |
+
"eval_loss": 0.08669053018093109,
|
221 |
+
"eval_runtime": 3.4251,
|
222 |
+
"eval_samples_per_second": 14.306,
|
223 |
+
"eval_steps_per_second": 0.584,
|
224 |
"step": 66
|
225 |
},
|
226 |
{
|
227 |
"epoch": 22.86,
|
228 |
+
"eval_accuracy": 0.9591836734693877,
|
229 |
+
"eval_loss": 0.08126597851514816,
|
230 |
+
"eval_runtime": 3.4044,
|
231 |
+
"eval_samples_per_second": 14.393,
|
232 |
+
"eval_steps_per_second": 0.587,
|
233 |
"step": 69
|
234 |
},
|
235 |
{
|
236 |
"epoch": 23.86,
|
237 |
+
"eval_accuracy": 0.9591836734693877,
|
238 |
+
"eval_loss": 0.07681093364953995,
|
239 |
+
"eval_runtime": 3.6377,
|
240 |
+
"eval_samples_per_second": 13.47,
|
241 |
+
"eval_steps_per_second": 0.55,
|
242 |
"step": 72
|
243 |
},
|
244 |
{
|
245 |
"epoch": 24.86,
|
246 |
+
"eval_accuracy": 0.9795918367346939,
|
247 |
+
"eval_loss": 0.07339165359735489,
|
248 |
+
"eval_runtime": 3.6437,
|
249 |
+
"eval_samples_per_second": 13.448,
|
250 |
+
"eval_steps_per_second": 0.549,
|
251 |
"step": 75
|
252 |
},
|
253 |
{
|
254 |
"epoch": 25.86,
|
255 |
+
"eval_accuracy": 0.9795918367346939,
|
256 |
+
"eval_loss": 0.0697600468993187,
|
257 |
+
"eval_runtime": 3.6092,
|
258 |
+
"eval_samples_per_second": 13.577,
|
259 |
+
"eval_steps_per_second": 0.554,
|
260 |
"step": 78
|
261 |
},
|
262 |
{
|
263 |
"epoch": 26.57,
|
264 |
"learning_rate": 1.8518518518518518e-05,
|
265 |
+
"loss": 0.306,
|
266 |
"step": 80
|
267 |
},
|
268 |
{
|
269 |
"epoch": 26.86,
|
270 |
+
"eval_accuracy": 0.9591836734693877,
|
271 |
+
"eval_loss": 0.061838988214731216,
|
272 |
+
"eval_runtime": 3.3297,
|
273 |
+
"eval_samples_per_second": 14.716,
|
274 |
+
"eval_steps_per_second": 0.601,
|
275 |
"step": 81
|
276 |
},
|
277 |
{
|
278 |
"epoch": 27.86,
|
279 |
+
"eval_accuracy": 0.9795918367346939,
|
280 |
+
"eval_loss": 0.05467281490564346,
|
281 |
+
"eval_runtime": 3.6132,
|
282 |
+
"eval_samples_per_second": 13.562,
|
283 |
+
"eval_steps_per_second": 0.554,
|
284 |
"step": 84
|
285 |
},
|
286 |
{
|
287 |
"epoch": 28.86,
|
288 |
+
"eval_accuracy": 0.9591836734693877,
|
289 |
+
"eval_loss": 0.053797200322151184,
|
290 |
+
"eval_runtime": 3.6286,
|
291 |
+
"eval_samples_per_second": 13.504,
|
292 |
+
"eval_steps_per_second": 0.551,
|
293 |
"step": 87
|
294 |
},
|
295 |
{
|
296 |
"epoch": 29.86,
|
297 |
+
"eval_accuracy": 0.9795918367346939,
|
298 |
+
"eval_loss": 0.048745423555374146,
|
299 |
+
"eval_runtime": 3.5673,
|
300 |
+
"eval_samples_per_second": 13.736,
|
301 |
+
"eval_steps_per_second": 0.561,
|
302 |
"step": 90
|
303 |
},
|
304 |
{
|
305 |
"epoch": 30.86,
|
306 |
+
"eval_accuracy": 1.0,
|
307 |
+
"eval_loss": 0.04471803084015846,
|
308 |
+
"eval_runtime": 3.3732,
|
309 |
+
"eval_samples_per_second": 14.526,
|
310 |
+
"eval_steps_per_second": 0.593,
|
311 |
"step": 93
|
312 |
},
|
313 |
{
|
314 |
"epoch": 31.86,
|
315 |
+
"eval_accuracy": 1.0,
|
316 |
+
"eval_loss": 0.04248499870300293,
|
317 |
+
"eval_runtime": 3.634,
|
318 |
+
"eval_samples_per_second": 13.484,
|
319 |
+
"eval_steps_per_second": 0.55,
|
320 |
"step": 96
|
321 |
},
|
322 |
{
|
323 |
"epoch": 32.86,
|
324 |
+
"eval_accuracy": 1.0,
|
325 |
+
"eval_loss": 0.04510816931724548,
|
326 |
+
"eval_runtime": 3.5707,
|
327 |
+
"eval_samples_per_second": 13.723,
|
328 |
+
"eval_steps_per_second": 0.56,
|
329 |
"step": 99
|
330 |
},
|
331 |
{
|
332 |
"epoch": 33.29,
|
333 |
"learning_rate": 9.259259259259259e-06,
|
334 |
+
"loss": 0.2966,
|
335 |
"step": 100
|
336 |
},
|
337 |
{
|
338 |
"epoch": 33.86,
|
339 |
+
"eval_accuracy": 1.0,
|
340 |
+
"eval_loss": 0.04972054436802864,
|
341 |
+
"eval_runtime": 3.5902,
|
342 |
+
"eval_samples_per_second": 13.648,
|
343 |
+
"eval_steps_per_second": 0.557,
|
344 |
"step": 102
|
345 |
},
|
346 |
{
|
347 |
"epoch": 34.86,
|
348 |
+
"eval_accuracy": 1.0,
|
349 |
+
"eval_loss": 0.05577036738395691,
|
350 |
+
"eval_runtime": 3.3881,
|
351 |
+
"eval_samples_per_second": 14.462,
|
352 |
+
"eval_steps_per_second": 0.59,
|
353 |
"step": 105
|
354 |
},
|
355 |
{
|
356 |
"epoch": 35.86,
|
357 |
+
"eval_accuracy": 0.9795918367346939,
|
358 |
+
"eval_loss": 0.05818271264433861,
|
359 |
+
"eval_runtime": 3.6322,
|
360 |
+
"eval_samples_per_second": 13.491,
|
361 |
+
"eval_steps_per_second": 0.551,
|
362 |
"step": 108
|
363 |
},
|
364 |
{
|
365 |
"epoch": 36.86,
|
366 |
+
"eval_accuracy": 0.9591836734693877,
|
367 |
+
"eval_loss": 0.061642248183488846,
|
368 |
+
"eval_runtime": 3.5883,
|
369 |
+
"eval_samples_per_second": 13.655,
|
370 |
+
"eval_steps_per_second": 0.557,
|
371 |
"step": 111
|
372 |
},
|
373 |
{
|
374 |
"epoch": 37.86,
|
375 |
+
"eval_accuracy": 0.9591836734693877,
|
376 |
+
"eval_loss": 0.06565477699041367,
|
377 |
+
"eval_runtime": 3.6509,
|
378 |
+
"eval_samples_per_second": 13.421,
|
379 |
+
"eval_steps_per_second": 0.548,
|
380 |
"step": 114
|
381 |
},
|
382 |
{
|
383 |
"epoch": 38.86,
|
384 |
+
"eval_accuracy": 0.9591836734693877,
|
385 |
+
"eval_loss": 0.067948117852211,
|
386 |
+
"eval_runtime": 3.3455,
|
387 |
+
"eval_samples_per_second": 14.647,
|
388 |
+
"eval_steps_per_second": 0.598,
|
389 |
"step": 117
|
390 |
},
|
391 |
{
|
392 |
"epoch": 39.86,
|
393 |
"learning_rate": 0.0,
|
394 |
+
"loss": 0.2535,
|
395 |
"step": 120
|
396 |
},
|
397 |
{
|
398 |
"epoch": 39.86,
|
399 |
+
"eval_accuracy": 0.9591836734693877,
|
400 |
+
"eval_loss": 0.06835878640413284,
|
401 |
+
"eval_runtime": 3.6892,
|
402 |
+
"eval_samples_per_second": 13.282,
|
403 |
+
"eval_steps_per_second": 0.542,
|
404 |
"step": 120
|
405 |
},
|
406 |
{
|
407 |
"epoch": 39.86,
|
408 |
"step": 120,
|
409 |
+
"total_flos": 4.283662751949128e+17,
|
410 |
+
"train_loss": 0.5828357299168905,
|
411 |
+
"train_runtime": 1853.5405,
|
412 |
+
"train_samples_per_second": 9.323,
|
413 |
+
"train_steps_per_second": 0.065
|
414 |
}
|
415 |
],
|
416 |
"max_steps": 120,
|
417 |
"num_train_epochs": 40,
|
418 |
+
"total_flos": 4.283662751949128e+17,
|
419 |
"trial_name": null,
|
420 |
"trial_params": null
|
421 |
}
|