JEdward7777
commited on
Commit
·
4fb1ae9
1
Parent(s):
c9ce9e9
End of training
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +258 -258
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch": 39.
|
3 |
-
"eval_accuracy": 0
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"total_flos": 3.
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second": 1.
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 39.73,
|
3 |
+
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.0415542908012867,
|
5 |
+
"eval_runtime": 7.8769,
|
6 |
+
"eval_samples_per_second": 4.697,
|
7 |
+
"eval_steps_per_second": 0.254,
|
8 |
+
"total_flos": 3.262961773565706e+17,
|
9 |
+
"train_loss": 0.18748833239078522,
|
10 |
+
"train_runtime": 7500.5041,
|
11 |
+
"train_samples_per_second": 1.76,
|
12 |
+
"train_steps_per_second": 0.011
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 39.
|
3 |
-
"eval_accuracy": 0
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 39.73,
|
3 |
+
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.0415542908012867,
|
5 |
+
"eval_runtime": 7.8769,
|
6 |
+
"eval_samples_per_second": 4.697,
|
7 |
+
"eval_steps_per_second": 0.254
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 39.
|
3 |
-
"total_flos": 3.
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 1.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 39.73,
|
3 |
+
"total_flos": 3.262961773565706e+17,
|
4 |
+
"train_loss": 0.18748833239078522,
|
5 |
+
"train_runtime": 7500.5041,
|
6 |
+
"train_samples_per_second": 1.76,
|
7 |
+
"train_steps_per_second": 0.011
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,409 +1,409 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0
|
3 |
-
"best_model_checkpoint": "delivery_truck_classification\\checkpoint-
|
4 |
-
"epoch": 39.
|
5 |
"global_step": 80,
|
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": 0.
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second": 0.
|
17 |
"step": 2
|
18 |
},
|
19 |
{
|
20 |
-
"epoch": 1.
|
21 |
-
"eval_accuracy": 0
|
22 |
-
"eval_loss": 0.
|
23 |
-
"eval_runtime":
|
24 |
-
"eval_samples_per_second":
|
25 |
-
"eval_steps_per_second": 0.
|
26 |
"step": 4
|
27 |
},
|
28 |
{
|
29 |
-
"epoch": 2.
|
30 |
-
"eval_accuracy": 0
|
31 |
-
"eval_loss": 0.
|
32 |
-
"eval_runtime":
|
33 |
-
"eval_samples_per_second":
|
34 |
-
"eval_steps_per_second": 0.
|
35 |
"step": 6
|
36 |
},
|
37 |
{
|
38 |
-
"epoch": 3.
|
39 |
-
"eval_accuracy": 0
|
40 |
-
"eval_loss": 0.
|
41 |
-
"eval_runtime":
|
42 |
-
"eval_samples_per_second": 4.
|
43 |
-
"eval_steps_per_second": 0.
|
44 |
"step": 8
|
45 |
},
|
46 |
{
|
47 |
-
"epoch": 4.
|
48 |
-
"eval_accuracy": 0
|
49 |
-
"eval_loss": 0.
|
50 |
-
"eval_runtime":
|
51 |
-
"eval_samples_per_second":
|
52 |
-
"eval_steps_per_second": 0.
|
53 |
"step": 10
|
54 |
},
|
55 |
{
|
56 |
-
"epoch": 5.
|
57 |
-
"eval_accuracy": 0.
|
58 |
-
"eval_loss": 0.
|
59 |
-
"eval_runtime":
|
60 |
-
"eval_samples_per_second":
|
61 |
-
"eval_steps_per_second": 0.
|
62 |
"step": 12
|
63 |
},
|
64 |
{
|
65 |
-
"epoch": 6.
|
66 |
-
"eval_accuracy": 0
|
67 |
-
"eval_loss": 0.
|
68 |
-
"eval_runtime":
|
69 |
-
"eval_samples_per_second":
|
70 |
-
"eval_steps_per_second": 0.
|
71 |
"step": 14
|
72 |
},
|
73 |
{
|
74 |
-
"epoch": 7.
|
75 |
-
"eval_accuracy": 0
|
76 |
-
"eval_loss": 0.
|
77 |
-
"eval_runtime":
|
78 |
-
"eval_samples_per_second":
|
79 |
-
"eval_steps_per_second": 0.
|
80 |
"step": 16
|
81 |
},
|
82 |
{
|
83 |
-
"epoch": 8.
|
84 |
-
"eval_accuracy": 0
|
85 |
-
"eval_loss": 0.
|
86 |
-
"eval_runtime":
|
87 |
-
"eval_samples_per_second":
|
88 |
-
"eval_steps_per_second": 0.
|
89 |
"step": 18
|
90 |
},
|
91 |
{
|
92 |
-
"epoch": 9.
|
93 |
"learning_rate": 4.166666666666667e-05,
|
94 |
-
"loss": 0.
|
95 |
"step": 20
|
96 |
},
|
97 |
{
|
98 |
-
"epoch": 9.
|
99 |
-
"eval_accuracy": 0
|
100 |
-
"eval_loss": 0.
|
101 |
-
"eval_runtime":
|
102 |
-
"eval_samples_per_second":
|
103 |
-
"eval_steps_per_second": 0.
|
104 |
"step": 20
|
105 |
},
|
106 |
{
|
107 |
-
"epoch": 10.
|
108 |
-
"eval_accuracy": 0
|
109 |
-
"eval_loss": 0.
|
110 |
-
"eval_runtime":
|
111 |
-
"eval_samples_per_second": 4.
|
112 |
-
"eval_steps_per_second": 0.
|
113 |
"step": 22
|
114 |
},
|
115 |
{
|
116 |
-
"epoch": 11.
|
117 |
-
"eval_accuracy": 0.
|
118 |
-
"eval_loss": 0.
|
119 |
-
"eval_runtime":
|
120 |
-
"eval_samples_per_second": 4.
|
121 |
-
"eval_steps_per_second": 0.
|
122 |
"step": 24
|
123 |
},
|
124 |
{
|
125 |
-
"epoch": 12.
|
126 |
-
"eval_accuracy": 0.
|
127 |
-
"eval_loss": 0.
|
128 |
-
"eval_runtime":
|
129 |
-
"eval_samples_per_second":
|
130 |
-
"eval_steps_per_second": 0.
|
131 |
"step": 26
|
132 |
},
|
133 |
{
|
134 |
-
"epoch": 13.
|
135 |
-
"eval_accuracy": 0
|
136 |
-
"eval_loss": 0.
|
137 |
-
"eval_runtime":
|
138 |
-
"eval_samples_per_second":
|
139 |
-
"eval_steps_per_second": 0.
|
140 |
"step": 28
|
141 |
},
|
142 |
{
|
143 |
-
"epoch": 14.
|
144 |
-
"eval_accuracy": 0
|
145 |
-
"eval_loss": 0.
|
146 |
-
"eval_runtime":
|
147 |
-
"eval_samples_per_second":
|
148 |
-
"eval_steps_per_second": 0.
|
149 |
"step": 30
|
150 |
},
|
151 |
{
|
152 |
-
"epoch": 15.
|
153 |
-
"eval_accuracy": 0
|
154 |
-
"eval_loss": 0.
|
155 |
-
"eval_runtime": 7.
|
156 |
-
"eval_samples_per_second":
|
157 |
-
"eval_steps_per_second": 0.
|
158 |
"step": 32
|
159 |
},
|
160 |
{
|
161 |
-
"epoch": 16.
|
162 |
-
"eval_accuracy": 0
|
163 |
-
"eval_loss": 0.
|
164 |
-
"eval_runtime":
|
165 |
-
"eval_samples_per_second":
|
166 |
-
"eval_steps_per_second": 0.
|
167 |
"step": 34
|
168 |
},
|
169 |
{
|
170 |
-
"epoch": 17.
|
171 |
-
"eval_accuracy": 0.
|
172 |
-
"eval_loss": 0.
|
173 |
-
"eval_runtime":
|
174 |
-
"eval_samples_per_second":
|
175 |
-
"eval_steps_per_second": 0.
|
176 |
"step": 36
|
177 |
},
|
178 |
{
|
179 |
-
"epoch": 18.
|
180 |
-
"eval_accuracy": 0.
|
181 |
-
"eval_loss": 0.
|
182 |
-
"eval_runtime": 7.
|
183 |
-
"eval_samples_per_second": 4.
|
184 |
-
"eval_steps_per_second": 0.
|
185 |
"step": 38
|
186 |
},
|
187 |
{
|
188 |
-
"epoch": 19.
|
189 |
"learning_rate": 2.777777777777778e-05,
|
190 |
-
"loss": 0.
|
191 |
"step": 40
|
192 |
},
|
193 |
{
|
194 |
-
"epoch": 19.
|
195 |
-
"eval_accuracy": 0.
|
196 |
-
"eval_loss": 0.
|
197 |
-
"eval_runtime":
|
198 |
-
"eval_samples_per_second":
|
199 |
-
"eval_steps_per_second": 0.
|
200 |
"step": 40
|
201 |
},
|
202 |
{
|
203 |
-
"epoch": 20.
|
204 |
-
"eval_accuracy": 0
|
205 |
-
"eval_loss": 0.
|
206 |
-
"eval_runtime": 7.
|
207 |
-
"eval_samples_per_second":
|
208 |
-
"eval_steps_per_second": 0.
|
209 |
"step": 42
|
210 |
},
|
211 |
{
|
212 |
-
"epoch": 21.
|
213 |
-
"eval_accuracy": 0
|
214 |
-
"eval_loss": 0.
|
215 |
-
"eval_runtime":
|
216 |
-
"eval_samples_per_second":
|
217 |
-
"eval_steps_per_second": 0.
|
218 |
"step": 44
|
219 |
},
|
220 |
{
|
221 |
-
"epoch": 22.
|
222 |
-
"eval_accuracy": 0
|
223 |
-
"eval_loss": 0.
|
224 |
-
"eval_runtime":
|
225 |
-
"eval_samples_per_second":
|
226 |
-
"eval_steps_per_second": 0.
|
227 |
"step": 46
|
228 |
},
|
229 |
{
|
230 |
-
"epoch": 23.
|
231 |
-
"eval_accuracy": 0
|
232 |
-
"eval_loss": 0.
|
233 |
-
"eval_runtime":
|
234 |
-
"eval_samples_per_second":
|
235 |
-
"eval_steps_per_second": 0.
|
236 |
"step": 48
|
237 |
},
|
238 |
{
|
239 |
-
"epoch": 24.
|
240 |
-
"eval_accuracy": 0.
|
241 |
-
"eval_loss": 0.
|
242 |
-
"eval_runtime":
|
243 |
-
"eval_samples_per_second": 4.
|
244 |
-
"eval_steps_per_second": 0.
|
245 |
"step": 50
|
246 |
},
|
247 |
{
|
248 |
-
"epoch": 25.
|
249 |
-
"eval_accuracy": 0.
|
250 |
-
"eval_loss": 0.
|
251 |
-
"eval_runtime":
|
252 |
-
"eval_samples_per_second": 5.
|
253 |
-
"eval_steps_per_second": 0.
|
254 |
"step": 52
|
255 |
},
|
256 |
{
|
257 |
-
"epoch": 26.
|
258 |
-
"eval_accuracy": 0.
|
259 |
-
"eval_loss": 0.
|
260 |
-
"eval_runtime":
|
261 |
-
"eval_samples_per_second":
|
262 |
-
"eval_steps_per_second": 0.
|
263 |
"step": 54
|
264 |
},
|
265 |
{
|
266 |
-
"epoch": 27.
|
267 |
-
"eval_accuracy": 0.
|
268 |
-
"eval_loss": 0.
|
269 |
-
"eval_runtime":
|
270 |
-
"eval_samples_per_second":
|
271 |
-
"eval_steps_per_second": 0.
|
272 |
"step": 56
|
273 |
},
|
274 |
{
|
275 |
-
"epoch": 28.
|
276 |
-
"eval_accuracy": 0.
|
277 |
-
"eval_loss": 0.
|
278 |
-
"eval_runtime": 6.
|
279 |
-
"eval_samples_per_second": 5.
|
280 |
-
"eval_steps_per_second": 0.
|
281 |
"step": 58
|
282 |
},
|
283 |
{
|
284 |
-
"epoch": 29.
|
285 |
"learning_rate": 1.388888888888889e-05,
|
286 |
-
"loss": 0.
|
287 |
"step": 60
|
288 |
},
|
289 |
{
|
290 |
-
"epoch": 29.
|
291 |
-
"eval_accuracy": 0.
|
292 |
-
"eval_loss": 0.
|
293 |
-
"eval_runtime":
|
294 |
-
"eval_samples_per_second":
|
295 |
-
"eval_steps_per_second": 0.
|
296 |
"step": 60
|
297 |
},
|
298 |
{
|
299 |
-
"epoch": 30.
|
300 |
-
"eval_accuracy": 0.
|
301 |
-
"eval_loss": 0.
|
302 |
-
"eval_runtime":
|
303 |
-
"eval_samples_per_second": 4.
|
304 |
-
"eval_steps_per_second": 0.
|
305 |
"step": 62
|
306 |
},
|
307 |
{
|
308 |
-
"epoch": 31.
|
309 |
-
"eval_accuracy": 0.
|
310 |
-
"eval_loss": 0.
|
311 |
-
"eval_runtime": 7.
|
312 |
-
"eval_samples_per_second": 4.
|
313 |
-
"eval_steps_per_second": 0.
|
314 |
"step": 64
|
315 |
},
|
316 |
{
|
317 |
-
"epoch": 32.
|
318 |
-
"eval_accuracy": 0.
|
319 |
-
"eval_loss": 0.
|
320 |
-
"eval_runtime":
|
321 |
-
"eval_samples_per_second":
|
322 |
-
"eval_steps_per_second": 0.
|
323 |
"step": 66
|
324 |
},
|
325 |
{
|
326 |
-
"epoch": 33.
|
327 |
-
"eval_accuracy": 0.
|
328 |
-
"eval_loss": 0.
|
329 |
-
"eval_runtime":
|
330 |
-
"eval_samples_per_second":
|
331 |
-
"eval_steps_per_second": 0.
|
332 |
"step": 68
|
333 |
},
|
334 |
{
|
335 |
-
"epoch": 34.
|
336 |
-
"eval_accuracy": 0.
|
337 |
-
"eval_loss": 0.
|
338 |
-
"eval_runtime":
|
339 |
-
"eval_samples_per_second": 4.
|
340 |
-
"eval_steps_per_second": 0.
|
341 |
"step": 70
|
342 |
},
|
343 |
{
|
344 |
-
"epoch": 35.
|
345 |
-
"eval_accuracy": 0.
|
346 |
-
"eval_loss": 0.
|
347 |
-
"eval_runtime":
|
348 |
-
"eval_samples_per_second": 4.
|
349 |
-
"eval_steps_per_second": 0.
|
350 |
"step": 72
|
351 |
},
|
352 |
{
|
353 |
-
"epoch": 36.
|
354 |
-
"eval_accuracy": 0.
|
355 |
-
"eval_loss": 0.
|
356 |
-
"eval_runtime": 7.
|
357 |
-
"eval_samples_per_second": 4.
|
358 |
-
"eval_steps_per_second": 0.
|
359 |
"step": 74
|
360 |
},
|
361 |
{
|
362 |
-
"epoch": 37.
|
363 |
-
"eval_accuracy": 0.
|
364 |
-
"eval_loss": 0.
|
365 |
-
"eval_runtime":
|
366 |
-
"eval_samples_per_second":
|
367 |
-
"eval_steps_per_second": 0.
|
368 |
"step": 76
|
369 |
},
|
370 |
{
|
371 |
-
"epoch": 38.
|
372 |
-
"eval_accuracy": 0.
|
373 |
-
"eval_loss": 0.
|
374 |
-
"eval_runtime":
|
375 |
-
"eval_samples_per_second":
|
376 |
-
"eval_steps_per_second": 0.
|
377 |
"step": 78
|
378 |
},
|
379 |
{
|
380 |
-
"epoch": 39.
|
381 |
"learning_rate": 0.0,
|
382 |
-
"loss": 0.
|
383 |
"step": 80
|
384 |
},
|
385 |
{
|
386 |
-
"epoch": 39.
|
387 |
-
"eval_accuracy": 0.
|
388 |
-
"eval_loss": 0.
|
389 |
-
"eval_runtime":
|
390 |
-
"eval_samples_per_second":
|
391 |
-
"eval_steps_per_second": 0.
|
392 |
"step": 80
|
393 |
},
|
394 |
{
|
395 |
-
"epoch": 39.
|
396 |
"step": 80,
|
397 |
-
"total_flos": 3.
|
398 |
-
"train_loss": 0.
|
399 |
-
"train_runtime":
|
400 |
-
"train_samples_per_second": 1.
|
401 |
-
"train_steps_per_second": 0.
|
402 |
}
|
403 |
],
|
404 |
"max_steps": 80,
|
405 |
"num_train_epochs": 40,
|
406 |
-
"total_flos": 3.
|
407 |
"trial_name": null,
|
408 |
"trial_params": null
|
409 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.0,
|
3 |
+
"best_model_checkpoint": "delivery_truck_classification\\checkpoint-2",
|
4 |
+
"epoch": 39.72727272727273,
|
5 |
"global_step": 80,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.73,
|
12 |
+
"eval_accuracy": 1.0,
|
13 |
+
"eval_loss": 0.0415542908012867,
|
14 |
+
"eval_runtime": 7.7969,
|
15 |
+
"eval_samples_per_second": 4.745,
|
16 |
+
"eval_steps_per_second": 0.257,
|
17 |
"step": 2
|
18 |
},
|
19 |
{
|
20 |
+
"epoch": 1.73,
|
21 |
+
"eval_accuracy": 1.0,
|
22 |
+
"eval_loss": 0.03460519760847092,
|
23 |
+
"eval_runtime": 9.6408,
|
24 |
+
"eval_samples_per_second": 3.838,
|
25 |
+
"eval_steps_per_second": 0.207,
|
26 |
"step": 4
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 2.73,
|
30 |
+
"eval_accuracy": 1.0,
|
31 |
+
"eval_loss": 0.029270131140947342,
|
32 |
+
"eval_runtime": 11.5968,
|
33 |
+
"eval_samples_per_second": 3.191,
|
34 |
+
"eval_steps_per_second": 0.172,
|
35 |
"step": 6
|
36 |
},
|
37 |
{
|
38 |
+
"epoch": 3.73,
|
39 |
+
"eval_accuracy": 1.0,
|
40 |
+
"eval_loss": 0.01861225999891758,
|
41 |
+
"eval_runtime": 8.4881,
|
42 |
+
"eval_samples_per_second": 4.359,
|
43 |
+
"eval_steps_per_second": 0.236,
|
44 |
"step": 8
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 4.73,
|
48 |
+
"eval_accuracy": 1.0,
|
49 |
+
"eval_loss": 0.020498055964708328,
|
50 |
+
"eval_runtime": 9.9982,
|
51 |
+
"eval_samples_per_second": 3.701,
|
52 |
+
"eval_steps_per_second": 0.2,
|
53 |
"step": 10
|
54 |
},
|
55 |
{
|
56 |
+
"epoch": 5.73,
|
57 |
+
"eval_accuracy": 0.972972972972973,
|
58 |
+
"eval_loss": 0.06043216958642006,
|
59 |
+
"eval_runtime": 8.9914,
|
60 |
+
"eval_samples_per_second": 4.115,
|
61 |
+
"eval_steps_per_second": 0.222,
|
62 |
"step": 12
|
63 |
},
|
64 |
{
|
65 |
+
"epoch": 6.73,
|
66 |
+
"eval_accuracy": 1.0,
|
67 |
+
"eval_loss": 0.0332246832549572,
|
68 |
+
"eval_runtime": 8.8254,
|
69 |
+
"eval_samples_per_second": 4.192,
|
70 |
+
"eval_steps_per_second": 0.227,
|
71 |
"step": 14
|
72 |
},
|
73 |
{
|
74 |
+
"epoch": 7.73,
|
75 |
+
"eval_accuracy": 1.0,
|
76 |
+
"eval_loss": 0.025004582479596138,
|
77 |
+
"eval_runtime": 11.8616,
|
78 |
+
"eval_samples_per_second": 3.119,
|
79 |
+
"eval_steps_per_second": 0.169,
|
80 |
"step": 16
|
81 |
},
|
82 |
{
|
83 |
+
"epoch": 8.73,
|
84 |
+
"eval_accuracy": 1.0,
|
85 |
+
"eval_loss": 0.03864024579524994,
|
86 |
+
"eval_runtime": 8.8843,
|
87 |
+
"eval_samples_per_second": 4.165,
|
88 |
+
"eval_steps_per_second": 0.225,
|
89 |
"step": 18
|
90 |
},
|
91 |
{
|
92 |
+
"epoch": 9.73,
|
93 |
"learning_rate": 4.166666666666667e-05,
|
94 |
+
"loss": 0.2483,
|
95 |
"step": 20
|
96 |
},
|
97 |
{
|
98 |
+
"epoch": 9.73,
|
99 |
+
"eval_accuracy": 1.0,
|
100 |
+
"eval_loss": 0.04379289597272873,
|
101 |
+
"eval_runtime": 8.6752,
|
102 |
+
"eval_samples_per_second": 4.265,
|
103 |
+
"eval_steps_per_second": 0.231,
|
104 |
"step": 20
|
105 |
},
|
106 |
{
|
107 |
+
"epoch": 10.73,
|
108 |
+
"eval_accuracy": 1.0,
|
109 |
+
"eval_loss": 0.04468226432800293,
|
110 |
+
"eval_runtime": 8.2704,
|
111 |
+
"eval_samples_per_second": 4.474,
|
112 |
+
"eval_steps_per_second": 0.242,
|
113 |
"step": 22
|
114 |
},
|
115 |
{
|
116 |
+
"epoch": 11.73,
|
117 |
+
"eval_accuracy": 0.972972972972973,
|
118 |
+
"eval_loss": 0.06756877154111862,
|
119 |
+
"eval_runtime": 8.2231,
|
120 |
+
"eval_samples_per_second": 4.5,
|
121 |
+
"eval_steps_per_second": 0.243,
|
122 |
"step": 24
|
123 |
},
|
124 |
{
|
125 |
+
"epoch": 12.73,
|
126 |
+
"eval_accuracy": 0.972972972972973,
|
127 |
+
"eval_loss": 0.07861027866601944,
|
128 |
+
"eval_runtime": 8.9079,
|
129 |
+
"eval_samples_per_second": 4.154,
|
130 |
+
"eval_steps_per_second": 0.225,
|
131 |
"step": 26
|
132 |
},
|
133 |
{
|
134 |
+
"epoch": 13.73,
|
135 |
+
"eval_accuracy": 1.0,
|
136 |
+
"eval_loss": 0.03886393457651138,
|
137 |
+
"eval_runtime": 7.4091,
|
138 |
+
"eval_samples_per_second": 4.994,
|
139 |
+
"eval_steps_per_second": 0.27,
|
140 |
"step": 28
|
141 |
},
|
142 |
{
|
143 |
+
"epoch": 14.73,
|
144 |
+
"eval_accuracy": 1.0,
|
145 |
+
"eval_loss": 0.02784094214439392,
|
146 |
+
"eval_runtime": 9.7376,
|
147 |
+
"eval_samples_per_second": 3.8,
|
148 |
+
"eval_steps_per_second": 0.205,
|
149 |
"step": 30
|
150 |
},
|
151 |
{
|
152 |
+
"epoch": 15.73,
|
153 |
+
"eval_accuracy": 1.0,
|
154 |
+
"eval_loss": 0.02497038058936596,
|
155 |
+
"eval_runtime": 7.3256,
|
156 |
+
"eval_samples_per_second": 5.051,
|
157 |
+
"eval_steps_per_second": 0.273,
|
158 |
"step": 32
|
159 |
},
|
160 |
{
|
161 |
+
"epoch": 16.73,
|
162 |
+
"eval_accuracy": 1.0,
|
163 |
+
"eval_loss": 0.02828327752649784,
|
164 |
+
"eval_runtime": 11.0099,
|
165 |
+
"eval_samples_per_second": 3.361,
|
166 |
+
"eval_steps_per_second": 0.182,
|
167 |
"step": 34
|
168 |
},
|
169 |
{
|
170 |
+
"epoch": 17.73,
|
171 |
+
"eval_accuracy": 0.972972972972973,
|
172 |
+
"eval_loss": 0.05021832138299942,
|
173 |
+
"eval_runtime": 9.5468,
|
174 |
+
"eval_samples_per_second": 3.876,
|
175 |
+
"eval_steps_per_second": 0.209,
|
176 |
"step": 36
|
177 |
},
|
178 |
{
|
179 |
+
"epoch": 18.73,
|
180 |
+
"eval_accuracy": 0.972972972972973,
|
181 |
+
"eval_loss": 0.07113233208656311,
|
182 |
+
"eval_runtime": 7.5069,
|
183 |
+
"eval_samples_per_second": 4.929,
|
184 |
+
"eval_steps_per_second": 0.266,
|
185 |
"step": 38
|
186 |
},
|
187 |
{
|
188 |
+
"epoch": 19.73,
|
189 |
"learning_rate": 2.777777777777778e-05,
|
190 |
+
"loss": 0.1759,
|
191 |
"step": 40
|
192 |
},
|
193 |
{
|
194 |
+
"epoch": 19.73,
|
195 |
+
"eval_accuracy": 0.972972972972973,
|
196 |
+
"eval_loss": 0.06368651241064072,
|
197 |
+
"eval_runtime": 10.8688,
|
198 |
+
"eval_samples_per_second": 3.404,
|
199 |
+
"eval_steps_per_second": 0.184,
|
200 |
"step": 40
|
201 |
},
|
202 |
{
|
203 |
+
"epoch": 20.73,
|
204 |
+
"eval_accuracy": 1.0,
|
205 |
+
"eval_loss": 0.04590895399451256,
|
206 |
+
"eval_runtime": 7.36,
|
207 |
+
"eval_samples_per_second": 5.027,
|
208 |
+
"eval_steps_per_second": 0.272,
|
209 |
"step": 42
|
210 |
},
|
211 |
{
|
212 |
+
"epoch": 21.73,
|
213 |
+
"eval_accuracy": 1.0,
|
214 |
+
"eval_loss": 0.03937483951449394,
|
215 |
+
"eval_runtime": 7.6664,
|
216 |
+
"eval_samples_per_second": 4.826,
|
217 |
+
"eval_steps_per_second": 0.261,
|
218 |
"step": 44
|
219 |
},
|
220 |
{
|
221 |
+
"epoch": 22.73,
|
222 |
+
"eval_accuracy": 1.0,
|
223 |
+
"eval_loss": 0.04189879819750786,
|
224 |
+
"eval_runtime": 7.6918,
|
225 |
+
"eval_samples_per_second": 4.81,
|
226 |
+
"eval_steps_per_second": 0.26,
|
227 |
"step": 46
|
228 |
},
|
229 |
{
|
230 |
+
"epoch": 23.73,
|
231 |
+
"eval_accuracy": 1.0,
|
232 |
+
"eval_loss": 0.042252812534570694,
|
233 |
+
"eval_runtime": 9.2536,
|
234 |
+
"eval_samples_per_second": 3.998,
|
235 |
+
"eval_steps_per_second": 0.216,
|
236 |
"step": 48
|
237 |
},
|
238 |
{
|
239 |
+
"epoch": 24.73,
|
240 |
+
"eval_accuracy": 0.972972972972973,
|
241 |
+
"eval_loss": 0.046256761997938156,
|
242 |
+
"eval_runtime": 8.404,
|
243 |
+
"eval_samples_per_second": 4.403,
|
244 |
+
"eval_steps_per_second": 0.238,
|
245 |
"step": 50
|
246 |
},
|
247 |
{
|
248 |
+
"epoch": 25.73,
|
249 |
+
"eval_accuracy": 0.972972972972973,
|
250 |
+
"eval_loss": 0.050322916358709335,
|
251 |
+
"eval_runtime": 7.2832,
|
252 |
+
"eval_samples_per_second": 5.08,
|
253 |
+
"eval_steps_per_second": 0.275,
|
254 |
"step": 52
|
255 |
},
|
256 |
{
|
257 |
+
"epoch": 26.73,
|
258 |
+
"eval_accuracy": 0.972972972972973,
|
259 |
+
"eval_loss": 0.061594847589731216,
|
260 |
+
"eval_runtime": 7.736,
|
261 |
+
"eval_samples_per_second": 4.783,
|
262 |
+
"eval_steps_per_second": 0.259,
|
263 |
"step": 54
|
264 |
},
|
265 |
{
|
266 |
+
"epoch": 27.73,
|
267 |
+
"eval_accuracy": 0.972972972972973,
|
268 |
+
"eval_loss": 0.0641237199306488,
|
269 |
+
"eval_runtime": 8.3429,
|
270 |
+
"eval_samples_per_second": 4.435,
|
271 |
+
"eval_steps_per_second": 0.24,
|
272 |
"step": 56
|
273 |
},
|
274 |
{
|
275 |
+
"epoch": 28.73,
|
276 |
+
"eval_accuracy": 0.972972972972973,
|
277 |
+
"eval_loss": 0.05289805307984352,
|
278 |
+
"eval_runtime": 6.6939,
|
279 |
+
"eval_samples_per_second": 5.527,
|
280 |
+
"eval_steps_per_second": 0.299,
|
281 |
"step": 58
|
282 |
},
|
283 |
{
|
284 |
+
"epoch": 29.73,
|
285 |
"learning_rate": 1.388888888888889e-05,
|
286 |
+
"loss": 0.1669,
|
287 |
"step": 60
|
288 |
},
|
289 |
{
|
290 |
+
"epoch": 29.73,
|
291 |
+
"eval_accuracy": 0.972972972972973,
|
292 |
+
"eval_loss": 0.048487674444913864,
|
293 |
+
"eval_runtime": 8.2178,
|
294 |
+
"eval_samples_per_second": 4.502,
|
295 |
+
"eval_steps_per_second": 0.243,
|
296 |
"step": 60
|
297 |
},
|
298 |
{
|
299 |
+
"epoch": 30.73,
|
300 |
+
"eval_accuracy": 0.972972972972973,
|
301 |
+
"eval_loss": 0.04654627665877342,
|
302 |
+
"eval_runtime": 9.0621,
|
303 |
+
"eval_samples_per_second": 4.083,
|
304 |
+
"eval_steps_per_second": 0.221,
|
305 |
"step": 62
|
306 |
},
|
307 |
{
|
308 |
+
"epoch": 31.73,
|
309 |
+
"eval_accuracy": 0.972972972972973,
|
310 |
+
"eval_loss": 0.045613404363393784,
|
311 |
+
"eval_runtime": 7.5057,
|
312 |
+
"eval_samples_per_second": 4.93,
|
313 |
+
"eval_steps_per_second": 0.266,
|
314 |
"step": 64
|
315 |
},
|
316 |
{
|
317 |
+
"epoch": 32.73,
|
318 |
+
"eval_accuracy": 0.972972972972973,
|
319 |
+
"eval_loss": 0.047752730548381805,
|
320 |
+
"eval_runtime": 7.6794,
|
321 |
+
"eval_samples_per_second": 4.818,
|
322 |
+
"eval_steps_per_second": 0.26,
|
323 |
"step": 66
|
324 |
},
|
325 |
{
|
326 |
+
"epoch": 33.73,
|
327 |
+
"eval_accuracy": 0.972972972972973,
|
328 |
+
"eval_loss": 0.0467178151011467,
|
329 |
+
"eval_runtime": 7.7621,
|
330 |
+
"eval_samples_per_second": 4.767,
|
331 |
+
"eval_steps_per_second": 0.258,
|
332 |
"step": 68
|
333 |
},
|
334 |
{
|
335 |
+
"epoch": 34.73,
|
336 |
+
"eval_accuracy": 0.972972972972973,
|
337 |
+
"eval_loss": 0.04733948037028313,
|
338 |
+
"eval_runtime": 8.0246,
|
339 |
+
"eval_samples_per_second": 4.611,
|
340 |
+
"eval_steps_per_second": 0.249,
|
341 |
"step": 70
|
342 |
},
|
343 |
{
|
344 |
+
"epoch": 35.73,
|
345 |
+
"eval_accuracy": 0.972972972972973,
|
346 |
+
"eval_loss": 0.048583876341581345,
|
347 |
+
"eval_runtime": 8.5589,
|
348 |
+
"eval_samples_per_second": 4.323,
|
349 |
+
"eval_steps_per_second": 0.234,
|
350 |
"step": 72
|
351 |
},
|
352 |
{
|
353 |
+
"epoch": 36.73,
|
354 |
+
"eval_accuracy": 0.972972972972973,
|
355 |
+
"eval_loss": 0.05004884675145149,
|
356 |
+
"eval_runtime": 7.4868,
|
357 |
+
"eval_samples_per_second": 4.942,
|
358 |
+
"eval_steps_per_second": 0.267,
|
359 |
"step": 74
|
360 |
},
|
361 |
{
|
362 |
+
"epoch": 37.73,
|
363 |
+
"eval_accuracy": 0.972972972972973,
|
364 |
+
"eval_loss": 0.0501551553606987,
|
365 |
+
"eval_runtime": 8.2774,
|
366 |
+
"eval_samples_per_second": 4.47,
|
367 |
+
"eval_steps_per_second": 0.242,
|
368 |
"step": 76
|
369 |
},
|
370 |
{
|
371 |
+
"epoch": 38.73,
|
372 |
+
"eval_accuracy": 0.972972972972973,
|
373 |
+
"eval_loss": 0.05001495033502579,
|
374 |
+
"eval_runtime": 7.8563,
|
375 |
+
"eval_samples_per_second": 4.71,
|
376 |
+
"eval_steps_per_second": 0.255,
|
377 |
"step": 78
|
378 |
},
|
379 |
{
|
380 |
+
"epoch": 39.73,
|
381 |
"learning_rate": 0.0,
|
382 |
+
"loss": 0.1589,
|
383 |
"step": 80
|
384 |
},
|
385 |
{
|
386 |
+
"epoch": 39.73,
|
387 |
+
"eval_accuracy": 0.972972972972973,
|
388 |
+
"eval_loss": 0.04929113760590553,
|
389 |
+
"eval_runtime": 8.4253,
|
390 |
+
"eval_samples_per_second": 4.392,
|
391 |
+
"eval_steps_per_second": 0.237,
|
392 |
"step": 80
|
393 |
},
|
394 |
{
|
395 |
+
"epoch": 39.73,
|
396 |
"step": 80,
|
397 |
+
"total_flos": 3.262961773565706e+17,
|
398 |
+
"train_loss": 0.18748833239078522,
|
399 |
+
"train_runtime": 7500.5041,
|
400 |
+
"train_samples_per_second": 1.76,
|
401 |
+
"train_steps_per_second": 0.011
|
402 |
}
|
403 |
],
|
404 |
"max_steps": 80,
|
405 |
"num_train_epochs": 40,
|
406 |
+
"total_flos": 3.262961773565706e+17,
|
407 |
"trial_name": null,
|
408 |
"trial_params": null
|
409 |
}
|