andrecastro
commited on
Commit
•
8413146
1
Parent(s):
f5df4f7
Training in progress, epoch 1
Browse files- all_results.json +5 -5
- model.safetensors +1 -1
- runs/Dec07_17-37-42_5dd1a2af6ce4/events.out.tfevents.1701976934.5dd1a2af6ce4.735.5 +3 -0
- runs/Dec07_17-37-42_5dd1a2af6ce4/events.out.tfevents.1701978244.5dd1a2af6ce4.735.6 +3 -0
- runs/Dec07_17-37-42_5dd1a2af6ce4/events.out.tfevents.1701978260.5dd1a2af6ce4.735.7 +3 -0
- runs/Dec07_19-45-01_5dd1a2af6ce4/events.out.tfevents.1701978315.5dd1a2af6ce4.735.8 +3 -0
- runs/Dec07_19-45-01_5dd1a2af6ce4/events.out.tfevents.1701978557.5dd1a2af6ce4.735.9 +3 -0
- runs/Dec07_19-45-01_5dd1a2af6ce4/events.out.tfevents.1701978876.5dd1a2af6ce4.735.10 +3 -0
- train_results.json +5 -5
- trainer_state.json +152 -152
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"total_flos": 8.
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 32.
|
7 |
-
"train_steps_per_second": 1.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"total_flos": 8.924294285481738e+17,
|
4 |
+
"train_loss": 0.06514118614095245,
|
5 |
+
"train_runtime": 1099.2319,
|
6 |
+
"train_samples_per_second": 32.663,
|
7 |
+
"train_steps_per_second": 1.021
|
8 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 110342832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c7ffb3113d1016163932d5b2bf3394d9f249e309e5201d1b81a1682bb1d4208
|
3 |
size 110342832
|
runs/Dec07_17-37-42_5dd1a2af6ce4/events.out.tfevents.1701976934.5dd1a2af6ce4.735.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a037710cc319f5f08703d3c2c519640277167d9a045a11b1b81a41913798485
|
3 |
+
size 4903
|
runs/Dec07_17-37-42_5dd1a2af6ce4/events.out.tfevents.1701978244.5dd1a2af6ce4.735.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d6a441d256038a87f28d16da3bad9aa844a1537c2d6a01237df4ee61a4bf896
|
3 |
+
size 4749
|
runs/Dec07_17-37-42_5dd1a2af6ce4/events.out.tfevents.1701978260.5dd1a2af6ce4.735.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30ec5935832cdff92663edd5c6bdfcfc600accb6b7d58104436d2f6d7a09c0ff
|
3 |
+
size 4749
|
runs/Dec07_19-45-01_5dd1a2af6ce4/events.out.tfevents.1701978315.5dd1a2af6ce4.735.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51b078566cd93beb933d4f65debc0d145ab219a1df1ef711f34f44a37fdf5550
|
3 |
+
size 7647
|
runs/Dec07_19-45-01_5dd1a2af6ce4/events.out.tfevents.1701978557.5dd1a2af6ce4.735.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1daea6bd1d87712c834d1928a7c2b9ad86a4321568926226056b733dcbe77e2b
|
3 |
+
size 5365
|
runs/Dec07_19-45-01_5dd1a2af6ce4/events.out.tfevents.1701978876.5dd1a2af6ce4.735.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9299ac12e3186d8cb65c90a0e1fa07c96a323f0e829683db32df502f52cd318
|
3 |
+
size 10948
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"total_flos": 8.
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 32.
|
7 |
-
"train_steps_per_second": 1.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"total_flos": 8.924294285481738e+17,
|
4 |
+
"train_loss": 0.06514118614095245,
|
5 |
+
"train_runtime": 1099.2319,
|
6 |
+
"train_samples_per_second": 32.663,
|
7 |
+
"train_steps_per_second": 1.021
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-
|
4 |
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1122,
|
@@ -11,753 +11,753 @@
|
|
11 |
{
|
12 |
"epoch": 0.03,
|
13 |
"learning_rate": 4.424778761061947e-06,
|
14 |
-
"loss": 0.
|
15 |
"step": 10
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.05,
|
19 |
"learning_rate": 8.849557522123894e-06,
|
20 |
-
"loss": 0.
|
21 |
"step": 20
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.08,
|
25 |
"learning_rate": 1.3274336283185843e-05,
|
26 |
-
"loss": 0.
|
27 |
"step": 30
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.11,
|
31 |
"learning_rate": 1.7699115044247787e-05,
|
32 |
-
"loss": 0.
|
33 |
"step": 40
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.13,
|
37 |
"learning_rate": 2.2123893805309738e-05,
|
38 |
-
"loss": 0.
|
39 |
"step": 50
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.16,
|
43 |
"learning_rate": 2.6548672566371686e-05,
|
44 |
-
"loss": 0.
|
45 |
"step": 60
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.19,
|
49 |
"learning_rate": 3.097345132743363e-05,
|
50 |
-
"loss": 0.
|
51 |
"step": 70
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.21,
|
55 |
"learning_rate": 3.5398230088495574e-05,
|
56 |
-
"loss": 0.
|
57 |
"step": 80
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.24,
|
61 |
"learning_rate": 3.982300884955752e-05,
|
62 |
-
"loss": 0.
|
63 |
"step": 90
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.27,
|
67 |
"learning_rate": 4.4247787610619477e-05,
|
68 |
-
"loss": 0.
|
69 |
"step": 100
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.29,
|
73 |
"learning_rate": 4.867256637168142e-05,
|
74 |
-
"loss": 0.
|
75 |
"step": 110
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.32,
|
79 |
"learning_rate": 4.9653121902874134e-05,
|
80 |
-
"loss": 0.
|
81 |
"step": 120
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.35,
|
85 |
"learning_rate": 4.9157581764122896e-05,
|
86 |
-
"loss": 0.
|
87 |
"step": 130
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.37,
|
91 |
"learning_rate": 4.866204162537166e-05,
|
92 |
-
"loss": 0.
|
93 |
"step": 140
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.4,
|
97 |
"learning_rate": 4.816650148662042e-05,
|
98 |
-
"loss": 0.
|
99 |
"step": 150
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.43,
|
103 |
"learning_rate": 4.767096134786918e-05,
|
104 |
-
"loss": 0.
|
105 |
"step": 160
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.45,
|
109 |
"learning_rate": 4.717542120911794e-05,
|
110 |
-
"loss": 0.
|
111 |
"step": 170
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.48,
|
115 |
"learning_rate": 4.66798810703667e-05,
|
116 |
-
"loss": 0.
|
117 |
"step": 180
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.51,
|
121 |
"learning_rate": 4.618434093161546e-05,
|
122 |
-
"loss": 0.
|
123 |
"step": 190
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.53,
|
127 |
"learning_rate": 4.568880079286422e-05,
|
128 |
-
"loss": 0.
|
129 |
"step": 200
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.56,
|
133 |
"learning_rate": 4.5193260654112984e-05,
|
134 |
-
"loss": 0.
|
135 |
"step": 210
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.59,
|
139 |
"learning_rate": 4.4697720515361746e-05,
|
140 |
-
"loss": 0.
|
141 |
"step": 220
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.61,
|
145 |
"learning_rate": 4.420218037661051e-05,
|
146 |
-
"loss": 0.
|
147 |
"step": 230
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.64,
|
151 |
"learning_rate": 4.370664023785927e-05,
|
152 |
-
"loss": 0.
|
153 |
"step": 240
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.67,
|
157 |
"learning_rate": 4.321110009910803e-05,
|
158 |
-
"loss": 0.
|
159 |
"step": 250
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.7,
|
163 |
"learning_rate": 4.27155599603568e-05,
|
164 |
-
"loss": 0.
|
165 |
"step": 260
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.72,
|
169 |
"learning_rate": 4.222001982160555e-05,
|
170 |
-
"loss": 0.
|
171 |
"step": 270
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.75,
|
175 |
"learning_rate": 4.172447968285431e-05,
|
176 |
-
"loss": 0.
|
177 |
"step": 280
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.78,
|
181 |
"learning_rate": 4.122893954410307e-05,
|
182 |
-
"loss": 0.
|
183 |
"step": 290
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.8,
|
187 |
"learning_rate": 4.0733399405351834e-05,
|
188 |
-
"loss": 0.
|
189 |
"step": 300
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.83,
|
193 |
"learning_rate": 4.0237859266600596e-05,
|
194 |
-
"loss": 0.
|
195 |
"step": 310
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.86,
|
199 |
"learning_rate": 3.9742319127849357e-05,
|
200 |
-
"loss": 0.
|
201 |
"step": 320
|
202 |
},
|
203 |
{
|
204 |
"epoch": 0.88,
|
205 |
"learning_rate": 3.924677898909812e-05,
|
206 |
-
"loss": 0.
|
207 |
"step": 330
|
208 |
},
|
209 |
{
|
210 |
"epoch": 0.91,
|
211 |
"learning_rate": 3.8751238850346886e-05,
|
212 |
-
"loss": 0.
|
213 |
"step": 340
|
214 |
},
|
215 |
{
|
216 |
"epoch": 0.94,
|
217 |
"learning_rate": 3.825569871159564e-05,
|
218 |
-
"loss": 0.
|
219 |
"step": 350
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.96,
|
223 |
"learning_rate": 3.77601585728444e-05,
|
224 |
-
"loss": 0.
|
225 |
"step": 360
|
226 |
},
|
227 |
{
|
228 |
"epoch": 0.99,
|
229 |
"learning_rate": 3.726461843409316e-05,
|
230 |
-
"loss": 0.
|
231 |
"step": 370
|
232 |
},
|
233 |
{
|
234 |
"epoch": 1.0,
|
235 |
-
"eval_accuracy": 0.
|
236 |
"eval_confusion_matrix": [
|
237 |
[
|
238 |
-
|
239 |
-
|
240 |
],
|
241 |
[
|
242 |
-
|
243 |
-
|
244 |
]
|
245 |
],
|
246 |
-
"eval_loss": 0.
|
247 |
-
"eval_precision": 0.
|
248 |
-
"eval_recall": 0.
|
249 |
-
"eval_runtime":
|
250 |
-
"eval_samples_per_second":
|
251 |
-
"eval_steps_per_second":
|
252 |
"step": 374
|
253 |
},
|
254 |
{
|
255 |
"epoch": 1.02,
|
256 |
"learning_rate": 3.676907829534192e-05,
|
257 |
-
"loss": 0.
|
258 |
"step": 380
|
259 |
},
|
260 |
{
|
261 |
"epoch": 1.04,
|
262 |
"learning_rate": 3.6273538156590684e-05,
|
263 |
-
"loss": 0.
|
264 |
"step": 390
|
265 |
},
|
266 |
{
|
267 |
"epoch": 1.07,
|
268 |
"learning_rate": 3.5777998017839445e-05,
|
269 |
-
"loss": 0.
|
270 |
"step": 400
|
271 |
},
|
272 |
{
|
273 |
"epoch": 1.1,
|
274 |
"learning_rate": 3.5282457879088207e-05,
|
275 |
-
"loss": 0.
|
276 |
"step": 410
|
277 |
},
|
278 |
{
|
279 |
"epoch": 1.12,
|
280 |
"learning_rate": 3.4786917740336974e-05,
|
281 |
-
"loss": 0.
|
282 |
"step": 420
|
283 |
},
|
284 |
{
|
285 |
"epoch": 1.15,
|
286 |
"learning_rate": 3.429137760158573e-05,
|
287 |
-
"loss": 0.
|
288 |
"step": 430
|
289 |
},
|
290 |
{
|
291 |
"epoch": 1.18,
|
292 |
"learning_rate": 3.379583746283449e-05,
|
293 |
-
"loss": 0.
|
294 |
"step": 440
|
295 |
},
|
296 |
{
|
297 |
"epoch": 1.2,
|
298 |
"learning_rate": 3.330029732408325e-05,
|
299 |
-
"loss": 0.
|
300 |
"step": 450
|
301 |
},
|
302 |
{
|
303 |
"epoch": 1.23,
|
304 |
"learning_rate": 3.280475718533201e-05,
|
305 |
-
"loss": 0.
|
306 |
"step": 460
|
307 |
},
|
308 |
{
|
309 |
"epoch": 1.26,
|
310 |
"learning_rate": 3.230921704658077e-05,
|
311 |
-
"loss": 0.
|
312 |
"step": 470
|
313 |
},
|
314 |
{
|
315 |
"epoch": 1.28,
|
316 |
"learning_rate": 3.1813676907829534e-05,
|
317 |
-
"loss": 0.
|
318 |
"step": 480
|
319 |
},
|
320 |
{
|
321 |
"epoch": 1.31,
|
322 |
"learning_rate": 3.13181367690783e-05,
|
323 |
-
"loss": 0.
|
324 |
"step": 490
|
325 |
},
|
326 |
{
|
327 |
"epoch": 1.34,
|
328 |
"learning_rate": 3.0822596630327057e-05,
|
329 |
-
"loss": 0.
|
330 |
"step": 500
|
331 |
},
|
332 |
{
|
333 |
"epoch": 1.36,
|
334 |
"learning_rate": 3.0327056491575818e-05,
|
335 |
-
"loss": 0.
|
336 |
"step": 510
|
337 |
},
|
338 |
{
|
339 |
"epoch": 1.39,
|
340 |
"learning_rate": 2.983151635282458e-05,
|
341 |
-
"loss": 0.
|
342 |
"step": 520
|
343 |
},
|
344 |
{
|
345 |
"epoch": 1.42,
|
346 |
"learning_rate": 2.933597621407334e-05,
|
347 |
-
"loss": 0.
|
348 |
"step": 530
|
349 |
},
|
350 |
{
|
351 |
"epoch": 1.44,
|
352 |
"learning_rate": 2.88404360753221e-05,
|
353 |
-
"loss": 0.
|
354 |
"step": 540
|
355 |
},
|
356 |
{
|
357 |
"epoch": 1.47,
|
358 |
"learning_rate": 2.8344895936570865e-05,
|
359 |
-
"loss": 0.
|
360 |
"step": 550
|
361 |
},
|
362 |
{
|
363 |
"epoch": 1.5,
|
364 |
"learning_rate": 2.7849355797819627e-05,
|
365 |
-
"loss": 0.
|
366 |
"step": 560
|
367 |
},
|
368 |
{
|
369 |
"epoch": 1.52,
|
370 |
"learning_rate": 2.7353815659068388e-05,
|
371 |
-
"loss": 0.
|
372 |
"step": 570
|
373 |
},
|
374 |
{
|
375 |
"epoch": 1.55,
|
376 |
"learning_rate": 2.6858275520317145e-05,
|
377 |
-
"loss": 0.
|
378 |
"step": 580
|
379 |
},
|
380 |
{
|
381 |
"epoch": 1.58,
|
382 |
"learning_rate": 2.6362735381565906e-05,
|
383 |
-
"loss": 0.
|
384 |
"step": 590
|
385 |
},
|
386 |
{
|
387 |
"epoch": 1.6,
|
388 |
"learning_rate": 2.5867195242814668e-05,
|
389 |
-
"loss": 0.
|
390 |
"step": 600
|
391 |
},
|
392 |
{
|
393 |
"epoch": 1.63,
|
394 |
"learning_rate": 2.537165510406343e-05,
|
395 |
-
"loss": 0.
|
396 |
"step": 610
|
397 |
},
|
398 |
{
|
399 |
"epoch": 1.66,
|
400 |
"learning_rate": 2.4876114965312193e-05,
|
401 |
-
"loss": 0.
|
402 |
"step": 620
|
403 |
},
|
404 |
{
|
405 |
"epoch": 1.68,
|
406 |
"learning_rate": 2.4380574826560954e-05,
|
407 |
-
"loss": 0.
|
408 |
"step": 630
|
409 |
},
|
410 |
{
|
411 |
"epoch": 1.71,
|
412 |
"learning_rate": 2.3885034687809712e-05,
|
413 |
-
"loss": 0.
|
414 |
"step": 640
|
415 |
},
|
416 |
{
|
417 |
"epoch": 1.74,
|
418 |
"learning_rate": 2.3389494549058473e-05,
|
419 |
-
"loss": 0.
|
420 |
"step": 650
|
421 |
},
|
422 |
{
|
423 |
"epoch": 1.76,
|
424 |
"learning_rate": 2.2893954410307238e-05,
|
425 |
-
"loss": 0.
|
426 |
"step": 660
|
427 |
},
|
428 |
{
|
429 |
"epoch": 1.79,
|
430 |
"learning_rate": 2.2398414271556e-05,
|
431 |
-
"loss": 0.
|
432 |
"step": 670
|
433 |
},
|
434 |
{
|
435 |
"epoch": 1.82,
|
436 |
"learning_rate": 2.1902874132804756e-05,
|
437 |
-
"loss": 0.
|
438 |
"step": 680
|
439 |
},
|
440 |
{
|
441 |
"epoch": 1.84,
|
442 |
"learning_rate": 2.1407333994053518e-05,
|
443 |
-
"loss": 0.
|
444 |
"step": 690
|
445 |
},
|
446 |
{
|
447 |
"epoch": 1.87,
|
448 |
"learning_rate": 2.0911793855302282e-05,
|
449 |
-
"loss": 0.
|
450 |
"step": 700
|
451 |
},
|
452 |
{
|
453 |
"epoch": 1.9,
|
454 |
"learning_rate": 2.0416253716551043e-05,
|
455 |
-
"loss": 0.
|
456 |
"step": 710
|
457 |
},
|
458 |
{
|
459 |
"epoch": 1.93,
|
460 |
"learning_rate": 1.99207135777998e-05,
|
461 |
-
"loss": 0.
|
462 |
"step": 720
|
463 |
},
|
464 |
{
|
465 |
"epoch": 1.95,
|
466 |
"learning_rate": 1.9425173439048562e-05,
|
467 |
-
"loss": 0.
|
468 |
"step": 730
|
469 |
},
|
470 |
{
|
471 |
"epoch": 1.98,
|
472 |
"learning_rate": 1.8929633300297326e-05,
|
473 |
-
"loss": 0.
|
474 |
"step": 740
|
475 |
},
|
476 |
{
|
477 |
"epoch": 2.0,
|
478 |
-
"eval_accuracy": 0.
|
479 |
"eval_confusion_matrix": [
|
480 |
[
|
481 |
-
|
482 |
-
|
483 |
],
|
484 |
[
|
485 |
-
|
486 |
-
|
487 |
]
|
488 |
],
|
489 |
-
"eval_loss": 0.
|
490 |
-
"eval_precision": 0.
|
491 |
-
"eval_recall": 0.
|
492 |
-
"eval_runtime":
|
493 |
-
"eval_samples_per_second":
|
494 |
-
"eval_steps_per_second":
|
495 |
"step": 748
|
496 |
},
|
497 |
{
|
498 |
"epoch": 2.01,
|
499 |
"learning_rate": 1.8434093161546088e-05,
|
500 |
-
"loss": 0.
|
501 |
"step": 750
|
502 |
},
|
503 |
{
|
504 |
"epoch": 2.03,
|
505 |
"learning_rate": 1.7938553022794845e-05,
|
506 |
-
"loss": 0.
|
507 |
"step": 760
|
508 |
},
|
509 |
{
|
510 |
"epoch": 2.06,
|
511 |
"learning_rate": 1.7443012884043606e-05,
|
512 |
-
"loss": 0.
|
513 |
"step": 770
|
514 |
},
|
515 |
{
|
516 |
"epoch": 2.09,
|
517 |
"learning_rate": 1.694747274529237e-05,
|
518 |
-
"loss": 0.
|
519 |
"step": 780
|
520 |
},
|
521 |
{
|
522 |
"epoch": 2.11,
|
523 |
"learning_rate": 1.6451932606541132e-05,
|
524 |
-
"loss": 0.
|
525 |
"step": 790
|
526 |
},
|
527 |
{
|
528 |
"epoch": 2.14,
|
529 |
"learning_rate": 1.595639246778989e-05,
|
530 |
-
"loss": 0.
|
531 |
"step": 800
|
532 |
},
|
533 |
{
|
534 |
"epoch": 2.17,
|
535 |
"learning_rate": 1.5460852329038654e-05,
|
536 |
-
"loss": 0.
|
537 |
"step": 810
|
538 |
},
|
539 |
{
|
540 |
"epoch": 2.19,
|
541 |
"learning_rate": 1.4965312190287414e-05,
|
542 |
-
"loss": 0.
|
543 |
"step": 820
|
544 |
},
|
545 |
{
|
546 |
"epoch": 2.22,
|
547 |
"learning_rate": 1.4469772051536176e-05,
|
548 |
-
"loss": 0.
|
549 |
"step": 830
|
550 |
},
|
551 |
{
|
552 |
"epoch": 2.25,
|
553 |
"learning_rate": 1.3974231912784936e-05,
|
554 |
-
"loss": 0.
|
555 |
"step": 840
|
556 |
},
|
557 |
{
|
558 |
"epoch": 2.27,
|
559 |
"learning_rate": 1.3478691774033697e-05,
|
560 |
-
"loss": 0.
|
561 |
"step": 850
|
562 |
},
|
563 |
{
|
564 |
"epoch": 2.3,
|
565 |
"learning_rate": 1.298315163528246e-05,
|
566 |
-
"loss": 0.
|
567 |
"step": 860
|
568 |
},
|
569 |
{
|
570 |
"epoch": 2.33,
|
571 |
"learning_rate": 1.2487611496531219e-05,
|
572 |
-
"loss": 0.
|
573 |
"step": 870
|
574 |
},
|
575 |
{
|
576 |
"epoch": 2.35,
|
577 |
"learning_rate": 1.1992071357779982e-05,
|
578 |
-
"loss": 0.
|
579 |
"step": 880
|
580 |
},
|
581 |
{
|
582 |
"epoch": 2.38,
|
583 |
"learning_rate": 1.1496531219028741e-05,
|
584 |
-
"loss": 0.
|
585 |
"step": 890
|
586 |
},
|
587 |
{
|
588 |
"epoch": 2.41,
|
589 |
"learning_rate": 1.1000991080277504e-05,
|
590 |
-
"loss": 0.
|
591 |
"step": 900
|
592 |
},
|
593 |
{
|
594 |
"epoch": 2.43,
|
595 |
"learning_rate": 1.0505450941526264e-05,
|
596 |
-
"loss": 0.
|
597 |
"step": 910
|
598 |
},
|
599 |
{
|
600 |
"epoch": 2.46,
|
601 |
"learning_rate": 1.0009910802775026e-05,
|
602 |
-
"loss": 0.
|
603 |
"step": 920
|
604 |
},
|
605 |
{
|
606 |
"epoch": 2.49,
|
607 |
"learning_rate": 9.514370664023786e-06,
|
608 |
-
"loss": 0.
|
609 |
"step": 930
|
610 |
},
|
611 |
{
|
612 |
"epoch": 2.51,
|
613 |
"learning_rate": 9.018830525272549e-06,
|
614 |
-
"loss": 0.
|
615 |
"step": 940
|
616 |
},
|
617 |
{
|
618 |
"epoch": 2.54,
|
619 |
"learning_rate": 8.523290386521308e-06,
|
620 |
-
"loss": 0.
|
621 |
"step": 950
|
622 |
},
|
623 |
{
|
624 |
"epoch": 2.57,
|
625 |
"learning_rate": 8.02775024777007e-06,
|
626 |
-
"loss": 0.
|
627 |
"step": 960
|
628 |
},
|
629 |
{
|
630 |
"epoch": 2.59,
|
631 |
"learning_rate": 7.532210109018831e-06,
|
632 |
-
"loss": 0.
|
633 |
"step": 970
|
634 |
},
|
635 |
{
|
636 |
"epoch": 2.62,
|
637 |
"learning_rate": 7.036669970267593e-06,
|
638 |
-
"loss": 0.
|
639 |
"step": 980
|
640 |
},
|
641 |
{
|
642 |
"epoch": 2.65,
|
643 |
"learning_rate": 6.541129831516353e-06,
|
644 |
-
"loss": 0.
|
645 |
"step": 990
|
646 |
},
|
647 |
{
|
648 |
"epoch": 2.67,
|
649 |
"learning_rate": 6.045589692765114e-06,
|
650 |
-
"loss": 0.
|
651 |
"step": 1000
|
652 |
},
|
653 |
{
|
654 |
"epoch": 2.7,
|
655 |
"learning_rate": 5.5500495540138754e-06,
|
656 |
-
"loss": 0.
|
657 |
"step": 1010
|
658 |
},
|
659 |
{
|
660 |
"epoch": 2.73,
|
661 |
"learning_rate": 5.0545094152626366e-06,
|
662 |
-
"loss": 0.
|
663 |
"step": 1020
|
664 |
},
|
665 |
{
|
666 |
"epoch": 2.75,
|
667 |
"learning_rate": 4.558969276511398e-06,
|
668 |
-
"loss": 0.
|
669 |
"step": 1030
|
670 |
},
|
671 |
{
|
672 |
"epoch": 2.78,
|
673 |
"learning_rate": 4.063429137760159e-06,
|
674 |
-
"loss": 0.
|
675 |
"step": 1040
|
676 |
},
|
677 |
{
|
678 |
"epoch": 2.81,
|
679 |
"learning_rate": 3.56788899900892e-06,
|
680 |
-
"loss": 0.
|
681 |
"step": 1050
|
682 |
},
|
683 |
{
|
684 |
"epoch": 2.83,
|
685 |
"learning_rate": 3.072348860257681e-06,
|
686 |
-
"loss": 0.
|
687 |
"step": 1060
|
688 |
},
|
689 |
{
|
690 |
"epoch": 2.86,
|
691 |
"learning_rate": 2.576808721506442e-06,
|
692 |
-
"loss": 0.
|
693 |
"step": 1070
|
694 |
},
|
695 |
{
|
696 |
"epoch": 2.89,
|
697 |
"learning_rate": 2.081268582755203e-06,
|
698 |
-
"loss": 0.
|
699 |
"step": 1080
|
700 |
},
|
701 |
{
|
702 |
"epoch": 2.91,
|
703 |
"learning_rate": 1.5857284440039643e-06,
|
704 |
-
"loss": 0.
|
705 |
"step": 1090
|
706 |
},
|
707 |
{
|
708 |
"epoch": 2.94,
|
709 |
"learning_rate": 1.0901883052527254e-06,
|
710 |
-
"loss": 0.
|
711 |
"step": 1100
|
712 |
},
|
713 |
{
|
714 |
"epoch": 2.97,
|
715 |
"learning_rate": 5.946481665014866e-07,
|
716 |
-
"loss": 0.
|
717 |
"step": 1110
|
718 |
},
|
719 |
{
|
720 |
"epoch": 2.99,
|
721 |
"learning_rate": 9.910802775024777e-08,
|
722 |
-
"loss": 0.
|
723 |
"step": 1120
|
724 |
},
|
725 |
{
|
726 |
"epoch": 3.0,
|
727 |
-
"eval_accuracy": 0.
|
728 |
"eval_confusion_matrix": [
|
729 |
[
|
730 |
1506,
|
731 |
-
|
732 |
],
|
733 |
[
|
734 |
-
|
735 |
-
|
736 |
]
|
737 |
],
|
738 |
-
"eval_loss": 0.
|
739 |
-
"eval_precision": 0.
|
740 |
-
"eval_recall": 0.
|
741 |
-
"eval_runtime":
|
742 |
-
"eval_samples_per_second":
|
743 |
-
"eval_steps_per_second":
|
744 |
"step": 1122
|
745 |
},
|
746 |
{
|
747 |
"epoch": 3.0,
|
748 |
"step": 1122,
|
749 |
-
"total_flos": 8.
|
750 |
-
"train_loss": 0.
|
751 |
-
"train_runtime":
|
752 |
-
"train_samples_per_second": 32.
|
753 |
-
"train_steps_per_second": 1.
|
754 |
}
|
755 |
],
|
756 |
"logging_steps": 10,
|
757 |
"max_steps": 1122,
|
758 |
"num_train_epochs": 3,
|
759 |
"save_steps": 500,
|
760 |
-
"total_flos": 8.
|
761 |
"trial_name": null,
|
762 |
"trial_params": null
|
763 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9304580407890337,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-748",
|
4 |
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1122,
|
|
|
11 |
{
|
12 |
"epoch": 0.03,
|
13 |
"learning_rate": 4.424778761061947e-06,
|
14 |
+
"loss": 0.0218,
|
15 |
"step": 10
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.05,
|
19 |
"learning_rate": 8.849557522123894e-06,
|
20 |
+
"loss": 0.0608,
|
21 |
"step": 20
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.08,
|
25 |
"learning_rate": 1.3274336283185843e-05,
|
26 |
+
"loss": 0.1012,
|
27 |
"step": 30
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.11,
|
31 |
"learning_rate": 1.7699115044247787e-05,
|
32 |
+
"loss": 0.1097,
|
33 |
"step": 40
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.13,
|
37 |
"learning_rate": 2.2123893805309738e-05,
|
38 |
+
"loss": 0.0407,
|
39 |
"step": 50
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.16,
|
43 |
"learning_rate": 2.6548672566371686e-05,
|
44 |
+
"loss": 0.0788,
|
45 |
"step": 60
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.19,
|
49 |
"learning_rate": 3.097345132743363e-05,
|
50 |
+
"loss": 0.1467,
|
51 |
"step": 70
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.21,
|
55 |
"learning_rate": 3.5398230088495574e-05,
|
56 |
+
"loss": 0.0436,
|
57 |
"step": 80
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.24,
|
61 |
"learning_rate": 3.982300884955752e-05,
|
62 |
+
"loss": 0.0363,
|
63 |
"step": 90
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.27,
|
67 |
"learning_rate": 4.4247787610619477e-05,
|
68 |
+
"loss": 0.1346,
|
69 |
"step": 100
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.29,
|
73 |
"learning_rate": 4.867256637168142e-05,
|
74 |
+
"loss": 0.1131,
|
75 |
"step": 110
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.32,
|
79 |
"learning_rate": 4.9653121902874134e-05,
|
80 |
+
"loss": 0.0879,
|
81 |
"step": 120
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.35,
|
85 |
"learning_rate": 4.9157581764122896e-05,
|
86 |
+
"loss": 0.0898,
|
87 |
"step": 130
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.37,
|
91 |
"learning_rate": 4.866204162537166e-05,
|
92 |
+
"loss": 0.067,
|
93 |
"step": 140
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.4,
|
97 |
"learning_rate": 4.816650148662042e-05,
|
98 |
+
"loss": 0.0875,
|
99 |
"step": 150
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.43,
|
103 |
"learning_rate": 4.767096134786918e-05,
|
104 |
+
"loss": 0.1182,
|
105 |
"step": 160
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.45,
|
109 |
"learning_rate": 4.717542120911794e-05,
|
110 |
+
"loss": 0.0777,
|
111 |
"step": 170
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.48,
|
115 |
"learning_rate": 4.66798810703667e-05,
|
116 |
+
"loss": 0.1198,
|
117 |
"step": 180
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.51,
|
121 |
"learning_rate": 4.618434093161546e-05,
|
122 |
+
"loss": 0.1235,
|
123 |
"step": 190
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.53,
|
127 |
"learning_rate": 4.568880079286422e-05,
|
128 |
+
"loss": 0.0982,
|
129 |
"step": 200
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.56,
|
133 |
"learning_rate": 4.5193260654112984e-05,
|
134 |
+
"loss": 0.0373,
|
135 |
"step": 210
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.59,
|
139 |
"learning_rate": 4.4697720515361746e-05,
|
140 |
+
"loss": 0.1309,
|
141 |
"step": 220
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.61,
|
145 |
"learning_rate": 4.420218037661051e-05,
|
146 |
+
"loss": 0.0781,
|
147 |
"step": 230
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.64,
|
151 |
"learning_rate": 4.370664023785927e-05,
|
152 |
+
"loss": 0.1057,
|
153 |
"step": 240
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.67,
|
157 |
"learning_rate": 4.321110009910803e-05,
|
158 |
+
"loss": 0.1375,
|
159 |
"step": 250
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.7,
|
163 |
"learning_rate": 4.27155599603568e-05,
|
164 |
+
"loss": 0.0338,
|
165 |
"step": 260
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.72,
|
169 |
"learning_rate": 4.222001982160555e-05,
|
170 |
+
"loss": 0.1145,
|
171 |
"step": 270
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.75,
|
175 |
"learning_rate": 4.172447968285431e-05,
|
176 |
+
"loss": 0.0874,
|
177 |
"step": 280
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.78,
|
181 |
"learning_rate": 4.122893954410307e-05,
|
182 |
+
"loss": 0.1257,
|
183 |
"step": 290
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.8,
|
187 |
"learning_rate": 4.0733399405351834e-05,
|
188 |
+
"loss": 0.09,
|
189 |
"step": 300
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.83,
|
193 |
"learning_rate": 4.0237859266600596e-05,
|
194 |
+
"loss": 0.0619,
|
195 |
"step": 310
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.86,
|
199 |
"learning_rate": 3.9742319127849357e-05,
|
200 |
+
"loss": 0.0678,
|
201 |
"step": 320
|
202 |
},
|
203 |
{
|
204 |
"epoch": 0.88,
|
205 |
"learning_rate": 3.924677898909812e-05,
|
206 |
+
"loss": 0.1208,
|
207 |
"step": 330
|
208 |
},
|
209 |
{
|
210 |
"epoch": 0.91,
|
211 |
"learning_rate": 3.8751238850346886e-05,
|
212 |
+
"loss": 0.0344,
|
213 |
"step": 340
|
214 |
},
|
215 |
{
|
216 |
"epoch": 0.94,
|
217 |
"learning_rate": 3.825569871159564e-05,
|
218 |
+
"loss": 0.1028,
|
219 |
"step": 350
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.96,
|
223 |
"learning_rate": 3.77601585728444e-05,
|
224 |
+
"loss": 0.0468,
|
225 |
"step": 360
|
226 |
},
|
227 |
{
|
228 |
"epoch": 0.99,
|
229 |
"learning_rate": 3.726461843409316e-05,
|
230 |
+
"loss": 0.0727,
|
231 |
"step": 370
|
232 |
},
|
233 |
{
|
234 |
"epoch": 1.0,
|
235 |
+
"eval_accuracy": 0.905717151454363,
|
236 |
"eval_confusion_matrix": [
|
237 |
[
|
238 |
+
1508,
|
239 |
+
3
|
240 |
],
|
241 |
[
|
242 |
+
279,
|
243 |
+
1201
|
244 |
]
|
245 |
],
|
246 |
+
"eval_loss": 0.29149046540260315,
|
247 |
+
"eval_precision": 0.9198941847825107,
|
248 |
+
"eval_recall": 0.905717151454363,
|
249 |
+
"eval_runtime": 59.6464,
|
250 |
+
"eval_samples_per_second": 50.146,
|
251 |
+
"eval_steps_per_second": 6.27,
|
252 |
"step": 374
|
253 |
},
|
254 |
{
|
255 |
"epoch": 1.02,
|
256 |
"learning_rate": 3.676907829534192e-05,
|
257 |
+
"loss": 0.0519,
|
258 |
"step": 380
|
259 |
},
|
260 |
{
|
261 |
"epoch": 1.04,
|
262 |
"learning_rate": 3.6273538156590684e-05,
|
263 |
+
"loss": 0.093,
|
264 |
"step": 390
|
265 |
},
|
266 |
{
|
267 |
"epoch": 1.07,
|
268 |
"learning_rate": 3.5777998017839445e-05,
|
269 |
+
"loss": 0.0575,
|
270 |
"step": 400
|
271 |
},
|
272 |
{
|
273 |
"epoch": 1.1,
|
274 |
"learning_rate": 3.5282457879088207e-05,
|
275 |
+
"loss": 0.0909,
|
276 |
"step": 410
|
277 |
},
|
278 |
{
|
279 |
"epoch": 1.12,
|
280 |
"learning_rate": 3.4786917740336974e-05,
|
281 |
+
"loss": 0.0944,
|
282 |
"step": 420
|
283 |
},
|
284 |
{
|
285 |
"epoch": 1.15,
|
286 |
"learning_rate": 3.429137760158573e-05,
|
287 |
+
"loss": 0.0738,
|
288 |
"step": 430
|
289 |
},
|
290 |
{
|
291 |
"epoch": 1.18,
|
292 |
"learning_rate": 3.379583746283449e-05,
|
293 |
+
"loss": 0.1116,
|
294 |
"step": 440
|
295 |
},
|
296 |
{
|
297 |
"epoch": 1.2,
|
298 |
"learning_rate": 3.330029732408325e-05,
|
299 |
+
"loss": 0.0861,
|
300 |
"step": 450
|
301 |
},
|
302 |
{
|
303 |
"epoch": 1.23,
|
304 |
"learning_rate": 3.280475718533201e-05,
|
305 |
+
"loss": 0.0376,
|
306 |
"step": 460
|
307 |
},
|
308 |
{
|
309 |
"epoch": 1.26,
|
310 |
"learning_rate": 3.230921704658077e-05,
|
311 |
+
"loss": 0.0339,
|
312 |
"step": 470
|
313 |
},
|
314 |
{
|
315 |
"epoch": 1.28,
|
316 |
"learning_rate": 3.1813676907829534e-05,
|
317 |
+
"loss": 0.0791,
|
318 |
"step": 480
|
319 |
},
|
320 |
{
|
321 |
"epoch": 1.31,
|
322 |
"learning_rate": 3.13181367690783e-05,
|
323 |
+
"loss": 0.0621,
|
324 |
"step": 490
|
325 |
},
|
326 |
{
|
327 |
"epoch": 1.34,
|
328 |
"learning_rate": 3.0822596630327057e-05,
|
329 |
+
"loss": 0.0911,
|
330 |
"step": 500
|
331 |
},
|
332 |
{
|
333 |
"epoch": 1.36,
|
334 |
"learning_rate": 3.0327056491575818e-05,
|
335 |
+
"loss": 0.0688,
|
336 |
"step": 510
|
337 |
},
|
338 |
{
|
339 |
"epoch": 1.39,
|
340 |
"learning_rate": 2.983151635282458e-05,
|
341 |
+
"loss": 0.0797,
|
342 |
"step": 520
|
343 |
},
|
344 |
{
|
345 |
"epoch": 1.42,
|
346 |
"learning_rate": 2.933597621407334e-05,
|
347 |
+
"loss": 0.0315,
|
348 |
"step": 530
|
349 |
},
|
350 |
{
|
351 |
"epoch": 1.44,
|
352 |
"learning_rate": 2.88404360753221e-05,
|
353 |
+
"loss": 0.0703,
|
354 |
"step": 540
|
355 |
},
|
356 |
{
|
357 |
"epoch": 1.47,
|
358 |
"learning_rate": 2.8344895936570865e-05,
|
359 |
+
"loss": 0.0482,
|
360 |
"step": 550
|
361 |
},
|
362 |
{
|
363 |
"epoch": 1.5,
|
364 |
"learning_rate": 2.7849355797819627e-05,
|
365 |
+
"loss": 0.0723,
|
366 |
"step": 560
|
367 |
},
|
368 |
{
|
369 |
"epoch": 1.52,
|
370 |
"learning_rate": 2.7353815659068388e-05,
|
371 |
+
"loss": 0.067,
|
372 |
"step": 570
|
373 |
},
|
374 |
{
|
375 |
"epoch": 1.55,
|
376 |
"learning_rate": 2.6858275520317145e-05,
|
377 |
+
"loss": 0.0432,
|
378 |
"step": 580
|
379 |
},
|
380 |
{
|
381 |
"epoch": 1.58,
|
382 |
"learning_rate": 2.6362735381565906e-05,
|
383 |
+
"loss": 0.0915,
|
384 |
"step": 590
|
385 |
},
|
386 |
{
|
387 |
"epoch": 1.6,
|
388 |
"learning_rate": 2.5867195242814668e-05,
|
389 |
+
"loss": 0.0428,
|
390 |
"step": 600
|
391 |
},
|
392 |
{
|
393 |
"epoch": 1.63,
|
394 |
"learning_rate": 2.537165510406343e-05,
|
395 |
+
"loss": 0.0547,
|
396 |
"step": 610
|
397 |
},
|
398 |
{
|
399 |
"epoch": 1.66,
|
400 |
"learning_rate": 2.4876114965312193e-05,
|
401 |
+
"loss": 0.0834,
|
402 |
"step": 620
|
403 |
},
|
404 |
{
|
405 |
"epoch": 1.68,
|
406 |
"learning_rate": 2.4380574826560954e-05,
|
407 |
+
"loss": 0.1056,
|
408 |
"step": 630
|
409 |
},
|
410 |
{
|
411 |
"epoch": 1.71,
|
412 |
"learning_rate": 2.3885034687809712e-05,
|
413 |
+
"loss": 0.0595,
|
414 |
"step": 640
|
415 |
},
|
416 |
{
|
417 |
"epoch": 1.74,
|
418 |
"learning_rate": 2.3389494549058473e-05,
|
419 |
+
"loss": 0.0547,
|
420 |
"step": 650
|
421 |
},
|
422 |
{
|
423 |
"epoch": 1.76,
|
424 |
"learning_rate": 2.2893954410307238e-05,
|
425 |
+
"loss": 0.0575,
|
426 |
"step": 660
|
427 |
},
|
428 |
{
|
429 |
"epoch": 1.79,
|
430 |
"learning_rate": 2.2398414271556e-05,
|
431 |
+
"loss": 0.0444,
|
432 |
"step": 670
|
433 |
},
|
434 |
{
|
435 |
"epoch": 1.82,
|
436 |
"learning_rate": 2.1902874132804756e-05,
|
437 |
+
"loss": 0.0269,
|
438 |
"step": 680
|
439 |
},
|
440 |
{
|
441 |
"epoch": 1.84,
|
442 |
"learning_rate": 2.1407333994053518e-05,
|
443 |
+
"loss": 0.0118,
|
444 |
"step": 690
|
445 |
},
|
446 |
{
|
447 |
"epoch": 1.87,
|
448 |
"learning_rate": 2.0911793855302282e-05,
|
449 |
+
"loss": 0.0489,
|
450 |
"step": 700
|
451 |
},
|
452 |
{
|
453 |
"epoch": 1.9,
|
454 |
"learning_rate": 2.0416253716551043e-05,
|
455 |
+
"loss": 0.1239,
|
456 |
"step": 710
|
457 |
},
|
458 |
{
|
459 |
"epoch": 1.93,
|
460 |
"learning_rate": 1.99207135777998e-05,
|
461 |
+
"loss": 0.0958,
|
462 |
"step": 720
|
463 |
},
|
464 |
{
|
465 |
"epoch": 1.95,
|
466 |
"learning_rate": 1.9425173439048562e-05,
|
467 |
+
"loss": 0.1,
|
468 |
"step": 730
|
469 |
},
|
470 |
{
|
471 |
"epoch": 1.98,
|
472 |
"learning_rate": 1.8929633300297326e-05,
|
473 |
+
"loss": 0.0635,
|
474 |
"step": 740
|
475 |
},
|
476 |
{
|
477 |
"epoch": 2.0,
|
478 |
+
"eval_accuracy": 0.9304580407890337,
|
479 |
"eval_confusion_matrix": [
|
480 |
[
|
481 |
+
1505,
|
482 |
+
6
|
483 |
],
|
484 |
[
|
485 |
+
202,
|
486 |
+
1278
|
487 |
]
|
488 |
],
|
489 |
+
"eval_loss": 0.17639653384685516,
|
490 |
+
"eval_precision": 0.9379063923736161,
|
491 |
+
"eval_recall": 0.9304580407890337,
|
492 |
+
"eval_runtime": 59.9361,
|
493 |
+
"eval_samples_per_second": 49.903,
|
494 |
+
"eval_steps_per_second": 6.24,
|
495 |
"step": 748
|
496 |
},
|
497 |
{
|
498 |
"epoch": 2.01,
|
499 |
"learning_rate": 1.8434093161546088e-05,
|
500 |
+
"loss": 0.0345,
|
501 |
"step": 750
|
502 |
},
|
503 |
{
|
504 |
"epoch": 2.03,
|
505 |
"learning_rate": 1.7938553022794845e-05,
|
506 |
+
"loss": 0.0866,
|
507 |
"step": 760
|
508 |
},
|
509 |
{
|
510 |
"epoch": 2.06,
|
511 |
"learning_rate": 1.7443012884043606e-05,
|
512 |
+
"loss": 0.0151,
|
513 |
"step": 770
|
514 |
},
|
515 |
{
|
516 |
"epoch": 2.09,
|
517 |
"learning_rate": 1.694747274529237e-05,
|
518 |
+
"loss": 0.0656,
|
519 |
"step": 780
|
520 |
},
|
521 |
{
|
522 |
"epoch": 2.11,
|
523 |
"learning_rate": 1.6451932606541132e-05,
|
524 |
+
"loss": 0.0597,
|
525 |
"step": 790
|
526 |
},
|
527 |
{
|
528 |
"epoch": 2.14,
|
529 |
"learning_rate": 1.595639246778989e-05,
|
530 |
+
"loss": 0.0368,
|
531 |
"step": 800
|
532 |
},
|
533 |
{
|
534 |
"epoch": 2.17,
|
535 |
"learning_rate": 1.5460852329038654e-05,
|
536 |
+
"loss": 0.0472,
|
537 |
"step": 810
|
538 |
},
|
539 |
{
|
540 |
"epoch": 2.19,
|
541 |
"learning_rate": 1.4965312190287414e-05,
|
542 |
+
"loss": 0.082,
|
543 |
"step": 820
|
544 |
},
|
545 |
{
|
546 |
"epoch": 2.22,
|
547 |
"learning_rate": 1.4469772051536176e-05,
|
548 |
+
"loss": 0.0437,
|
549 |
"step": 830
|
550 |
},
|
551 |
{
|
552 |
"epoch": 2.25,
|
553 |
"learning_rate": 1.3974231912784936e-05,
|
554 |
+
"loss": 0.0298,
|
555 |
"step": 840
|
556 |
},
|
557 |
{
|
558 |
"epoch": 2.27,
|
559 |
"learning_rate": 1.3478691774033697e-05,
|
560 |
+
"loss": 0.0314,
|
561 |
"step": 850
|
562 |
},
|
563 |
{
|
564 |
"epoch": 2.3,
|
565 |
"learning_rate": 1.298315163528246e-05,
|
566 |
+
"loss": 0.0419,
|
567 |
"step": 860
|
568 |
},
|
569 |
{
|
570 |
"epoch": 2.33,
|
571 |
"learning_rate": 1.2487611496531219e-05,
|
572 |
+
"loss": 0.0314,
|
573 |
"step": 870
|
574 |
},
|
575 |
{
|
576 |
"epoch": 2.35,
|
577 |
"learning_rate": 1.1992071357779982e-05,
|
578 |
+
"loss": 0.0206,
|
579 |
"step": 880
|
580 |
},
|
581 |
{
|
582 |
"epoch": 2.38,
|
583 |
"learning_rate": 1.1496531219028741e-05,
|
584 |
+
"loss": 0.0667,
|
585 |
"step": 890
|
586 |
},
|
587 |
{
|
588 |
"epoch": 2.41,
|
589 |
"learning_rate": 1.1000991080277504e-05,
|
590 |
+
"loss": 0.0498,
|
591 |
"step": 900
|
592 |
},
|
593 |
{
|
594 |
"epoch": 2.43,
|
595 |
"learning_rate": 1.0505450941526264e-05,
|
596 |
+
"loss": 0.0168,
|
597 |
"step": 910
|
598 |
},
|
599 |
{
|
600 |
"epoch": 2.46,
|
601 |
"learning_rate": 1.0009910802775026e-05,
|
602 |
+
"loss": 0.0458,
|
603 |
"step": 920
|
604 |
},
|
605 |
{
|
606 |
"epoch": 2.49,
|
607 |
"learning_rate": 9.514370664023786e-06,
|
608 |
+
"loss": 0.0292,
|
609 |
"step": 930
|
610 |
},
|
611 |
{
|
612 |
"epoch": 2.51,
|
613 |
"learning_rate": 9.018830525272549e-06,
|
614 |
+
"loss": 0.0849,
|
615 |
"step": 940
|
616 |
},
|
617 |
{
|
618 |
"epoch": 2.54,
|
619 |
"learning_rate": 8.523290386521308e-06,
|
620 |
+
"loss": 0.0332,
|
621 |
"step": 950
|
622 |
},
|
623 |
{
|
624 |
"epoch": 2.57,
|
625 |
"learning_rate": 8.02775024777007e-06,
|
626 |
+
"loss": 0.0523,
|
627 |
"step": 960
|
628 |
},
|
629 |
{
|
630 |
"epoch": 2.59,
|
631 |
"learning_rate": 7.532210109018831e-06,
|
632 |
+
"loss": 0.0458,
|
633 |
"step": 970
|
634 |
},
|
635 |
{
|
636 |
"epoch": 2.62,
|
637 |
"learning_rate": 7.036669970267593e-06,
|
638 |
+
"loss": 0.0254,
|
639 |
"step": 980
|
640 |
},
|
641 |
{
|
642 |
"epoch": 2.65,
|
643 |
"learning_rate": 6.541129831516353e-06,
|
644 |
+
"loss": 0.0504,
|
645 |
"step": 990
|
646 |
},
|
647 |
{
|
648 |
"epoch": 2.67,
|
649 |
"learning_rate": 6.045589692765114e-06,
|
650 |
+
"loss": 0.0441,
|
651 |
"step": 1000
|
652 |
},
|
653 |
{
|
654 |
"epoch": 2.7,
|
655 |
"learning_rate": 5.5500495540138754e-06,
|
656 |
+
"loss": 0.0362,
|
657 |
"step": 1010
|
658 |
},
|
659 |
{
|
660 |
"epoch": 2.73,
|
661 |
"learning_rate": 5.0545094152626366e-06,
|
662 |
+
"loss": 0.0589,
|
663 |
"step": 1020
|
664 |
},
|
665 |
{
|
666 |
"epoch": 2.75,
|
667 |
"learning_rate": 4.558969276511398e-06,
|
668 |
+
"loss": 0.0199,
|
669 |
"step": 1030
|
670 |
},
|
671 |
{
|
672 |
"epoch": 2.78,
|
673 |
"learning_rate": 4.063429137760159e-06,
|
674 |
+
"loss": 0.0215,
|
675 |
"step": 1040
|
676 |
},
|
677 |
{
|
678 |
"epoch": 2.81,
|
679 |
"learning_rate": 3.56788899900892e-06,
|
680 |
+
"loss": 0.0281,
|
681 |
"step": 1050
|
682 |
},
|
683 |
{
|
684 |
"epoch": 2.83,
|
685 |
"learning_rate": 3.072348860257681e-06,
|
686 |
+
"loss": 0.0395,
|
687 |
"step": 1060
|
688 |
},
|
689 |
{
|
690 |
"epoch": 2.86,
|
691 |
"learning_rate": 2.576808721506442e-06,
|
692 |
+
"loss": 0.0603,
|
693 |
"step": 1070
|
694 |
},
|
695 |
{
|
696 |
"epoch": 2.89,
|
697 |
"learning_rate": 2.081268582755203e-06,
|
698 |
+
"loss": 0.0299,
|
699 |
"step": 1080
|
700 |
},
|
701 |
{
|
702 |
"epoch": 2.91,
|
703 |
"learning_rate": 1.5857284440039643e-06,
|
704 |
+
"loss": 0.0488,
|
705 |
"step": 1090
|
706 |
},
|
707 |
{
|
708 |
"epoch": 2.94,
|
709 |
"learning_rate": 1.0901883052527254e-06,
|
710 |
+
"loss": 0.0206,
|
711 |
"step": 1100
|
712 |
},
|
713 |
{
|
714 |
"epoch": 2.97,
|
715 |
"learning_rate": 5.946481665014866e-07,
|
716 |
+
"loss": 0.0205,
|
717 |
"step": 1110
|
718 |
},
|
719 |
{
|
720 |
"epoch": 2.99,
|
721 |
"learning_rate": 9.910802775024777e-08,
|
722 |
+
"loss": 0.0396,
|
723 |
"step": 1120
|
724 |
},
|
725 |
{
|
726 |
"epoch": 3.0,
|
727 |
+
"eval_accuracy": 0.8993647609495152,
|
728 |
"eval_confusion_matrix": [
|
729 |
[
|
730 |
1506,
|
731 |
+
5
|
732 |
],
|
733 |
[
|
734 |
+
296,
|
735 |
+
1184
|
736 |
]
|
737 |
],
|
738 |
+
"eval_loss": 0.2879287004470825,
|
739 |
+
"eval_precision": 0.914936979126043,
|
740 |
+
"eval_recall": 0.8993647609495152,
|
741 |
+
"eval_runtime": 61.2494,
|
742 |
+
"eval_samples_per_second": 48.833,
|
743 |
+
"eval_steps_per_second": 6.106,
|
744 |
"step": 1122
|
745 |
},
|
746 |
{
|
747 |
"epoch": 3.0,
|
748 |
"step": 1122,
|
749 |
+
"total_flos": 8.924294285481738e+17,
|
750 |
+
"train_loss": 0.06514118614095245,
|
751 |
+
"train_runtime": 1099.2319,
|
752 |
+
"train_samples_per_second": 32.663,
|
753 |
+
"train_steps_per_second": 1.021
|
754 |
}
|
755 |
],
|
756 |
"logging_steps": 10,
|
757 |
"max_steps": 1122,
|
758 |
"num_train_epochs": 3,
|
759 |
"save_steps": 500,
|
760 |
+
"total_flos": 8.924294285481738e+17,
|
761 |
"trial_name": null,
|
762 |
"trial_params": null
|
763 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba0836a3bceb1649ba314ad98db1212abc6ff6b9b4c6c91de913dcd1e8190f62
|
3 |
size 4664
|