Model save
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/May29_07-42-30_project/events.out.tfevents.1685346162.project.185939.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +335 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 5.983391481940132e+18,
|
4 |
+
"train_loss": 0.1365605974694093,
|
5 |
+
"train_runtime": 14584.4296,
|
6 |
+
"train_samples_per_second": 5.236,
|
7 |
+
"train_steps_per_second": 0.021
|
8 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 347601681
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cb2f074f487ea047260d859056c3dfa5f0280574f7c1c17902155587eb0608a
|
3 |
size 347601681
|
runs/May29_07-42-30_project/events.out.tfevents.1685346162.project.185939.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce52e40d7cdf1fdceb1ffc3d868bc33b3db9cb261e25f56fb11d25bfc5d7e646
|
3 |
+
size 14997
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 5.983391481940132e+18,
|
4 |
+
"train_loss": 0.1365605974694093,
|
5 |
+
"train_runtime": 14584.4296,
|
6 |
+
"train_samples_per_second": 5.236,
|
7 |
+
"train_steps_per_second": 0.021
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,335 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9760408483896308,
|
3 |
+
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_12/checkpoint-270",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 300,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.33,
|
12 |
+
"learning_rate": 3.3333333333333335e-05,
|
13 |
+
"loss": 1.3016,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.67,
|
18 |
+
"learning_rate": 6.666666666666667e-05,
|
19 |
+
"loss": 0.6828,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"learning_rate": 0.0001,
|
25 |
+
"loss": 0.3644,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"eval_accuracy": 0.8955223880597015,
|
31 |
+
"eval_f1_score": 0.8974001833670424,
|
32 |
+
"eval_loss": 0.29182684421539307,
|
33 |
+
"eval_precision": 0.907029413169219,
|
34 |
+
"eval_runtime": 141.6635,
|
35 |
+
"eval_samples_per_second": 17.972,
|
36 |
+
"eval_sensitivity": 0.8957445034204233,
|
37 |
+
"eval_specificity": 0.9733575562525472,
|
38 |
+
"eval_steps_per_second": 0.282,
|
39 |
+
"step": 30
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.33,
|
43 |
+
"learning_rate": 9.62962962962963e-05,
|
44 |
+
"loss": 0.2491,
|
45 |
+
"step": 40
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.67,
|
49 |
+
"learning_rate": 9.25925925925926e-05,
|
50 |
+
"loss": 0.1871,
|
51 |
+
"step": 50
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 2.0,
|
55 |
+
"learning_rate": 8.888888888888889e-05,
|
56 |
+
"loss": 0.2177,
|
57 |
+
"step": 60
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 2.0,
|
61 |
+
"eval_accuracy": 0.9151610369206599,
|
62 |
+
"eval_f1_score": 0.9154763574988526,
|
63 |
+
"eval_loss": 0.231949582695961,
|
64 |
+
"eval_precision": 0.9237202260263041,
|
65 |
+
"eval_runtime": 141.1838,
|
66 |
+
"eval_samples_per_second": 18.033,
|
67 |
+
"eval_sensitivity": 0.9156321134434031,
|
68 |
+
"eval_specificity": 0.9785744694099139,
|
69 |
+
"eval_steps_per_second": 0.283,
|
70 |
+
"step": 60
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 2.33,
|
74 |
+
"learning_rate": 8.518518518518518e-05,
|
75 |
+
"loss": 0.1231,
|
76 |
+
"step": 70
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 2.67,
|
80 |
+
"learning_rate": 8.148148148148148e-05,
|
81 |
+
"loss": 0.1208,
|
82 |
+
"step": 80
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 3.0,
|
86 |
+
"learning_rate": 7.777777777777778e-05,
|
87 |
+
"loss": 0.1171,
|
88 |
+
"step": 90
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 3.0,
|
92 |
+
"eval_accuracy": 0.9489395129615082,
|
93 |
+
"eval_f1_score": 0.9493719922653666,
|
94 |
+
"eval_loss": 0.1653948426246643,
|
95 |
+
"eval_precision": 0.9531974738275035,
|
96 |
+
"eval_runtime": 141.9016,
|
97 |
+
"eval_samples_per_second": 17.942,
|
98 |
+
"eval_sensitivity": 0.9492288551886346,
|
99 |
+
"eval_specificity": 0.9871567326622118,
|
100 |
+
"eval_steps_per_second": 0.282,
|
101 |
+
"step": 90
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 3.33,
|
105 |
+
"learning_rate": 7.407407407407407e-05,
|
106 |
+
"loss": 0.0833,
|
107 |
+
"step": 100
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.67,
|
111 |
+
"learning_rate": 7.037037037037038e-05,
|
112 |
+
"loss": 0.0658,
|
113 |
+
"step": 110
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 4.0,
|
117 |
+
"learning_rate": 6.666666666666667e-05,
|
118 |
+
"loss": 0.068,
|
119 |
+
"step": 120
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 4.0,
|
123 |
+
"eval_accuracy": 0.9450117831893166,
|
124 |
+
"eval_f1_score": 0.9450733960859783,
|
125 |
+
"eval_loss": 0.15997998416423798,
|
126 |
+
"eval_precision": 0.9465681527498646,
|
127 |
+
"eval_runtime": 141.3669,
|
128 |
+
"eval_samples_per_second": 18.01,
|
129 |
+
"eval_sensitivity": 0.9454632114511998,
|
130 |
+
"eval_specificity": 0.986114525355863,
|
131 |
+
"eval_steps_per_second": 0.283,
|
132 |
+
"step": 120
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 4.33,
|
136 |
+
"learning_rate": 6.296296296296296e-05,
|
137 |
+
"loss": 0.0632,
|
138 |
+
"step": 130
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 4.67,
|
142 |
+
"learning_rate": 5.925925925925926e-05,
|
143 |
+
"loss": 0.0664,
|
144 |
+
"step": 140
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 5.0,
|
148 |
+
"learning_rate": 5.555555555555556e-05,
|
149 |
+
"loss": 0.0499,
|
150 |
+
"step": 150
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 5.0,
|
154 |
+
"eval_accuracy": 0.9654359780047133,
|
155 |
+
"eval_f1_score": 0.9655558479515587,
|
156 |
+
"eval_loss": 0.0947260707616806,
|
157 |
+
"eval_precision": 0.9656214890103378,
|
158 |
+
"eval_runtime": 140.2722,
|
159 |
+
"eval_samples_per_second": 18.15,
|
160 |
+
"eval_sensitivity": 0.9656782254257974,
|
161 |
+
"eval_specificity": 0.9912799165215678,
|
162 |
+
"eval_steps_per_second": 0.285,
|
163 |
+
"step": 150
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 5.33,
|
167 |
+
"learning_rate": 5.185185185185185e-05,
|
168 |
+
"loss": 0.0397,
|
169 |
+
"step": 160
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 5.67,
|
173 |
+
"learning_rate": 4.814814814814815e-05,
|
174 |
+
"loss": 0.0364,
|
175 |
+
"step": 170
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 6.0,
|
179 |
+
"learning_rate": 4.4444444444444447e-05,
|
180 |
+
"loss": 0.0302,
|
181 |
+
"step": 180
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 6.0,
|
185 |
+
"eval_accuracy": 0.9713275726630007,
|
186 |
+
"eval_f1_score": 0.9713961045425188,
|
187 |
+
"eval_loss": 0.08822068572044373,
|
188 |
+
"eval_precision": 0.9714994973822426,
|
189 |
+
"eval_runtime": 140.5761,
|
190 |
+
"eval_samples_per_second": 18.111,
|
191 |
+
"eval_sensitivity": 0.9715333079033974,
|
192 |
+
"eval_specificity": 0.9927834971929292,
|
193 |
+
"eval_steps_per_second": 0.285,
|
194 |
+
"step": 180
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 6.33,
|
198 |
+
"learning_rate": 4.074074074074074e-05,
|
199 |
+
"loss": 0.0221,
|
200 |
+
"step": 190
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 6.67,
|
204 |
+
"learning_rate": 3.7037037037037037e-05,
|
205 |
+
"loss": 0.0299,
|
206 |
+
"step": 200
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 7.0,
|
210 |
+
"learning_rate": 3.3333333333333335e-05,
|
211 |
+
"loss": 0.0207,
|
212 |
+
"step": 210
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 7.0,
|
216 |
+
"eval_accuracy": 0.9697564807541241,
|
217 |
+
"eval_f1_score": 0.9698988819326013,
|
218 |
+
"eval_loss": 0.10023057460784912,
|
219 |
+
"eval_precision": 0.9707690938825231,
|
220 |
+
"eval_runtime": 141.3669,
|
221 |
+
"eval_samples_per_second": 18.01,
|
222 |
+
"eval_sensitivity": 0.9698979472474506,
|
223 |
+
"eval_specificity": 0.9924055150633387,
|
224 |
+
"eval_steps_per_second": 0.283,
|
225 |
+
"step": 210
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 7.33,
|
229 |
+
"learning_rate": 2.962962962962963e-05,
|
230 |
+
"loss": 0.0238,
|
231 |
+
"step": 220
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 7.67,
|
235 |
+
"learning_rate": 2.5925925925925925e-05,
|
236 |
+
"loss": 0.0232,
|
237 |
+
"step": 230
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 8.0,
|
241 |
+
"learning_rate": 2.2222222222222223e-05,
|
242 |
+
"loss": 0.0205,
|
243 |
+
"step": 240
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 8.0,
|
247 |
+
"eval_accuracy": 0.9524744697564808,
|
248 |
+
"eval_f1_score": 0.9521142281383307,
|
249 |
+
"eval_loss": 0.15503662824630737,
|
250 |
+
"eval_precision": 0.9544453536467878,
|
251 |
+
"eval_runtime": 139.2147,
|
252 |
+
"eval_samples_per_second": 18.288,
|
253 |
+
"eval_sensitivity": 0.9528977045128385,
|
254 |
+
"eval_specificity": 0.9880677808840496,
|
255 |
+
"eval_steps_per_second": 0.287,
|
256 |
+
"step": 240
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 8.33,
|
260 |
+
"learning_rate": 1.8518518518518518e-05,
|
261 |
+
"loss": 0.0166,
|
262 |
+
"step": 250
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 8.67,
|
266 |
+
"learning_rate": 1.4814814814814815e-05,
|
267 |
+
"loss": 0.0184,
|
268 |
+
"step": 260
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 9.0,
|
272 |
+
"learning_rate": 1.1111111111111112e-05,
|
273 |
+
"loss": 0.0163,
|
274 |
+
"step": 270
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 9.0,
|
278 |
+
"eval_accuracy": 0.9760408483896308,
|
279 |
+
"eval_f1_score": 0.9760955386577261,
|
280 |
+
"eval_loss": 0.07892601191997528,
|
281 |
+
"eval_precision": 0.9762470546227865,
|
282 |
+
"eval_runtime": 142.9926,
|
283 |
+
"eval_samples_per_second": 17.805,
|
284 |
+
"eval_sensitivity": 0.976185641458774,
|
285 |
+
"eval_specificity": 0.9939801768095587,
|
286 |
+
"eval_steps_per_second": 0.28,
|
287 |
+
"step": 270
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 9.33,
|
291 |
+
"learning_rate": 7.4074074074074075e-06,
|
292 |
+
"loss": 0.0108,
|
293 |
+
"step": 280
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 9.67,
|
297 |
+
"learning_rate": 3.7037037037037037e-06,
|
298 |
+
"loss": 0.0097,
|
299 |
+
"step": 290
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 10.0,
|
303 |
+
"learning_rate": 0.0,
|
304 |
+
"loss": 0.0181,
|
305 |
+
"step": 300
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 10.0,
|
309 |
+
"eval_accuracy": 0.9736842105263158,
|
310 |
+
"eval_f1_score": 0.9737106615818243,
|
311 |
+
"eval_loss": 0.09225168079137802,
|
312 |
+
"eval_precision": 0.973953427126813,
|
313 |
+
"eval_runtime": 141.4794,
|
314 |
+
"eval_samples_per_second": 17.996,
|
315 |
+
"eval_sensitivity": 0.9738430623943066,
|
316 |
+
"eval_specificity": 0.9933886802049243,
|
317 |
+
"eval_steps_per_second": 0.283,
|
318 |
+
"step": 300
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 10.0,
|
322 |
+
"step": 300,
|
323 |
+
"total_flos": 5.983391481940132e+18,
|
324 |
+
"train_loss": 0.1365605974694093,
|
325 |
+
"train_runtime": 14584.4296,
|
326 |
+
"train_samples_per_second": 5.236,
|
327 |
+
"train_steps_per_second": 0.021
|
328 |
+
}
|
329 |
+
],
|
330 |
+
"max_steps": 300,
|
331 |
+
"num_train_epochs": 10,
|
332 |
+
"total_flos": 5.983391481940132e+18,
|
333 |
+
"trial_name": null,
|
334 |
+
"trial_params": null
|
335 |
+
}
|