Model save
Browse files
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.81,
|
3 |
+
"total_flos": 4.0507959904511017e+18,
|
4 |
+
"train_loss": 0.25211207201847663,
|
5 |
+
"train_runtime": 12845.6349,
|
6 |
+
"train_samples_per_second": 4.1,
|
7 |
+
"train_steps_per_second": 0.01
|
8 |
+
}
|
runs/May24_20-40-57_project/events.out.tfevents.1684960883.project.76576.0
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:a4b63cbd7be077d46351feca98fd92d6e770d3e4719bcd122eef20cfd6ed096b
|
3 |
+
size 11197
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.81,
|
3 |
+
"total_flos": 4.0507959904511017e+18,
|
4 |
+
"train_loss": 0.25211207201847663,
|
5 |
+
"train_runtime": 12845.6349,
|
6 |
+
"train_samples_per_second": 4.1,
|
7 |
+
"train_steps_per_second": 0.01
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9698177676537585,
|
3 |
+
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_05/checkpoint-130",
|
4 |
+
"epoch": 9.81132075471698,
|
5 |
+
"global_step": 130,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.75,
|
12 |
+
"learning_rate": 3.846153846153846e-05,
|
13 |
+
"loss": 1.3233,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.98,
|
18 |
+
"eval_accuracy": 0.7813211845102506,
|
19 |
+
"eval_f1_score": 0.7712648163133784,
|
20 |
+
"eval_loss": 0.7675661444664001,
|
21 |
+
"eval_precision": 0.7795759501080758,
|
22 |
+
"eval_runtime": 101.0485,
|
23 |
+
"eval_samples_per_second": 17.378,
|
24 |
+
"eval_steps_per_second": 0.178,
|
25 |
+
"step": 13
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.51,
|
29 |
+
"learning_rate": 4.700854700854701e-05,
|
30 |
+
"loss": 0.6659,
|
31 |
+
"step": 20
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 1.96,
|
35 |
+
"eval_accuracy": 0.9145785876993167,
|
36 |
+
"eval_f1_score": 0.911126636903928,
|
37 |
+
"eval_loss": 0.2466699331998825,
|
38 |
+
"eval_precision": 0.9128365808009684,
|
39 |
+
"eval_runtime": 101.2043,
|
40 |
+
"eval_samples_per_second": 17.351,
|
41 |
+
"eval_steps_per_second": 0.178,
|
42 |
+
"step": 26
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 2.26,
|
46 |
+
"learning_rate": 4.2735042735042735e-05,
|
47 |
+
"loss": 0.3122,
|
48 |
+
"step": 30
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.94,
|
52 |
+
"eval_accuracy": 0.9441913439635535,
|
53 |
+
"eval_f1_score": 0.9417095477838238,
|
54 |
+
"eval_loss": 0.15920311212539673,
|
55 |
+
"eval_precision": 0.9409731109863889,
|
56 |
+
"eval_runtime": 101.5776,
|
57 |
+
"eval_samples_per_second": 17.287,
|
58 |
+
"eval_steps_per_second": 0.177,
|
59 |
+
"step": 39
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 3.02,
|
63 |
+
"learning_rate": 3.846153846153846e-05,
|
64 |
+
"loss": 0.2058,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 3.77,
|
69 |
+
"learning_rate": 3.418803418803419e-05,
|
70 |
+
"loss": 0.1505,
|
71 |
+
"step": 50
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_accuracy": 0.9607061503416856,
|
76 |
+
"eval_f1_score": 0.9585866813576853,
|
77 |
+
"eval_loss": 0.12405357509851456,
|
78 |
+
"eval_precision": 0.9599668342433857,
|
79 |
+
"eval_runtime": 101.5532,
|
80 |
+
"eval_samples_per_second": 17.291,
|
81 |
+
"eval_steps_per_second": 0.177,
|
82 |
+
"step": 53
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 4.53,
|
86 |
+
"learning_rate": 2.9914529914529915e-05,
|
87 |
+
"loss": 0.1369,
|
88 |
+
"step": 60
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 4.98,
|
92 |
+
"eval_accuracy": 0.9584282460136674,
|
93 |
+
"eval_f1_score": 0.9568426641687635,
|
94 |
+
"eval_loss": 0.11865244805812836,
|
95 |
+
"eval_precision": 0.9561593308993074,
|
96 |
+
"eval_runtime": 99.8374,
|
97 |
+
"eval_samples_per_second": 17.589,
|
98 |
+
"eval_steps_per_second": 0.18,
|
99 |
+
"step": 66
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 5.28,
|
103 |
+
"learning_rate": 2.564102564102564e-05,
|
104 |
+
"loss": 0.1014,
|
105 |
+
"step": 70
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 5.96,
|
109 |
+
"eval_accuracy": 0.9629840546697038,
|
110 |
+
"eval_f1_score": 0.961408175995166,
|
111 |
+
"eval_loss": 0.10318630188703537,
|
112 |
+
"eval_precision": 0.9605425088756555,
|
113 |
+
"eval_runtime": 97.4837,
|
114 |
+
"eval_samples_per_second": 18.013,
|
115 |
+
"eval_steps_per_second": 0.185,
|
116 |
+
"step": 79
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 6.04,
|
120 |
+
"learning_rate": 2.1367521367521368e-05,
|
121 |
+
"loss": 0.0915,
|
122 |
+
"step": 80
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 6.79,
|
126 |
+
"learning_rate": 1.7094017094017095e-05,
|
127 |
+
"loss": 0.0701,
|
128 |
+
"step": 90
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 6.94,
|
132 |
+
"eval_accuracy": 0.964123006833713,
|
133 |
+
"eval_f1_score": 0.9626001264665038,
|
134 |
+
"eval_loss": 0.0937563106417656,
|
135 |
+
"eval_precision": 0.9616476162827179,
|
136 |
+
"eval_runtime": 97.9129,
|
137 |
+
"eval_samples_per_second": 17.934,
|
138 |
+
"eval_steps_per_second": 0.184,
|
139 |
+
"step": 92
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 7.55,
|
143 |
+
"learning_rate": 1.282051282051282e-05,
|
144 |
+
"loss": 0.0573,
|
145 |
+
"step": 100
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 8.0,
|
149 |
+
"eval_accuracy": 0.9646924829157175,
|
150 |
+
"eval_f1_score": 0.9631470884281366,
|
151 |
+
"eval_loss": 0.09413320571184158,
|
152 |
+
"eval_precision": 0.962286619602796,
|
153 |
+
"eval_runtime": 97.7324,
|
154 |
+
"eval_samples_per_second": 17.967,
|
155 |
+
"eval_steps_per_second": 0.184,
|
156 |
+
"step": 106
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 8.3,
|
160 |
+
"learning_rate": 8.547008547008548e-06,
|
161 |
+
"loss": 0.0614,
|
162 |
+
"step": 110
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 8.98,
|
166 |
+
"eval_accuracy": 0.9686788154897494,
|
167 |
+
"eval_f1_score": 0.9673690693947884,
|
168 |
+
"eval_loss": 0.08304769545793533,
|
169 |
+
"eval_precision": 0.9666280950722521,
|
170 |
+
"eval_runtime": 97.3333,
|
171 |
+
"eval_samples_per_second": 18.041,
|
172 |
+
"eval_steps_per_second": 0.185,
|
173 |
+
"step": 119
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 9.06,
|
177 |
+
"learning_rate": 4.273504273504274e-06,
|
178 |
+
"loss": 0.0477,
|
179 |
+
"step": 120
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 9.81,
|
183 |
+
"learning_rate": 0.0,
|
184 |
+
"loss": 0.0534,
|
185 |
+
"step": 130
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 9.81,
|
189 |
+
"eval_accuracy": 0.9698177676537585,
|
190 |
+
"eval_f1_score": 0.9685806509996516,
|
191 |
+
"eval_loss": 0.0791645273566246,
|
192 |
+
"eval_precision": 0.9677462875813125,
|
193 |
+
"eval_runtime": 96.7311,
|
194 |
+
"eval_samples_per_second": 18.153,
|
195 |
+
"eval_steps_per_second": 0.186,
|
196 |
+
"step": 130
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 9.81,
|
200 |
+
"step": 130,
|
201 |
+
"total_flos": 4.0507959904511017e+18,
|
202 |
+
"train_loss": 0.25211207201847663,
|
203 |
+
"train_runtime": 12845.6349,
|
204 |
+
"train_samples_per_second": 4.1,
|
205 |
+
"train_steps_per_second": 0.01
|
206 |
+
}
|
207 |
+
],
|
208 |
+
"max_steps": 130,
|
209 |
+
"num_train_epochs": 10,
|
210 |
+
"total_flos": 4.0507959904511017e+18,
|
211 |
+
"trial_name": null,
|
212 |
+
"trial_params": null
|
213 |
+
}
|