🍻 cheers
Browse files
all_results.json
CHANGED
@@ -1,8 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 4.156707577848054e+17,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 2.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.8987341772151899,
|
4 |
+
"eval_loss": 0.3074355721473694,
|
5 |
+
"eval_runtime": 3.6489,
|
6 |
+
"eval_samples_per_second": 64.952,
|
7 |
+
"eval_steps_per_second": 8.222,
|
8 |
"total_flos": 4.156707577848054e+17,
|
9 |
+
"train_loss": 0.4933107083752042,
|
10 |
+
"train_runtime": 131.5099,
|
11 |
+
"train_samples_per_second": 40.788,
|
12 |
+
"train_steps_per_second": 2.555
|
13 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.8987341772151899,
|
4 |
+
"eval_loss": 0.3074355721473694,
|
5 |
+
"eval_runtime": 3.6489,
|
6 |
+
"eval_samples_per_second": 64.952,
|
7 |
+
"eval_steps_per_second": 8.222
|
8 |
+
}
|
runs/May13_10-04-37_4c49d2f8bc77/events.out.tfevents.1715595788.4c49d2f8bc77.7570.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcca50447cb9a1fe982032537d4e8eca1f3d40793978ac82a795ddcd015b90d6
|
3 |
+
size 411
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 4.156707577848054e+17,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 2.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 4.156707577848054e+17,
|
4 |
+
"train_loss": 0.4933107083752042,
|
5 |
+
"train_runtime": 131.5099,
|
6 |
+
"train_samples_per_second": 40.788,
|
7 |
+
"train_steps_per_second": 2.555
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"best_metric": 0.3074355721473694,
|
3 |
-
"best_model_checkpoint": "finetuned-breast_cancer_images/checkpoint-
|
4 |
"epoch": 4.0,
|
5 |
"global_step": 336,
|
6 |
"is_hyper_param_search": false,
|
@@ -9,237 +9,237 @@
|
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.12,
|
12 |
-
"learning_rate": 0.
|
13 |
-
"loss": 0.
|
14 |
"step": 10
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.24,
|
18 |
-
"learning_rate": 0.
|
19 |
-
"loss": 0.
|
20 |
"step": 20
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.36,
|
24 |
-
"learning_rate": 0.
|
25 |
-
"loss": 0.
|
26 |
"step": 30
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.48,
|
30 |
-
"learning_rate": 0.
|
31 |
-
"loss": 0.
|
32 |
"step": 40
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.6,
|
36 |
-
"learning_rate": 0.
|
37 |
-
"loss": 0.
|
38 |
"step": 50
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.71,
|
42 |
-
"learning_rate": 0.
|
43 |
-
"loss": 0.
|
44 |
"step": 60
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.83,
|
48 |
-
"learning_rate": 0.
|
49 |
-
"loss": 0.
|
50 |
"step": 70
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.95,
|
54 |
-
"learning_rate": 0.
|
55 |
-
"loss": 0.
|
56 |
"step": 80
|
57 |
},
|
58 |
{
|
59 |
"epoch": 1.07,
|
60 |
-
"learning_rate": 0.
|
61 |
-
"loss": 0.
|
62 |
"step": 90
|
63 |
},
|
64 |
{
|
65 |
"epoch": 1.19,
|
66 |
-
"learning_rate": 0.
|
67 |
-
"loss": 0.
|
68 |
"step": 100
|
69 |
},
|
70 |
{
|
71 |
"epoch": 1.19,
|
72 |
-
"eval_accuracy": 0.
|
73 |
-
"eval_loss": 0.
|
74 |
-
"eval_runtime": 2.
|
75 |
-
"eval_samples_per_second":
|
76 |
-
"eval_steps_per_second":
|
77 |
"step": 100
|
78 |
},
|
79 |
{
|
80 |
"epoch": 1.31,
|
81 |
-
"learning_rate": 0.
|
82 |
-
"loss": 0.
|
83 |
"step": 110
|
84 |
},
|
85 |
{
|
86 |
"epoch": 1.43,
|
87 |
-
"learning_rate": 0.
|
88 |
-
"loss": 0.
|
89 |
"step": 120
|
90 |
},
|
91 |
{
|
92 |
"epoch": 1.55,
|
93 |
-
"learning_rate": 0.
|
94 |
-
"loss": 0.
|
95 |
"step": 130
|
96 |
},
|
97 |
{
|
98 |
"epoch": 1.67,
|
99 |
-
"learning_rate": 0.
|
100 |
-
"loss": 0.
|
101 |
"step": 140
|
102 |
},
|
103 |
{
|
104 |
"epoch": 1.79,
|
105 |
-
"learning_rate": 0.
|
106 |
-
"loss": 0.
|
107 |
"step": 150
|
108 |
},
|
109 |
{
|
110 |
"epoch": 1.9,
|
111 |
-
"learning_rate": 0.
|
112 |
-
"loss": 0.
|
113 |
"step": 160
|
114 |
},
|
115 |
{
|
116 |
"epoch": 2.02,
|
117 |
-
"learning_rate":
|
118 |
-
"loss": 0.
|
119 |
"step": 170
|
120 |
},
|
121 |
{
|
122 |
"epoch": 2.14,
|
123 |
-
"learning_rate":
|
124 |
-
"loss": 0.
|
125 |
"step": 180
|
126 |
},
|
127 |
{
|
128 |
"epoch": 2.26,
|
129 |
-
"learning_rate":
|
130 |
-
"loss": 0.
|
131 |
"step": 190
|
132 |
},
|
133 |
{
|
134 |
"epoch": 2.38,
|
135 |
-
"learning_rate":
|
136 |
-
"loss": 0.
|
137 |
"step": 200
|
138 |
},
|
139 |
{
|
140 |
"epoch": 2.38,
|
141 |
"eval_accuracy": 0.8987341772151899,
|
142 |
"eval_loss": 0.3074355721473694,
|
143 |
-
"eval_runtime": 2.
|
144 |
-
"eval_samples_per_second":
|
145 |
-
"eval_steps_per_second": 12.
|
146 |
"step": 200
|
147 |
},
|
148 |
{
|
149 |
"epoch": 2.5,
|
150 |
-
"learning_rate":
|
151 |
-
"loss": 0.
|
152 |
"step": 210
|
153 |
},
|
154 |
{
|
155 |
"epoch": 2.62,
|
156 |
-
"learning_rate":
|
157 |
-
"loss": 0.
|
158 |
"step": 220
|
159 |
},
|
160 |
{
|
161 |
"epoch": 2.74,
|
162 |
-
"learning_rate":
|
163 |
-
"loss": 0.
|
164 |
"step": 230
|
165 |
},
|
166 |
{
|
167 |
"epoch": 2.86,
|
168 |
-
"learning_rate":
|
169 |
-
"loss": 0.
|
170 |
"step": 240
|
171 |
},
|
172 |
{
|
173 |
"epoch": 2.98,
|
174 |
-
"learning_rate":
|
175 |
-
"loss": 0.
|
176 |
"step": 250
|
177 |
},
|
178 |
{
|
179 |
"epoch": 3.1,
|
180 |
-
"learning_rate":
|
181 |
-
"loss": 0.
|
182 |
"step": 260
|
183 |
},
|
184 |
{
|
185 |
"epoch": 3.21,
|
186 |
-
"learning_rate":
|
187 |
-
"loss": 0.
|
188 |
"step": 270
|
189 |
},
|
190 |
{
|
191 |
"epoch": 3.33,
|
192 |
-
"learning_rate":
|
193 |
-
"loss": 0.
|
194 |
"step": 280
|
195 |
},
|
196 |
{
|
197 |
"epoch": 3.45,
|
198 |
-
"learning_rate":
|
199 |
-
"loss": 0.
|
200 |
"step": 290
|
201 |
},
|
202 |
{
|
203 |
"epoch": 3.57,
|
204 |
-
"learning_rate":
|
205 |
-
"loss": 0.
|
206 |
"step": 300
|
207 |
},
|
208 |
{
|
209 |
"epoch": 3.57,
|
210 |
-
"eval_accuracy": 0.
|
211 |
-
"eval_loss": 0.
|
212 |
-
"eval_runtime": 2.
|
213 |
-
"eval_samples_per_second":
|
214 |
-
"eval_steps_per_second": 12.
|
215 |
"step": 300
|
216 |
},
|
217 |
{
|
218 |
"epoch": 3.69,
|
219 |
-
"learning_rate":
|
220 |
-
"loss": 0.
|
221 |
"step": 310
|
222 |
},
|
223 |
{
|
224 |
"epoch": 3.81,
|
225 |
-
"learning_rate":
|
226 |
-
"loss": 0.
|
227 |
"step": 320
|
228 |
},
|
229 |
{
|
230 |
"epoch": 3.93,
|
231 |
-
"learning_rate":
|
232 |
-
"loss": 0.
|
233 |
"step": 330
|
234 |
},
|
235 |
{
|
236 |
"epoch": 4.0,
|
237 |
"step": 336,
|
238 |
"total_flos": 4.156707577848054e+17,
|
239 |
-
"train_loss": 0.
|
240 |
-
"train_runtime":
|
241 |
-
"train_samples_per_second":
|
242 |
-
"train_steps_per_second": 2.
|
243 |
}
|
244 |
],
|
245 |
"max_steps": 336,
|
|
|
1 |
{
|
2 |
"best_metric": 0.3074355721473694,
|
3 |
+
"best_model_checkpoint": "finetuned-breast_cancer_images/checkpoint-100",
|
4 |
"epoch": 4.0,
|
5 |
"global_step": 336,
|
6 |
"is_hyper_param_search": false,
|
|
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.12,
|
12 |
+
"learning_rate": 0.0,
|
13 |
+
"loss": 0.4362,
|
14 |
"step": 10
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.24,
|
18 |
+
"learning_rate": 0.0,
|
19 |
+
"loss": 0.4081,
|
20 |
"step": 20
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.36,
|
24 |
+
"learning_rate": 0.0,
|
25 |
+
"loss": 0.5069,
|
26 |
"step": 30
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.48,
|
30 |
+
"learning_rate": 0.0,
|
31 |
+
"loss": 0.4546,
|
32 |
"step": 40
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.6,
|
36 |
+
"learning_rate": 0.0,
|
37 |
+
"loss": 0.4799,
|
38 |
"step": 50
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.71,
|
42 |
+
"learning_rate": 0.0,
|
43 |
+
"loss": 0.5819,
|
44 |
"step": 60
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.83,
|
48 |
+
"learning_rate": 0.0,
|
49 |
+
"loss": 0.4704,
|
50 |
"step": 70
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.95,
|
54 |
+
"learning_rate": 0.0,
|
55 |
+
"loss": 0.5476,
|
56 |
"step": 80
|
57 |
},
|
58 |
{
|
59 |
"epoch": 1.07,
|
60 |
+
"learning_rate": 0.0,
|
61 |
+
"loss": 0.5506,
|
62 |
"step": 90
|
63 |
},
|
64 |
{
|
65 |
"epoch": 1.19,
|
66 |
+
"learning_rate": 0.0,
|
67 |
+
"loss": 0.4716,
|
68 |
"step": 100
|
69 |
},
|
70 |
{
|
71 |
"epoch": 1.19,
|
72 |
+
"eval_accuracy": 0.8987341772151899,
|
73 |
+
"eval_loss": 0.3074355721473694,
|
74 |
+
"eval_runtime": 2.4007,
|
75 |
+
"eval_samples_per_second": 98.722,
|
76 |
+
"eval_steps_per_second": 12.496,
|
77 |
"step": 100
|
78 |
},
|
79 |
{
|
80 |
"epoch": 1.31,
|
81 |
+
"learning_rate": 0.0,
|
82 |
+
"loss": 0.4972,
|
83 |
"step": 110
|
84 |
},
|
85 |
{
|
86 |
"epoch": 1.43,
|
87 |
+
"learning_rate": 0.0,
|
88 |
+
"loss": 0.5508,
|
89 |
"step": 120
|
90 |
},
|
91 |
{
|
92 |
"epoch": 1.55,
|
93 |
+
"learning_rate": 0.0,
|
94 |
+
"loss": 0.3687,
|
95 |
"step": 130
|
96 |
},
|
97 |
{
|
98 |
"epoch": 1.67,
|
99 |
+
"learning_rate": 0.0,
|
100 |
+
"loss": 0.5155,
|
101 |
"step": 140
|
102 |
},
|
103 |
{
|
104 |
"epoch": 1.79,
|
105 |
+
"learning_rate": 0.0,
|
106 |
+
"loss": 0.4511,
|
107 |
"step": 150
|
108 |
},
|
109 |
{
|
110 |
"epoch": 1.9,
|
111 |
+
"learning_rate": 0.0,
|
112 |
+
"loss": 0.4943,
|
113 |
"step": 160
|
114 |
},
|
115 |
{
|
116 |
"epoch": 2.02,
|
117 |
+
"learning_rate": 0.0,
|
118 |
+
"loss": 0.4756,
|
119 |
"step": 170
|
120 |
},
|
121 |
{
|
122 |
"epoch": 2.14,
|
123 |
+
"learning_rate": 0.0,
|
124 |
+
"loss": 0.4893,
|
125 |
"step": 180
|
126 |
},
|
127 |
{
|
128 |
"epoch": 2.26,
|
129 |
+
"learning_rate": 0.0,
|
130 |
+
"loss": 0.553,
|
131 |
"step": 190
|
132 |
},
|
133 |
{
|
134 |
"epoch": 2.38,
|
135 |
+
"learning_rate": 0.0,
|
136 |
+
"loss": 0.5523,
|
137 |
"step": 200
|
138 |
},
|
139 |
{
|
140 |
"epoch": 2.38,
|
141 |
"eval_accuracy": 0.8987341772151899,
|
142 |
"eval_loss": 0.3074355721473694,
|
143 |
+
"eval_runtime": 2.4171,
|
144 |
+
"eval_samples_per_second": 98.05,
|
145 |
+
"eval_steps_per_second": 12.411,
|
146 |
"step": 200
|
147 |
},
|
148 |
{
|
149 |
"epoch": 2.5,
|
150 |
+
"learning_rate": 0.0,
|
151 |
+
"loss": 0.5049,
|
152 |
"step": 210
|
153 |
},
|
154 |
{
|
155 |
"epoch": 2.62,
|
156 |
+
"learning_rate": 0.0,
|
157 |
+
"loss": 0.4306,
|
158 |
"step": 220
|
159 |
},
|
160 |
{
|
161 |
"epoch": 2.74,
|
162 |
+
"learning_rate": 0.0,
|
163 |
+
"loss": 0.4699,
|
164 |
"step": 230
|
165 |
},
|
166 |
{
|
167 |
"epoch": 2.86,
|
168 |
+
"learning_rate": 0.0,
|
169 |
+
"loss": 0.5013,
|
170 |
"step": 240
|
171 |
},
|
172 |
{
|
173 |
"epoch": 2.98,
|
174 |
+
"learning_rate": 0.0,
|
175 |
+
"loss": 0.509,
|
176 |
"step": 250
|
177 |
},
|
178 |
{
|
179 |
"epoch": 3.1,
|
180 |
+
"learning_rate": 0.0,
|
181 |
+
"loss": 0.4949,
|
182 |
"step": 260
|
183 |
},
|
184 |
{
|
185 |
"epoch": 3.21,
|
186 |
+
"learning_rate": 0.0,
|
187 |
+
"loss": 0.5185,
|
188 |
"step": 270
|
189 |
},
|
190 |
{
|
191 |
"epoch": 3.33,
|
192 |
+
"learning_rate": 0.0,
|
193 |
+
"loss": 0.469,
|
194 |
"step": 280
|
195 |
},
|
196 |
{
|
197 |
"epoch": 3.45,
|
198 |
+
"learning_rate": 0.0,
|
199 |
+
"loss": 0.5256,
|
200 |
"step": 290
|
201 |
},
|
202 |
{
|
203 |
"epoch": 3.57,
|
204 |
+
"learning_rate": 0.0,
|
205 |
+
"loss": 0.4472,
|
206 |
"step": 300
|
207 |
},
|
208 |
{
|
209 |
"epoch": 3.57,
|
210 |
+
"eval_accuracy": 0.8987341772151899,
|
211 |
+
"eval_loss": 0.3074355721473694,
|
212 |
+
"eval_runtime": 2.4655,
|
213 |
+
"eval_samples_per_second": 96.127,
|
214 |
+
"eval_steps_per_second": 12.168,
|
215 |
"step": 300
|
216 |
},
|
217 |
{
|
218 |
"epoch": 3.69,
|
219 |
+
"learning_rate": 0.0,
|
220 |
+
"loss": 0.4371,
|
221 |
"step": 310
|
222 |
},
|
223 |
{
|
224 |
"epoch": 3.81,
|
225 |
+
"learning_rate": 0.0,
|
226 |
+
"loss": 0.5614,
|
227 |
"step": 320
|
228 |
},
|
229 |
{
|
230 |
"epoch": 3.93,
|
231 |
+
"learning_rate": 0.0,
|
232 |
+
"loss": 0.4989,
|
233 |
"step": 330
|
234 |
},
|
235 |
{
|
236 |
"epoch": 4.0,
|
237 |
"step": 336,
|
238 |
"total_flos": 4.156707577848054e+17,
|
239 |
+
"train_loss": 0.4933107083752042,
|
240 |
+
"train_runtime": 131.5099,
|
241 |
+
"train_samples_per_second": 40.788,
|
242 |
+
"train_steps_per_second": 2.555
|
243 |
}
|
244 |
],
|
245 |
"max_steps": 336,
|