End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.5343573093414307,
|
5 |
+
"eval_runtime": 0.0743,
|
6 |
+
"eval_samples_per_second": 53.872,
|
7 |
+
"eval_steps_per_second": 13.468,
|
8 |
+
"total_flos": 1.789631206981632e+16,
|
9 |
+
"train_loss": 0.23643767833709717,
|
10 |
+
"train_runtime": 85.6091,
|
11 |
+
"train_samples_per_second": 8.41,
|
12 |
+
"train_steps_per_second": 0.234
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.5343573093414307,
|
5 |
+
"eval_runtime": 0.0743,
|
6 |
+
"eval_samples_per_second": 53.872,
|
7 |
+
"eval_steps_per_second": 13.468
|
8 |
+
}
|
runs/Aug20_18-14-11_25a392132e02/events.out.tfevents.1692555437.25a392132e02.4646.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7af94ca138d4ef5cfc4999550e08a08b855b849f73799ec58cb55d21dd143e60
|
3 |
+
size 405
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"total_flos": 1.789631206981632e+16,
|
4 |
+
"train_loss": 0.23643767833709717,
|
5 |
+
"train_runtime": 85.6091,
|
6 |
+
"train_samples_per_second": 8.41,
|
7 |
+
"train_steps_per_second": 0.234
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-mulder-v-scully-colab2/checkpoint-8",
|
4 |
+
"epoch": 20.0,
|
5 |
+
"global_step": 20,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.5,
|
13 |
+
"eval_loss": 0.6898614168167114,
|
14 |
+
"eval_runtime": 0.0706,
|
15 |
+
"eval_samples_per_second": 56.662,
|
16 |
+
"eval_steps_per_second": 14.165,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.25,
|
22 |
+
"eval_loss": 0.6700608730316162,
|
23 |
+
"eval_runtime": 0.0661,
|
24 |
+
"eval_samples_per_second": 60.508,
|
25 |
+
"eval_steps_per_second": 15.127,
|
26 |
+
"step": 2
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.5,
|
31 |
+
"eval_loss": 0.6308517456054688,
|
32 |
+
"eval_runtime": 0.0675,
|
33 |
+
"eval_samples_per_second": 59.3,
|
34 |
+
"eval_steps_per_second": 14.825,
|
35 |
+
"step": 3
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 4.0,
|
39 |
+
"eval_accuracy": 0.5,
|
40 |
+
"eval_loss": 0.6049411296844482,
|
41 |
+
"eval_runtime": 0.0756,
|
42 |
+
"eval_samples_per_second": 52.927,
|
43 |
+
"eval_steps_per_second": 13.232,
|
44 |
+
"step": 4
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 5.0,
|
48 |
+
"eval_accuracy": 0.5,
|
49 |
+
"eval_loss": 0.5827720165252686,
|
50 |
+
"eval_runtime": 0.0665,
|
51 |
+
"eval_samples_per_second": 60.157,
|
52 |
+
"eval_steps_per_second": 15.039,
|
53 |
+
"step": 5
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 6.0,
|
57 |
+
"eval_accuracy": 0.75,
|
58 |
+
"eval_loss": 0.564973771572113,
|
59 |
+
"eval_runtime": 0.0671,
|
60 |
+
"eval_samples_per_second": 59.633,
|
61 |
+
"eval_steps_per_second": 14.908,
|
62 |
+
"step": 6
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 7.0,
|
66 |
+
"eval_accuracy": 0.75,
|
67 |
+
"eval_loss": 0.5485844016075134,
|
68 |
+
"eval_runtime": 0.0664,
|
69 |
+
"eval_samples_per_second": 60.197,
|
70 |
+
"eval_steps_per_second": 15.049,
|
71 |
+
"step": 7
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 8.0,
|
75 |
+
"eval_accuracy": 1.0,
|
76 |
+
"eval_loss": 0.5343573093414307,
|
77 |
+
"eval_runtime": 0.0738,
|
78 |
+
"eval_samples_per_second": 54.186,
|
79 |
+
"eval_steps_per_second": 13.547,
|
80 |
+
"step": 8
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 9.0,
|
84 |
+
"eval_accuracy": 1.0,
|
85 |
+
"eval_loss": 0.5239884853363037,
|
86 |
+
"eval_runtime": 0.0694,
|
87 |
+
"eval_samples_per_second": 57.596,
|
88 |
+
"eval_steps_per_second": 14.399,
|
89 |
+
"step": 9
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 10.0,
|
93 |
+
"learning_rate": 2.777777777777778e-05,
|
94 |
+
"loss": 0.2978,
|
95 |
+
"step": 10
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 10.0,
|
99 |
+
"eval_accuracy": 1.0,
|
100 |
+
"eval_loss": 0.5149481296539307,
|
101 |
+
"eval_runtime": 0.0723,
|
102 |
+
"eval_samples_per_second": 55.291,
|
103 |
+
"eval_steps_per_second": 13.823,
|
104 |
+
"step": 10
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 11.0,
|
108 |
+
"eval_accuracy": 1.0,
|
109 |
+
"eval_loss": 0.5065804719924927,
|
110 |
+
"eval_runtime": 0.067,
|
111 |
+
"eval_samples_per_second": 59.67,
|
112 |
+
"eval_steps_per_second": 14.918,
|
113 |
+
"step": 11
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 12.0,
|
117 |
+
"eval_accuracy": 1.0,
|
118 |
+
"eval_loss": 0.49803948402404785,
|
119 |
+
"eval_runtime": 0.0682,
|
120 |
+
"eval_samples_per_second": 58.642,
|
121 |
+
"eval_steps_per_second": 14.66,
|
122 |
+
"step": 12
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 13.0,
|
126 |
+
"eval_accuracy": 1.0,
|
127 |
+
"eval_loss": 0.48803186416625977,
|
128 |
+
"eval_runtime": 0.0722,
|
129 |
+
"eval_samples_per_second": 55.406,
|
130 |
+
"eval_steps_per_second": 13.851,
|
131 |
+
"step": 13
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 14.0,
|
135 |
+
"eval_accuracy": 1.0,
|
136 |
+
"eval_loss": 0.46994858980178833,
|
137 |
+
"eval_runtime": 0.0706,
|
138 |
+
"eval_samples_per_second": 56.647,
|
139 |
+
"eval_steps_per_second": 14.162,
|
140 |
+
"step": 14
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 15.0,
|
144 |
+
"eval_accuracy": 1.0,
|
145 |
+
"eval_loss": 0.4506602883338928,
|
146 |
+
"eval_runtime": 0.0711,
|
147 |
+
"eval_samples_per_second": 56.227,
|
148 |
+
"eval_steps_per_second": 14.057,
|
149 |
+
"step": 15
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 16.0,
|
153 |
+
"eval_accuracy": 1.0,
|
154 |
+
"eval_loss": 0.4310106039047241,
|
155 |
+
"eval_runtime": 0.0688,
|
156 |
+
"eval_samples_per_second": 58.137,
|
157 |
+
"eval_steps_per_second": 14.534,
|
158 |
+
"step": 16
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 17.0,
|
162 |
+
"eval_accuracy": 1.0,
|
163 |
+
"eval_loss": 0.41549980640411377,
|
164 |
+
"eval_runtime": 0.0686,
|
165 |
+
"eval_samples_per_second": 58.309,
|
166 |
+
"eval_steps_per_second": 14.577,
|
167 |
+
"step": 17
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 18.0,
|
171 |
+
"eval_accuracy": 1.0,
|
172 |
+
"eval_loss": 0.4053996503353119,
|
173 |
+
"eval_runtime": 0.0697,
|
174 |
+
"eval_samples_per_second": 57.365,
|
175 |
+
"eval_steps_per_second": 14.341,
|
176 |
+
"step": 18
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 19.0,
|
180 |
+
"eval_accuracy": 1.0,
|
181 |
+
"eval_loss": 0.39938098192214966,
|
182 |
+
"eval_runtime": 0.0762,
|
183 |
+
"eval_samples_per_second": 52.495,
|
184 |
+
"eval_steps_per_second": 13.124,
|
185 |
+
"step": 19
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 20.0,
|
189 |
+
"learning_rate": 0.0,
|
190 |
+
"loss": 0.1751,
|
191 |
+
"step": 20
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 20.0,
|
195 |
+
"eval_accuracy": 1.0,
|
196 |
+
"eval_loss": 0.3969520628452301,
|
197 |
+
"eval_runtime": 0.0677,
|
198 |
+
"eval_samples_per_second": 59.119,
|
199 |
+
"eval_steps_per_second": 14.78,
|
200 |
+
"step": 20
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 20.0,
|
204 |
+
"step": 20,
|
205 |
+
"total_flos": 1.789631206981632e+16,
|
206 |
+
"train_loss": 0.23643767833709717,
|
207 |
+
"train_runtime": 85.6091,
|
208 |
+
"train_samples_per_second": 8.41,
|
209 |
+
"train_steps_per_second": 0.234
|
210 |
+
}
|
211 |
+
],
|
212 |
+
"max_steps": 20,
|
213 |
+
"num_train_epochs": 20,
|
214 |
+
"total_flos": 1.789631206981632e+16,
|
215 |
+
"trial_name": null,
|
216 |
+
"trial_params": null
|
217 |
+
}
|