Commit
•
ff764b4
1
Parent(s):
042a3ab
End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.6190476190476191,
|
4 |
+
"eval_loss": 0.9910643696784973,
|
5 |
+
"eval_runtime": 4.906,
|
6 |
+
"eval_samples_per_second": 8.561,
|
7 |
+
"eval_steps_per_second": 0.408,
|
8 |
+
"total_flos": 5.741178860545229e+17,
|
9 |
+
"train_loss": 1.1042359352111817,
|
10 |
+
"train_runtime": 2357.6438,
|
11 |
+
"train_samples_per_second": 3.147,
|
12 |
+
"train_steps_per_second": 0.025
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.6190476190476191,
|
4 |
+
"eval_loss": 0.9910643696784973,
|
5 |
+
"eval_runtime": 4.906,
|
6 |
+
"eval_samples_per_second": 8.561,
|
7 |
+
"eval_steps_per_second": 0.408
|
8 |
+
}
|
runs/Apr01_12-59-26_b000f2de1a15/events.out.tfevents.1711978793.b000f2de1a15.5893.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5113074fd3584bc17c1b57884395df0b6b8fddf083f701dcd8d19d5fc48b2e0f
|
3 |
+
size 405
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"total_flos": 5.741178860545229e+17,
|
4 |
+
"train_loss": 1.1042359352111817,
|
5 |
+
"train_runtime": 2357.6438,
|
6 |
+
"train_samples_per_second": 3.147,
|
7 |
+
"train_steps_per_second": 0.025
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6190476190476191,
|
3 |
+
"best_model_checkpoint": "beit-base-patch16-224-pt22k-finetuned-IDRiD/checkpoint-42",
|
4 |
+
"epoch": 20.0,
|
5 |
+
"global_step": 60,
|
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": 0.47619047619047616,
|
13 |
+
"eval_loss": 1.3246450424194336,
|
14 |
+
"eval_runtime": 4.8065,
|
15 |
+
"eval_samples_per_second": 8.738,
|
16 |
+
"eval_steps_per_second": 0.416,
|
17 |
+
"step": 3
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.2857142857142857,
|
22 |
+
"eval_loss": 1.3622591495513916,
|
23 |
+
"eval_runtime": 4.6869,
|
24 |
+
"eval_samples_per_second": 8.961,
|
25 |
+
"eval_steps_per_second": 0.427,
|
26 |
+
"step": 6
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.5,
|
31 |
+
"eval_loss": 1.2265574932098389,
|
32 |
+
"eval_runtime": 5.4584,
|
33 |
+
"eval_samples_per_second": 7.695,
|
34 |
+
"eval_steps_per_second": 0.366,
|
35 |
+
"step": 9
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 3.33,
|
39 |
+
"learning_rate": 4.62962962962963e-05,
|
40 |
+
"loss": 1.4927,
|
41 |
+
"step": 10
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 4.0,
|
45 |
+
"eval_accuracy": 0.5238095238095238,
|
46 |
+
"eval_loss": 1.1882591247558594,
|
47 |
+
"eval_runtime": 4.8763,
|
48 |
+
"eval_samples_per_second": 8.613,
|
49 |
+
"eval_steps_per_second": 0.41,
|
50 |
+
"step": 12
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 5.0,
|
54 |
+
"eval_accuracy": 0.5476190476190477,
|
55 |
+
"eval_loss": 1.1602239608764648,
|
56 |
+
"eval_runtime": 5.4275,
|
57 |
+
"eval_samples_per_second": 7.738,
|
58 |
+
"eval_steps_per_second": 0.368,
|
59 |
+
"step": 15
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 6.0,
|
63 |
+
"eval_accuracy": 0.5476190476190477,
|
64 |
+
"eval_loss": 1.1060962677001953,
|
65 |
+
"eval_runtime": 4.7627,
|
66 |
+
"eval_samples_per_second": 8.818,
|
67 |
+
"eval_steps_per_second": 0.42,
|
68 |
+
"step": 18
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 6.67,
|
72 |
+
"learning_rate": 3.7037037037037037e-05,
|
73 |
+
"loss": 1.2358,
|
74 |
+
"step": 20
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 7.0,
|
78 |
+
"eval_accuracy": 0.5,
|
79 |
+
"eval_loss": 1.1068215370178223,
|
80 |
+
"eval_runtime": 5.7419,
|
81 |
+
"eval_samples_per_second": 7.315,
|
82 |
+
"eval_steps_per_second": 0.348,
|
83 |
+
"step": 21
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 8.0,
|
87 |
+
"eval_accuracy": 0.5952380952380952,
|
88 |
+
"eval_loss": 1.0987563133239746,
|
89 |
+
"eval_runtime": 4.6754,
|
90 |
+
"eval_samples_per_second": 8.983,
|
91 |
+
"eval_steps_per_second": 0.428,
|
92 |
+
"step": 24
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 9.0,
|
96 |
+
"eval_accuracy": 0.5714285714285714,
|
97 |
+
"eval_loss": 0.9244362711906433,
|
98 |
+
"eval_runtime": 5.4929,
|
99 |
+
"eval_samples_per_second": 7.646,
|
100 |
+
"eval_steps_per_second": 0.364,
|
101 |
+
"step": 27
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 10.0,
|
105 |
+
"learning_rate": 2.777777777777778e-05,
|
106 |
+
"loss": 1.0867,
|
107 |
+
"step": 30
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 10.0,
|
111 |
+
"eval_accuracy": 0.5476190476190477,
|
112 |
+
"eval_loss": 1.1630090475082397,
|
113 |
+
"eval_runtime": 5.1486,
|
114 |
+
"eval_samples_per_second": 8.158,
|
115 |
+
"eval_steps_per_second": 0.388,
|
116 |
+
"step": 30
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 11.0,
|
120 |
+
"eval_accuracy": 0.5,
|
121 |
+
"eval_loss": 0.9561101794242859,
|
122 |
+
"eval_runtime": 4.6858,
|
123 |
+
"eval_samples_per_second": 8.963,
|
124 |
+
"eval_steps_per_second": 0.427,
|
125 |
+
"step": 33
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 12.0,
|
129 |
+
"eval_accuracy": 0.5,
|
130 |
+
"eval_loss": 1.242404580116272,
|
131 |
+
"eval_runtime": 5.05,
|
132 |
+
"eval_samples_per_second": 8.317,
|
133 |
+
"eval_steps_per_second": 0.396,
|
134 |
+
"step": 36
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 13.0,
|
138 |
+
"eval_accuracy": 0.5952380952380952,
|
139 |
+
"eval_loss": 0.8335705995559692,
|
140 |
+
"eval_runtime": 5.4096,
|
141 |
+
"eval_samples_per_second": 7.764,
|
142 |
+
"eval_steps_per_second": 0.37,
|
143 |
+
"step": 39
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 13.33,
|
147 |
+
"learning_rate": 1.8518518518518518e-05,
|
148 |
+
"loss": 0.9834,
|
149 |
+
"step": 40
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 14.0,
|
153 |
+
"eval_accuracy": 0.6190476190476191,
|
154 |
+
"eval_loss": 0.9910643696784973,
|
155 |
+
"eval_runtime": 4.7252,
|
156 |
+
"eval_samples_per_second": 8.889,
|
157 |
+
"eval_steps_per_second": 0.423,
|
158 |
+
"step": 42
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 15.0,
|
162 |
+
"eval_accuracy": 0.5476190476190477,
|
163 |
+
"eval_loss": 0.9701122045516968,
|
164 |
+
"eval_runtime": 5.6372,
|
165 |
+
"eval_samples_per_second": 7.451,
|
166 |
+
"eval_steps_per_second": 0.355,
|
167 |
+
"step": 45
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 16.0,
|
171 |
+
"eval_accuracy": 0.5952380952380952,
|
172 |
+
"eval_loss": 0.8365135192871094,
|
173 |
+
"eval_runtime": 4.8097,
|
174 |
+
"eval_samples_per_second": 8.732,
|
175 |
+
"eval_steps_per_second": 0.416,
|
176 |
+
"step": 48
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 16.67,
|
180 |
+
"learning_rate": 9.259259259259259e-06,
|
181 |
+
"loss": 0.9604,
|
182 |
+
"step": 50
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 17.0,
|
186 |
+
"eval_accuracy": 0.5,
|
187 |
+
"eval_loss": 0.8691428899765015,
|
188 |
+
"eval_runtime": 4.713,
|
189 |
+
"eval_samples_per_second": 8.912,
|
190 |
+
"eval_steps_per_second": 0.424,
|
191 |
+
"step": 51
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 18.0,
|
195 |
+
"eval_accuracy": 0.5476190476190477,
|
196 |
+
"eval_loss": 0.9503064155578613,
|
197 |
+
"eval_runtime": 5.1807,
|
198 |
+
"eval_samples_per_second": 8.107,
|
199 |
+
"eval_steps_per_second": 0.386,
|
200 |
+
"step": 54
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 19.0,
|
204 |
+
"eval_accuracy": 0.5476190476190477,
|
205 |
+
"eval_loss": 0.9222093224525452,
|
206 |
+
"eval_runtime": 4.8775,
|
207 |
+
"eval_samples_per_second": 8.611,
|
208 |
+
"eval_steps_per_second": 0.41,
|
209 |
+
"step": 57
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 20.0,
|
213 |
+
"learning_rate": 0.0,
|
214 |
+
"loss": 0.8664,
|
215 |
+
"step": 60
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 20.0,
|
219 |
+
"eval_accuracy": 0.5476190476190477,
|
220 |
+
"eval_loss": 0.9122352600097656,
|
221 |
+
"eval_runtime": 4.9066,
|
222 |
+
"eval_samples_per_second": 8.56,
|
223 |
+
"eval_steps_per_second": 0.408,
|
224 |
+
"step": 60
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 20.0,
|
228 |
+
"step": 60,
|
229 |
+
"total_flos": 5.741178860545229e+17,
|
230 |
+
"train_loss": 1.1042359352111817,
|
231 |
+
"train_runtime": 2357.6438,
|
232 |
+
"train_samples_per_second": 3.147,
|
233 |
+
"train_steps_per_second": 0.025
|
234 |
+
}
|
235 |
+
],
|
236 |
+
"max_steps": 60,
|
237 |
+
"num_train_epochs": 20,
|
238 |
+
"total_flos": 5.741178860545229e+17,
|
239 |
+
"trial_name": null,
|
240 |
+
"trial_params": null
|
241 |
+
}
|