Update model
Browse files- all_results.json +8 -8
- config.json +14 -10
- eval_results.json +4 -4
- pytorch_model.bin +2 -2
- runs/Aug24_13-10-32_surveily-ag-02/events.out.tfevents.1692875577.surveily-ag-02.7570.6 +3 -0
- runs/Aug29_10-07-00_surveily-ag-02/events.out.tfevents.1693296436.surveily-ag-02.7767.0 +3 -0
- runs/Aug29_10-09-28_surveily-ag-02/events.out.tfevents.1693296572.surveily-ag-02.7767.1 +3 -0
- runs/Aug29_10-10-05_surveily-ag-02/events.out.tfevents.1693296608.surveily-ag-02.7767.2 +3 -0
- runs/Aug29_10-10-52_surveily-ag-02/events.out.tfevents.1693296656.surveily-ag-02.7767.3 +3 -0
- runs/Aug29_10-12-51_surveily-ag-02/events.out.tfevents.1693296776.surveily-ag-02.8993.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +72 -72
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
"eval_accuracy": 0.8181818181818182,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 1.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 3.
|
8 |
-
"train_loss": 0.
|
9 |
-
"train_runtime":
|
10 |
-
"train_samples_per_second": 10.
|
11 |
-
"train_steps_per_second": 2.
|
12 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
"eval_accuracy": 0.8181818181818182,
|
4 |
+
"eval_loss": 0.7670823335647583,
|
5 |
+
"eval_runtime": 1.4179,
|
6 |
+
"eval_samples_per_second": 23.275,
|
7 |
+
"eval_steps_per_second": 3.526,
|
8 |
+
"train_loss": 0.10890771941714254,
|
9 |
+
"train_runtime": 100.0908,
|
10 |
+
"train_samples_per_second": 10.99,
|
11 |
+
"train_steps_per_second": 2.797
|
12 |
}
|
config.json
CHANGED
@@ -11,15 +11,17 @@
|
|
11 |
"id2label": {
|
12 |
"0": "airport",
|
13 |
"1": "bathroom",
|
14 |
-
"10": "
|
|
|
|
|
15 |
"2": "beach",
|
16 |
"3": "building_site",
|
17 |
"4": "factory",
|
18 |
"5": "food",
|
19 |
-
"6": "
|
20 |
-
"7": "
|
21 |
-
"8": "
|
22 |
-
"9": "
|
23 |
},
|
24 |
"image_size": 224,
|
25 |
"initializer_range": 0.02,
|
@@ -31,11 +33,13 @@
|
|
31 |
"building_site": "3",
|
32 |
"factory": "4",
|
33 |
"food": "5",
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
|
|
|
|
39 |
},
|
40 |
"layer_norm_eps": 1e-12,
|
41 |
"model_type": "vit",
|
|
|
11 |
"id2label": {
|
12 |
"0": "airport",
|
13 |
"1": "bathroom",
|
14 |
+
"10": "skatepark",
|
15 |
+
"11": "warehouse",
|
16 |
+
"12": "zoo",
|
17 |
"2": "beach",
|
18 |
"3": "building_site",
|
19 |
"4": "factory",
|
20 |
"5": "food",
|
21 |
+
"6": "harbour",
|
22 |
+
"7": "office",
|
23 |
+
"8": "railway",
|
24 |
+
"9": "road"
|
25 |
},
|
26 |
"image_size": 224,
|
27 |
"initializer_range": 0.02,
|
|
|
33 |
"building_site": "3",
|
34 |
"factory": "4",
|
35 |
"food": "5",
|
36 |
+
"harbour": "6",
|
37 |
+
"office": "7",
|
38 |
+
"railway": "8",
|
39 |
+
"road": "9",
|
40 |
+
"skatepark": "10",
|
41 |
+
"warehouse": "11",
|
42 |
+
"zoo": "12"
|
43 |
},
|
44 |
"layer_norm_eps": 1e-12,
|
45 |
"model_type": "vit",
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
"eval_accuracy": 0.8181818181818182,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 1.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 3.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
"eval_accuracy": 0.8181818181818182,
|
4 |
+
"eval_loss": 0.7670823335647583,
|
5 |
+
"eval_runtime": 1.4179,
|
6 |
+
"eval_samples_per_second": 23.275,
|
7 |
+
"eval_steps_per_second": 3.526
|
8 |
}
|
pytorch_model.bin
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:c57f45b24cf49970d490c292edff8e45c5037cb2caec37dbe71d9fc48e83b006
|
3 |
+
size 343302509
|
runs/Aug24_13-10-32_surveily-ag-02/events.out.tfevents.1692875577.surveily-ag-02.7570.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7f5cf7907f214aba4c8ffe6d5b1e10a879b9d83afc66f5a3df6c9b9d14225a4
|
3 |
+
size 411
|
runs/Aug29_10-07-00_surveily-ag-02/events.out.tfevents.1693296436.surveily-ag-02.7767.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a89de60cfb50cd93335caa91e13525403283e1a7ffde883e27991236340800d4
|
3 |
+
size 10123
|
runs/Aug29_10-09-28_surveily-ag-02/events.out.tfevents.1693296572.surveily-ag-02.7767.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2010437f54722d1c776676b0ae24b1388c307579b4948bacd89527d00693566
|
3 |
+
size 5138
|
runs/Aug29_10-10-05_surveily-ag-02/events.out.tfevents.1693296608.surveily-ag-02.7767.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eea89bfdcfcdc03b8e5beef3fc5148106ffec08a0d1de2bd880e6f2b1ed7c985
|
3 |
+
size 5908
|
runs/Aug29_10-10-52_surveily-ag-02/events.out.tfevents.1693296656.surveily-ag-02.7767.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d327dde2824fd7379dde14c22771bc4f2d368e4a79fe4ec81194539bffddbf1
|
3 |
+
size 8418
|
runs/Aug29_10-12-51_surveily-ag-02/events.out.tfevents.1693296776.surveily-ag-02.8993.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:713c31164b205b544d80b5a36da7f7452aad2ab04173356586b37ed97c51235c
|
3 |
+
size 8418
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second": 10.
|
6 |
-
"train_steps_per_second": 2.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"train_loss": 0.10890771941714254,
|
4 |
+
"train_runtime": 100.0908,
|
5 |
+
"train_samples_per_second": 10.99,
|
6 |
+
"train_steps_per_second": 2.797
|
7 |
}
|
trainer_state.json
CHANGED
@@ -9,230 +9,230 @@
|
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.71,
|
12 |
-
"learning_rate": 0.
|
13 |
-
"loss":
|
14 |
"step": 10
|
15 |
},
|
16 |
{
|
17 |
"epoch": 1.43,
|
18 |
-
"learning_rate": 0.
|
19 |
-
"loss":
|
20 |
"step": 20
|
21 |
},
|
22 |
{
|
23 |
"epoch": 2.14,
|
24 |
-
"learning_rate": 0.
|
25 |
-
"loss": 0.
|
26 |
"step": 30
|
27 |
},
|
28 |
{
|
29 |
"epoch": 2.86,
|
30 |
-
"learning_rate": 0.
|
31 |
-
"loss": 0.
|
32 |
"step": 40
|
33 |
},
|
34 |
{
|
35 |
"epoch": 3.57,
|
36 |
-
"learning_rate": 0.
|
37 |
-
"loss": 0.
|
38 |
"step": 50
|
39 |
},
|
40 |
{
|
41 |
"epoch": 3.57,
|
42 |
-
"eval_accuracy": 0.
|
43 |
-
"eval_loss":
|
44 |
-
"eval_runtime": 1.
|
45 |
-
"eval_samples_per_second": 25.
|
46 |
-
"eval_steps_per_second": 3.
|
47 |
"step": 50
|
48 |
},
|
49 |
{
|
50 |
"epoch": 4.29,
|
51 |
-
"learning_rate": 0.
|
52 |
-
"loss": 0.
|
53 |
"step": 60
|
54 |
},
|
55 |
{
|
56 |
"epoch": 5.0,
|
57 |
-
"learning_rate": 0.
|
58 |
-
"loss": 0.
|
59 |
"step": 70
|
60 |
},
|
61 |
{
|
62 |
"epoch": 5.71,
|
63 |
-
"learning_rate": 0.
|
64 |
-
"loss": 0.
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
"epoch": 6.43,
|
69 |
-
"learning_rate": 0.
|
70 |
-
"loss": 0.
|
71 |
"step": 90
|
72 |
},
|
73 |
{
|
74 |
"epoch": 7.14,
|
75 |
-
"learning_rate": 0.
|
76 |
-
"loss": 0.
|
77 |
"step": 100
|
78 |
},
|
79 |
{
|
80 |
"epoch": 7.14,
|
81 |
-
"eval_accuracy": 0.
|
82 |
-
"eval_loss": 0.
|
83 |
-
"eval_runtime": 1.
|
84 |
-
"eval_samples_per_second":
|
85 |
-
"eval_steps_per_second":
|
86 |
"step": 100
|
87 |
},
|
88 |
{
|
89 |
"epoch": 7.86,
|
90 |
-
"learning_rate": 0.
|
91 |
"loss": 0.0005,
|
92 |
"step": 110
|
93 |
},
|
94 |
{
|
95 |
"epoch": 8.57,
|
96 |
-
"learning_rate": 0.
|
97 |
-
"loss": 0.
|
98 |
"step": 120
|
99 |
},
|
100 |
{
|
101 |
"epoch": 9.29,
|
102 |
-
"learning_rate": 0.
|
103 |
-
"loss": 0.
|
104 |
"step": 130
|
105 |
},
|
106 |
{
|
107 |
"epoch": 10.0,
|
108 |
-
"learning_rate": 0.
|
109 |
"loss": 0.0004,
|
110 |
"step": 140
|
111 |
},
|
112 |
{
|
113 |
"epoch": 10.71,
|
114 |
-
"learning_rate": 9.
|
115 |
"loss": 0.0004,
|
116 |
"step": 150
|
117 |
},
|
118 |
{
|
119 |
"epoch": 10.71,
|
120 |
-
"eval_accuracy": 0.
|
121 |
-
"eval_loss": 0.
|
122 |
-
"eval_runtime": 1.
|
123 |
-
"eval_samples_per_second":
|
124 |
-
"eval_steps_per_second":
|
125 |
"step": 150
|
126 |
},
|
127 |
{
|
128 |
"epoch": 11.43,
|
129 |
-
"learning_rate": 8.
|
130 |
-
"loss": 0.
|
131 |
"step": 160
|
132 |
},
|
133 |
{
|
134 |
"epoch": 12.14,
|
135 |
-
"learning_rate":
|
136 |
-
"loss": 0.
|
137 |
"step": 170
|
138 |
},
|
139 |
{
|
140 |
"epoch": 12.86,
|
141 |
-
"learning_rate": 7.
|
142 |
-
"loss": 0.
|
143 |
"step": 180
|
144 |
},
|
145 |
{
|
146 |
"epoch": 13.57,
|
147 |
-
"learning_rate": 6.
|
148 |
"loss": 0.0003,
|
149 |
"step": 190
|
150 |
},
|
151 |
{
|
152 |
"epoch": 14.29,
|
153 |
-
"learning_rate": 5.
|
154 |
"loss": 0.0003,
|
155 |
"step": 200
|
156 |
},
|
157 |
{
|
158 |
"epoch": 14.29,
|
159 |
"eval_accuracy": 0.8181818181818182,
|
160 |
-
"eval_loss": 0.
|
161 |
-
"eval_runtime": 1.
|
162 |
-
"eval_samples_per_second":
|
163 |
-
"eval_steps_per_second":
|
164 |
"step": 200
|
165 |
},
|
166 |
{
|
167 |
"epoch": 15.0,
|
168 |
-
"learning_rate": 5.
|
169 |
"loss": 0.0003,
|
170 |
"step": 210
|
171 |
},
|
172 |
{
|
173 |
"epoch": 15.71,
|
174 |
-
"learning_rate": 4.
|
175 |
"loss": 0.0003,
|
176 |
"step": 220
|
177 |
},
|
178 |
{
|
179 |
"epoch": 16.43,
|
180 |
-
"learning_rate": 3.
|
181 |
"loss": 0.0003,
|
182 |
"step": 230
|
183 |
},
|
184 |
{
|
185 |
"epoch": 17.14,
|
186 |
-
"learning_rate":
|
187 |
"loss": 0.0003,
|
188 |
"step": 240
|
189 |
},
|
190 |
{
|
191 |
"epoch": 17.86,
|
192 |
-
"learning_rate": 2.
|
193 |
"loss": 0.0003,
|
194 |
"step": 250
|
195 |
},
|
196 |
{
|
197 |
"epoch": 17.86,
|
198 |
"eval_accuracy": 0.8181818181818182,
|
199 |
-
"eval_loss": 0.
|
200 |
-
"eval_runtime": 1.
|
201 |
-
"eval_samples_per_second":
|
202 |
-
"eval_steps_per_second":
|
203 |
"step": 250
|
204 |
},
|
205 |
{
|
206 |
"epoch": 18.57,
|
207 |
-
"learning_rate": 1.
|
208 |
"loss": 0.0003,
|
209 |
"step": 260
|
210 |
},
|
211 |
{
|
212 |
"epoch": 19.29,
|
213 |
-
"learning_rate":
|
214 |
"loss": 0.0003,
|
215 |
"step": 270
|
216 |
},
|
217 |
{
|
218 |
"epoch": 20.0,
|
219 |
-
"learning_rate":
|
220 |
"loss": 0.0003,
|
221 |
"step": 280
|
222 |
},
|
223 |
{
|
224 |
"epoch": 20.0,
|
225 |
"step": 280,
|
226 |
-
"total_flos": 8.
|
227 |
-
"train_loss": 0.
|
228 |
-
"train_runtime":
|
229 |
-
"train_samples_per_second": 10.
|
230 |
-
"train_steps_per_second": 2.
|
231 |
}
|
232 |
],
|
233 |
"max_steps": 280,
|
234 |
"num_train_epochs": 20,
|
235 |
-
"total_flos": 8.
|
236 |
"trial_name": null,
|
237 |
"trial_params": null
|
238 |
}
|
|
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 0.71,
|
12 |
+
"learning_rate": 0.00019357142857142858,
|
13 |
+
"loss": 1.9919,
|
14 |
"step": 10
|
15 |
},
|
16 |
{
|
17 |
"epoch": 1.43,
|
18 |
+
"learning_rate": 0.00018642857142857144,
|
19 |
+
"loss": 0.8872,
|
20 |
"step": 20
|
21 |
},
|
22 |
{
|
23 |
"epoch": 2.14,
|
24 |
+
"learning_rate": 0.0001792857142857143,
|
25 |
+
"loss": 0.1348,
|
26 |
"step": 30
|
27 |
},
|
28 |
{
|
29 |
"epoch": 2.86,
|
30 |
+
"learning_rate": 0.00017214285714285717,
|
31 |
+
"loss": 0.0191,
|
32 |
"step": 40
|
33 |
},
|
34 |
{
|
35 |
"epoch": 3.57,
|
36 |
+
"learning_rate": 0.000165,
|
37 |
+
"loss": 0.004,
|
38 |
"step": 50
|
39 |
},
|
40 |
{
|
41 |
"epoch": 3.57,
|
42 |
+
"eval_accuracy": 0.7575757575757576,
|
43 |
+
"eval_loss": 1.07438063621521,
|
44 |
+
"eval_runtime": 1.2746,
|
45 |
+
"eval_samples_per_second": 25.891,
|
46 |
+
"eval_steps_per_second": 3.923,
|
47 |
"step": 50
|
48 |
},
|
49 |
{
|
50 |
"epoch": 4.29,
|
51 |
+
"learning_rate": 0.00015785714285714285,
|
52 |
+
"loss": 0.0034,
|
53 |
"step": 60
|
54 |
},
|
55 |
{
|
56 |
"epoch": 5.0,
|
57 |
+
"learning_rate": 0.0001507142857142857,
|
58 |
+
"loss": 0.0012,
|
59 |
"step": 70
|
60 |
},
|
61 |
{
|
62 |
"epoch": 5.71,
|
63 |
+
"learning_rate": 0.0001435714285714286,
|
64 |
+
"loss": 0.0008,
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
"epoch": 6.43,
|
69 |
+
"learning_rate": 0.00013642857142857144,
|
70 |
+
"loss": 0.0008,
|
71 |
"step": 90
|
72 |
},
|
73 |
{
|
74 |
"epoch": 7.14,
|
75 |
+
"learning_rate": 0.0001292857142857143,
|
76 |
+
"loss": 0.0005,
|
77 |
"step": 100
|
78 |
},
|
79 |
{
|
80 |
"epoch": 7.14,
|
81 |
+
"eval_accuracy": 0.7878787878787878,
|
82 |
+
"eval_loss": 0.8181638121604919,
|
83 |
+
"eval_runtime": 1.1472,
|
84 |
+
"eval_samples_per_second": 28.766,
|
85 |
+
"eval_steps_per_second": 4.358,
|
86 |
"step": 100
|
87 |
},
|
88 |
{
|
89 |
"epoch": 7.86,
|
90 |
+
"learning_rate": 0.00012214285714285715,
|
91 |
"loss": 0.0005,
|
92 |
"step": 110
|
93 |
},
|
94 |
{
|
95 |
"epoch": 8.57,
|
96 |
+
"learning_rate": 0.00011499999999999999,
|
97 |
+
"loss": 0.0004,
|
98 |
"step": 120
|
99 |
},
|
100 |
{
|
101 |
"epoch": 9.29,
|
102 |
+
"learning_rate": 0.00010785714285714286,
|
103 |
+
"loss": 0.0004,
|
104 |
"step": 130
|
105 |
},
|
106 |
{
|
107 |
"epoch": 10.0,
|
108 |
+
"learning_rate": 0.00010071428571428571,
|
109 |
"loss": 0.0004,
|
110 |
"step": 140
|
111 |
},
|
112 |
{
|
113 |
"epoch": 10.71,
|
114 |
+
"learning_rate": 9.357142857142858e-05,
|
115 |
"loss": 0.0004,
|
116 |
"step": 150
|
117 |
},
|
118 |
{
|
119 |
"epoch": 10.71,
|
120 |
+
"eval_accuracy": 0.7878787878787878,
|
121 |
+
"eval_loss": 0.7808332443237305,
|
122 |
+
"eval_runtime": 1.1203,
|
123 |
+
"eval_samples_per_second": 29.456,
|
124 |
+
"eval_steps_per_second": 4.463,
|
125 |
"step": 150
|
126 |
},
|
127 |
{
|
128 |
"epoch": 11.43,
|
129 |
+
"learning_rate": 8.642857142857143e-05,
|
130 |
+
"loss": 0.0003,
|
131 |
"step": 160
|
132 |
},
|
133 |
{
|
134 |
"epoch": 12.14,
|
135 |
+
"learning_rate": 7.928571428571429e-05,
|
136 |
+
"loss": 0.0003,
|
137 |
"step": 170
|
138 |
},
|
139 |
{
|
140 |
"epoch": 12.86,
|
141 |
+
"learning_rate": 7.214285714285714e-05,
|
142 |
+
"loss": 0.0003,
|
143 |
"step": 180
|
144 |
},
|
145 |
{
|
146 |
"epoch": 13.57,
|
147 |
+
"learning_rate": 6.500000000000001e-05,
|
148 |
"loss": 0.0003,
|
149 |
"step": 190
|
150 |
},
|
151 |
{
|
152 |
"epoch": 14.29,
|
153 |
+
"learning_rate": 5.785714285714287e-05,
|
154 |
"loss": 0.0003,
|
155 |
"step": 200
|
156 |
},
|
157 |
{
|
158 |
"epoch": 14.29,
|
159 |
"eval_accuracy": 0.8181818181818182,
|
160 |
+
"eval_loss": 0.7710055112838745,
|
161 |
+
"eval_runtime": 1.1654,
|
162 |
+
"eval_samples_per_second": 28.316,
|
163 |
+
"eval_steps_per_second": 4.29,
|
164 |
"step": 200
|
165 |
},
|
166 |
{
|
167 |
"epoch": 15.0,
|
168 |
+
"learning_rate": 5.0714285714285716e-05,
|
169 |
"loss": 0.0003,
|
170 |
"step": 210
|
171 |
},
|
172 |
{
|
173 |
"epoch": 15.71,
|
174 |
+
"learning_rate": 4.3571428571428576e-05,
|
175 |
"loss": 0.0003,
|
176 |
"step": 220
|
177 |
},
|
178 |
{
|
179 |
"epoch": 16.43,
|
180 |
+
"learning_rate": 3.642857142857143e-05,
|
181 |
"loss": 0.0003,
|
182 |
"step": 230
|
183 |
},
|
184 |
{
|
185 |
"epoch": 17.14,
|
186 |
+
"learning_rate": 2.9285714285714288e-05,
|
187 |
"loss": 0.0003,
|
188 |
"step": 240
|
189 |
},
|
190 |
{
|
191 |
"epoch": 17.86,
|
192 |
+
"learning_rate": 2.214285714285714e-05,
|
193 |
"loss": 0.0003,
|
194 |
"step": 250
|
195 |
},
|
196 |
{
|
197 |
"epoch": 17.86,
|
198 |
"eval_accuracy": 0.8181818181818182,
|
199 |
+
"eval_loss": 0.7675150632858276,
|
200 |
+
"eval_runtime": 1.1463,
|
201 |
+
"eval_samples_per_second": 28.788,
|
202 |
+
"eval_steps_per_second": 4.362,
|
203 |
"step": 250
|
204 |
},
|
205 |
{
|
206 |
"epoch": 18.57,
|
207 |
+
"learning_rate": 1.5e-05,
|
208 |
"loss": 0.0003,
|
209 |
"step": 260
|
210 |
},
|
211 |
{
|
212 |
"epoch": 19.29,
|
213 |
+
"learning_rate": 7.857142857142858e-06,
|
214 |
"loss": 0.0003,
|
215 |
"step": 270
|
216 |
},
|
217 |
{
|
218 |
"epoch": 20.0,
|
219 |
+
"learning_rate": 7.142857142857143e-07,
|
220 |
"loss": 0.0003,
|
221 |
"step": 280
|
222 |
},
|
223 |
{
|
224 |
"epoch": 20.0,
|
225 |
"step": 280,
|
226 |
+
"total_flos": 8.5248064484352e+16,
|
227 |
+
"train_loss": 0.10890771941714254,
|
228 |
+
"train_runtime": 100.0908,
|
229 |
+
"train_samples_per_second": 10.99,
|
230 |
+
"train_steps_per_second": 2.797
|
231 |
}
|
232 |
],
|
233 |
"max_steps": 280,
|
234 |
"num_train_epochs": 20,
|
235 |
+
"total_flos": 8.5248064484352e+16,
|
236 |
"trial_name": null,
|
237 |
"trial_params": null
|
238 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c5b0c311923ad3075535c5b7986ef4fd4fdef3f2765192e5883dbe2d9c54862
|
3 |
size 3963
|