jerlawson13
commited on
Training in progress, step 100
Browse files- all_results.json +4 -4
- model.safetensors +1 -1
- runs/Jul24_12-35-53_REDLGLAUCORE01/events.out.tfevents.1721852709.REDLGLAUCORE01.547362.30 +3 -0
- runs/Jul25_11-46-02_REDLGLAUCORE01/events.out.tfevents.1721933163.REDLGLAUCORE01.547362.45 +3 -0
- runs/Jul25_12-18-37_REDLGLAUCORE01/events.out.tfevents.1721935117.REDLGLAUCORE01.547362.51 +3 -0
- train_results.json +4 -4
- trainer_state.json +70 -70
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -5,8 +5,8 @@
|
|
5 |
"eval_samples_per_second": 9.337,
|
6 |
"eval_steps_per_second": 0.294,
|
7 |
"total_flos": 7.020774259082035e+17,
|
8 |
-
"train_loss": 0.
|
9 |
-
"train_runtime":
|
10 |
-
"train_samples_per_second": 3.
|
11 |
-
"train_steps_per_second": 0.
|
12 |
}
|
|
|
5 |
"eval_samples_per_second": 9.337,
|
6 |
"eval_steps_per_second": 0.294,
|
7 |
"total_flos": 7.020774259082035e+17,
|
8 |
+
"train_loss": 0.16532422492378637,
|
9 |
+
"train_runtime": 2902.1592,
|
10 |
+
"train_samples_per_second": 3.142,
|
11 |
+
"train_steps_per_second": 0.098
|
12 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343223968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d6f7a6b18d0da72c185a99fe4e8643208b64100f6b30484a743d7bd765ad554
|
3 |
size 343223968
|
runs/Jul24_12-35-53_REDLGLAUCORE01/events.out.tfevents.1721852709.REDLGLAUCORE01.547362.30
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a9c0e04ef2ad4dce4baa06297b75524cf5d657409e23c1d945a1365473b8215
|
3 |
+
size 1057
|
runs/Jul25_11-46-02_REDLGLAUCORE01/events.out.tfevents.1721933163.REDLGLAUCORE01.547362.45
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77edb10c6be98140556e0965b42e24a03c2b2ac2a1b6c5bb4988de61112c4d72
|
3 |
+
size 5050
|
runs/Jul25_12-18-37_REDLGLAUCORE01/events.out.tfevents.1721935117.REDLGLAUCORE01.547362.51
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f3c5e61a0151accc82d344a8993562ea5db6a3eb04080ce9a99f7df7d7c1007
|
3 |
+
size 7437
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
"total_flos": 7.020774259082035e+17,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second": 3.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
"total_flos": 7.020774259082035e+17,
|
4 |
+
"train_loss": 0.16532422492378637,
|
5 |
+
"train_runtime": 2902.1592,
|
6 |
+
"train_samples_per_second": 3.142,
|
7 |
+
"train_steps_per_second": 0.098
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "/home/projects/Project - Fundus Photo Glaucoma Detection (AI)//model_results/vit-base-gpu/checkpoint-200",
|
4 |
"epoch": 5.0,
|
5 |
"eval_steps": 100,
|
@@ -10,72 +10,72 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.17543859649122806,
|
13 |
-
"grad_norm": 1.
|
14 |
"learning_rate": 9.649122807017545e-06,
|
15 |
"loss": 0.6232,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.3508771929824561,
|
20 |
-
"grad_norm": 1.
|
21 |
"learning_rate": 9.298245614035088e-06,
|
22 |
-
"loss": 0.
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.5263157894736842,
|
27 |
-
"grad_norm": 1.
|
28 |
"learning_rate": 8.947368421052632e-06,
|
29 |
-
"loss": 0.
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.7017543859649122,
|
34 |
-
"grad_norm": 1.
|
35 |
"learning_rate": 8.596491228070176e-06,
|
36 |
-
"loss": 0.
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.8771929824561403,
|
41 |
-
"grad_norm": 1.
|
42 |
"learning_rate": 8.24561403508772e-06,
|
43 |
-
"loss": 0.
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.0526315789473684,
|
48 |
-
"grad_norm": 0.
|
49 |
"learning_rate": 7.894736842105265e-06,
|
50 |
-
"loss": 0.
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
"epoch": 1.2280701754385965,
|
55 |
-
"grad_norm": 0.
|
56 |
"learning_rate": 7.5438596491228074e-06,
|
57 |
-
"loss": 0.
|
58 |
"step": 70
|
59 |
},
|
60 |
{
|
61 |
"epoch": 1.4035087719298245,
|
62 |
-
"grad_norm": 1.
|
63 |
"learning_rate": 7.192982456140352e-06,
|
64 |
-
"loss": 0.
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.5789473684210527,
|
69 |
-
"grad_norm": 0.
|
70 |
"learning_rate": 6.842105263157896e-06,
|
71 |
-
"loss": 0.
|
72 |
"step": 90
|
73 |
},
|
74 |
{
|
75 |
"epoch": 1.7543859649122808,
|
76 |
-
"grad_norm": 0.
|
77 |
"learning_rate": 6.491228070175439e-06,
|
78 |
-
"loss": 0.
|
79 |
"step": 100
|
80 |
},
|
81 |
{
|
@@ -91,165 +91,165 @@
|
|
91 |
161
|
92 |
]
|
93 |
],
|
94 |
-
"eval_loss": 0.
|
95 |
-
"eval_runtime":
|
96 |
-
"eval_samples_per_second":
|
97 |
-
"eval_steps_per_second": 0.
|
98 |
"step": 100
|
99 |
},
|
100 |
{
|
101 |
"epoch": 1.9298245614035088,
|
102 |
-
"grad_norm": 4.
|
103 |
"learning_rate": 6.140350877192983e-06,
|
104 |
-
"loss": 0.
|
105 |
"step": 110
|
106 |
},
|
107 |
{
|
108 |
"epoch": 2.1052631578947367,
|
109 |
-
"grad_norm": 0.
|
110 |
"learning_rate": 5.789473684210527e-06,
|
111 |
-
"loss": 0.
|
112 |
"step": 120
|
113 |
},
|
114 |
{
|
115 |
"epoch": 2.280701754385965,
|
116 |
-
"grad_norm": 0.
|
117 |
"learning_rate": 5.438596491228071e-06,
|
118 |
"loss": 0.1291,
|
119 |
"step": 130
|
120 |
},
|
121 |
{
|
122 |
"epoch": 2.456140350877193,
|
123 |
-
"grad_norm": 0.
|
124 |
"learning_rate": 5.087719298245615e-06,
|
125 |
-
"loss": 0.
|
126 |
"step": 140
|
127 |
},
|
128 |
{
|
129 |
"epoch": 2.6315789473684212,
|
130 |
-
"grad_norm": 0.
|
131 |
"learning_rate": 4.736842105263158e-06,
|
132 |
-
"loss": 0.
|
133 |
"step": 150
|
134 |
},
|
135 |
{
|
136 |
"epoch": 2.807017543859649,
|
137 |
-
"grad_norm": 0.
|
138 |
"learning_rate": 4.385964912280702e-06,
|
139 |
-
"loss": 0.
|
140 |
"step": 160
|
141 |
},
|
142 |
{
|
143 |
"epoch": 2.982456140350877,
|
144 |
-
"grad_norm": 1.
|
145 |
"learning_rate": 4.035087719298246e-06,
|
146 |
-
"loss": 0.
|
147 |
"step": 170
|
148 |
},
|
149 |
{
|
150 |
"epoch": 3.1578947368421053,
|
151 |
-
"grad_norm": 0.
|
152 |
"learning_rate": 3.6842105263157896e-06,
|
153 |
-
"loss": 0.
|
154 |
"step": 180
|
155 |
},
|
156 |
{
|
157 |
"epoch": 3.3333333333333335,
|
158 |
-
"grad_norm": 0.
|
159 |
"learning_rate": 3.3333333333333333e-06,
|
160 |
-
"loss": 0.
|
161 |
"step": 190
|
162 |
},
|
163 |
{
|
164 |
"epoch": 3.5087719298245617,
|
165 |
-
"grad_norm": 0.
|
166 |
"learning_rate": 2.9824561403508774e-06,
|
167 |
-
"loss": 0.
|
168 |
"step": 200
|
169 |
},
|
170 |
{
|
171 |
"epoch": 3.5087719298245617,
|
172 |
-
"eval_accuracy": 0.
|
173 |
"eval_confusion_matrix": [
|
174 |
[
|
175 |
-
|
176 |
-
|
177 |
],
|
178 |
[
|
179 |
0,
|
180 |
161
|
181 |
]
|
182 |
],
|
183 |
-
"eval_loss": 0.
|
184 |
-
"eval_runtime":
|
185 |
-
"eval_samples_per_second":
|
186 |
-
"eval_steps_per_second": 0.
|
187 |
"step": 200
|
188 |
},
|
189 |
{
|
190 |
"epoch": 3.6842105263157894,
|
191 |
-
"grad_norm": 0.
|
192 |
"learning_rate": 2.631578947368421e-06,
|
193 |
-
"loss": 0.
|
194 |
"step": 210
|
195 |
},
|
196 |
{
|
197 |
"epoch": 3.8596491228070176,
|
198 |
-
"grad_norm": 0.
|
199 |
"learning_rate": 2.280701754385965e-06,
|
200 |
-
"loss": 0.
|
201 |
"step": 220
|
202 |
},
|
203 |
{
|
204 |
"epoch": 4.035087719298246,
|
205 |
-
"grad_norm": 0.
|
206 |
"learning_rate": 1.929824561403509e-06,
|
207 |
-
"loss": 0.
|
208 |
"step": 230
|
209 |
},
|
210 |
{
|
211 |
"epoch": 4.2105263157894735,
|
212 |
-
"grad_norm": 0.
|
213 |
"learning_rate": 1.5789473684210526e-06,
|
214 |
-
"loss": 0.
|
215 |
"step": 240
|
216 |
},
|
217 |
{
|
218 |
"epoch": 4.385964912280702,
|
219 |
-
"grad_norm": 0.
|
220 |
"learning_rate": 1.2280701754385965e-06,
|
221 |
-
"loss": 0.
|
222 |
"step": 250
|
223 |
},
|
224 |
{
|
225 |
"epoch": 4.56140350877193,
|
226 |
-
"grad_norm": 0.
|
227 |
"learning_rate": 8.771929824561404e-07,
|
228 |
-
"loss": 0.
|
229 |
"step": 260
|
230 |
},
|
231 |
{
|
232 |
"epoch": 4.7368421052631575,
|
233 |
-
"grad_norm": 0.
|
234 |
"learning_rate": 5.263157894736843e-07,
|
235 |
-
"loss": 0.
|
236 |
"step": 270
|
237 |
},
|
238 |
{
|
239 |
"epoch": 4.912280701754386,
|
240 |
-
"grad_norm": 0.
|
241 |
"learning_rate": 1.7543859649122808e-07,
|
242 |
-
"loss": 0.
|
243 |
"step": 280
|
244 |
},
|
245 |
{
|
246 |
"epoch": 5.0,
|
247 |
"step": 285,
|
248 |
"total_flos": 7.020774259082035e+17,
|
249 |
-
"train_loss": 0.
|
250 |
-
"train_runtime":
|
251 |
-
"train_samples_per_second": 3.
|
252 |
-
"train_steps_per_second": 0.
|
253 |
}
|
254 |
],
|
255 |
"logging_steps": 10,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.11641146242618561,
|
3 |
"best_model_checkpoint": "/home/projects/Project - Fundus Photo Glaucoma Detection (AI)//model_results/vit-base-gpu/checkpoint-200",
|
4 |
"epoch": 5.0,
|
5 |
"eval_steps": 100,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.17543859649122806,
|
13 |
+
"grad_norm": 1.276576280593872,
|
14 |
"learning_rate": 9.649122807017545e-06,
|
15 |
"loss": 0.6232,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.3508771929824561,
|
20 |
+
"grad_norm": 1.7671723365783691,
|
21 |
"learning_rate": 9.298245614035088e-06,
|
22 |
+
"loss": 0.4728,
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.5263157894736842,
|
27 |
+
"grad_norm": 1.358464241027832,
|
28 |
"learning_rate": 8.947368421052632e-06,
|
29 |
+
"loss": 0.3828,
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.7017543859649122,
|
34 |
+
"grad_norm": 1.4662245512008667,
|
35 |
"learning_rate": 8.596491228070176e-06,
|
36 |
+
"loss": 0.3042,
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.8771929824561403,
|
41 |
+
"grad_norm": 1.1634291410446167,
|
42 |
"learning_rate": 8.24561403508772e-06,
|
43 |
+
"loss": 0.286,
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.0526315789473684,
|
48 |
+
"grad_norm": 0.8176971077919006,
|
49 |
"learning_rate": 7.894736842105265e-06,
|
50 |
+
"loss": 0.2169,
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
"epoch": 1.2280701754385965,
|
55 |
+
"grad_norm": 0.6673957705497742,
|
56 |
"learning_rate": 7.5438596491228074e-06,
|
57 |
+
"loss": 0.2044,
|
58 |
"step": 70
|
59 |
},
|
60 |
{
|
61 |
"epoch": 1.4035087719298245,
|
62 |
+
"grad_norm": 1.1810154914855957,
|
63 |
"learning_rate": 7.192982456140352e-06,
|
64 |
+
"loss": 0.1821,
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.5789473684210527,
|
69 |
+
"grad_norm": 0.759559690952301,
|
70 |
"learning_rate": 6.842105263157896e-06,
|
71 |
+
"loss": 0.1558,
|
72 |
"step": 90
|
73 |
},
|
74 |
{
|
75 |
"epoch": 1.7543859649122808,
|
76 |
+
"grad_norm": 0.4498167037963867,
|
77 |
"learning_rate": 6.491228070175439e-06,
|
78 |
+
"loss": 0.149,
|
79 |
"step": 100
|
80 |
},
|
81 |
{
|
|
|
91 |
161
|
92 |
]
|
93 |
],
|
94 |
+
"eval_loss": 0.17813891172409058,
|
95 |
+
"eval_runtime": 25.2489,
|
96 |
+
"eval_samples_per_second": 8.99,
|
97 |
+
"eval_steps_per_second": 0.317,
|
98 |
"step": 100
|
99 |
},
|
100 |
{
|
101 |
"epoch": 1.9298245614035088,
|
102 |
+
"grad_norm": 4.42154598236084,
|
103 |
"learning_rate": 6.140350877192983e-06,
|
104 |
+
"loss": 0.1435,
|
105 |
"step": 110
|
106 |
},
|
107 |
{
|
108 |
"epoch": 2.1052631578947367,
|
109 |
+
"grad_norm": 0.48428404331207275,
|
110 |
"learning_rate": 5.789473684210527e-06,
|
111 |
+
"loss": 0.1275,
|
112 |
"step": 120
|
113 |
},
|
114 |
{
|
115 |
"epoch": 2.280701754385965,
|
116 |
+
"grad_norm": 0.41149669885635376,
|
117 |
"learning_rate": 5.438596491228071e-06,
|
118 |
"loss": 0.1291,
|
119 |
"step": 130
|
120 |
},
|
121 |
{
|
122 |
"epoch": 2.456140350877193,
|
123 |
+
"grad_norm": 0.49232661724090576,
|
124 |
"learning_rate": 5.087719298245615e-06,
|
125 |
+
"loss": 0.0896,
|
126 |
"step": 140
|
127 |
},
|
128 |
{
|
129 |
"epoch": 2.6315789473684212,
|
130 |
+
"grad_norm": 0.36095741391181946,
|
131 |
"learning_rate": 4.736842105263158e-06,
|
132 |
+
"loss": 0.0997,
|
133 |
"step": 150
|
134 |
},
|
135 |
{
|
136 |
"epoch": 2.807017543859649,
|
137 |
+
"grad_norm": 0.4267736077308655,
|
138 |
"learning_rate": 4.385964912280702e-06,
|
139 |
+
"loss": 0.0925,
|
140 |
"step": 160
|
141 |
},
|
142 |
{
|
143 |
"epoch": 2.982456140350877,
|
144 |
+
"grad_norm": 1.9955291748046875,
|
145 |
"learning_rate": 4.035087719298246e-06,
|
146 |
+
"loss": 0.0907,
|
147 |
"step": 170
|
148 |
},
|
149 |
{
|
150 |
"epoch": 3.1578947368421053,
|
151 |
+
"grad_norm": 0.3319329619407654,
|
152 |
"learning_rate": 3.6842105263157896e-06,
|
153 |
+
"loss": 0.0979,
|
154 |
"step": 180
|
155 |
},
|
156 |
{
|
157 |
"epoch": 3.3333333333333335,
|
158 |
+
"grad_norm": 0.35440099239349365,
|
159 |
"learning_rate": 3.3333333333333333e-06,
|
160 |
+
"loss": 0.0886,
|
161 |
"step": 190
|
162 |
},
|
163 |
{
|
164 |
"epoch": 3.5087719298245617,
|
165 |
+
"grad_norm": 0.5289174318313599,
|
166 |
"learning_rate": 2.9824561403508774e-06,
|
167 |
+
"loss": 0.0996,
|
168 |
"step": 200
|
169 |
},
|
170 |
{
|
171 |
"epoch": 3.5087719298245617,
|
172 |
+
"eval_accuracy": 0.973568281938326,
|
173 |
"eval_confusion_matrix": [
|
174 |
[
|
175 |
+
60,
|
176 |
+
6
|
177 |
],
|
178 |
[
|
179 |
0,
|
180 |
161
|
181 |
]
|
182 |
],
|
183 |
+
"eval_loss": 0.11641146242618561,
|
184 |
+
"eval_runtime": 25.5874,
|
185 |
+
"eval_samples_per_second": 8.872,
|
186 |
+
"eval_steps_per_second": 0.313,
|
187 |
"step": 200
|
188 |
},
|
189 |
{
|
190 |
"epoch": 3.6842105263157894,
|
191 |
+
"grad_norm": 0.3807942569255829,
|
192 |
"learning_rate": 2.631578947368421e-06,
|
193 |
+
"loss": 0.1028,
|
194 |
"step": 210
|
195 |
},
|
196 |
{
|
197 |
"epoch": 3.8596491228070176,
|
198 |
+
"grad_norm": 0.6208366751670837,
|
199 |
"learning_rate": 2.280701754385965e-06,
|
200 |
+
"loss": 0.0741,
|
201 |
"step": 220
|
202 |
},
|
203 |
{
|
204 |
"epoch": 4.035087719298246,
|
205 |
+
"grad_norm": 0.7710980176925659,
|
206 |
"learning_rate": 1.929824561403509e-06,
|
207 |
+
"loss": 0.1073,
|
208 |
"step": 230
|
209 |
},
|
210 |
{
|
211 |
"epoch": 4.2105263157894735,
|
212 |
+
"grad_norm": 0.36691102385520935,
|
213 |
"learning_rate": 1.5789473684210526e-06,
|
214 |
+
"loss": 0.0777,
|
215 |
"step": 240
|
216 |
},
|
217 |
{
|
218 |
"epoch": 4.385964912280702,
|
219 |
+
"grad_norm": 0.29168033599853516,
|
220 |
"learning_rate": 1.2280701754385965e-06,
|
221 |
+
"loss": 0.0614,
|
222 |
"step": 250
|
223 |
},
|
224 |
{
|
225 |
"epoch": 4.56140350877193,
|
226 |
+
"grad_norm": 0.2981802821159363,
|
227 |
"learning_rate": 8.771929824561404e-07,
|
228 |
+
"loss": 0.0601,
|
229 |
"step": 260
|
230 |
},
|
231 |
{
|
232 |
"epoch": 4.7368421052631575,
|
233 |
+
"grad_norm": 0.28405195474624634,
|
234 |
"learning_rate": 5.263157894736843e-07,
|
235 |
+
"loss": 0.0525,
|
236 |
"step": 270
|
237 |
},
|
238 |
{
|
239 |
"epoch": 4.912280701754386,
|
240 |
+
"grad_norm": 0.5508224964141846,
|
241 |
"learning_rate": 1.7543859649122808e-07,
|
242 |
+
"loss": 0.0904,
|
243 |
"step": 280
|
244 |
},
|
245 |
{
|
246 |
"epoch": 5.0,
|
247 |
"step": 285,
|
248 |
"total_flos": 7.020774259082035e+17,
|
249 |
+
"train_loss": 0.16532422492378637,
|
250 |
+
"train_runtime": 2902.1592,
|
251 |
+
"train_samples_per_second": 3.142,
|
252 |
+
"train_steps_per_second": 0.098
|
253 |
}
|
254 |
],
|
255 |
"logging_steps": 10,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bf02dbf635dd7132d5414a7b6df1609bc0998eeaa814356e850cb9332a72661
|
3 |
size 5240
|