parvpareek commited on
Commit
5d9c3a1
1 Parent(s): 322fbae

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.98,
3
+ "eval_accuracy": 0.8483033932135728,
4
+ "eval_loss": 0.41903090476989746,
5
+ "eval_runtime": 21.2949,
6
+ "eval_samples_per_second": 47.054,
7
+ "eval_steps_per_second": 1.503,
8
+ "total_flos": 2.124298819894358e+18,
9
+ "train_loss": 0.6434233381634666,
10
+ "train_runtime": 1365.6224,
11
+ "train_samples_per_second": 19.8,
12
+ "train_steps_per_second": 0.154
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.98,
3
+ "eval_accuracy": 0.8483033932135728,
4
+ "eval_loss": 0.41903090476989746,
5
+ "eval_runtime": 21.2949,
6
+ "eval_samples_per_second": 47.054,
7
+ "eval_steps_per_second": 1.503
8
+ }
runs/Feb06_12-42-11_c60fb0bb745f/events.out.tfevents.1707224735.c60fb0bb745f.707.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96988aa234fefba97bed845998b4766bed48d61493d4aaa83ab6c53b7aceed8c
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.98,
3
+ "total_flos": 2.124298819894358e+18,
4
+ "train_loss": 0.6434233381634666,
5
+ "train_runtime": 1365.6224,
6
+ "train_samples_per_second": 19.8,
7
+ "train_steps_per_second": 0.154
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8483033932135728,
3
+ "best_model_checkpoint": "convnext-base-224-22k-1k-finetuned-eurosat/checkpoint-210",
4
+ "epoch": 2.978723404255319,
5
+ "eval_steps": 500,
6
+ "global_step": 210,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14,
13
+ "learning_rate": 2.380952380952381e-05,
14
+ "loss": 1.7284,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.28,
19
+ "learning_rate": 4.761904761904762e-05,
20
+ "loss": 1.0973,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.43,
25
+ "learning_rate": 4.761904761904762e-05,
26
+ "loss": 0.9371,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.57,
31
+ "learning_rate": 4.4973544973544974e-05,
32
+ "loss": 0.8303,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.71,
37
+ "learning_rate": 4.232804232804233e-05,
38
+ "loss": 0.7507,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.85,
43
+ "learning_rate": 3.968253968253968e-05,
44
+ "loss": 0.6892,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.99,
49
+ "learning_rate": 3.7037037037037037e-05,
50
+ "loss": 0.6643,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.99,
55
+ "eval_accuracy": 0.7754491017964071,
56
+ "eval_loss": 0.6090148687362671,
57
+ "eval_runtime": 20.9163,
58
+ "eval_samples_per_second": 47.905,
59
+ "eval_steps_per_second": 1.53,
60
+ "step": 70
61
+ },
62
+ {
63
+ "epoch": 1.13,
64
+ "learning_rate": 3.439153439153439e-05,
65
+ "loss": 0.5865,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 1.28,
70
+ "learning_rate": 3.1746031746031745e-05,
71
+ "loss": 0.5835,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.42,
76
+ "learning_rate": 2.91005291005291e-05,
77
+ "loss": 0.5331,
78
+ "step": 100
79
+ },
80
+ {
81
+ "epoch": 1.56,
82
+ "learning_rate": 2.6455026455026456e-05,
83
+ "loss": 0.542,
84
+ "step": 110
85
+ },
86
+ {
87
+ "epoch": 1.7,
88
+ "learning_rate": 2.380952380952381e-05,
89
+ "loss": 0.5329,
90
+ "step": 120
91
+ },
92
+ {
93
+ "epoch": 1.84,
94
+ "learning_rate": 2.1164021164021164e-05,
95
+ "loss": 0.494,
96
+ "step": 130
97
+ },
98
+ {
99
+ "epoch": 1.99,
100
+ "learning_rate": 1.8518518518518518e-05,
101
+ "loss": 0.4729,
102
+ "step": 140
103
+ },
104
+ {
105
+ "epoch": 2.0,
106
+ "eval_accuracy": 0.8253493013972056,
107
+ "eval_loss": 0.4640671908855438,
108
+ "eval_runtime": 20.9281,
109
+ "eval_samples_per_second": 47.878,
110
+ "eval_steps_per_second": 1.529,
111
+ "step": 141
112
+ },
113
+ {
114
+ "epoch": 2.13,
115
+ "learning_rate": 1.5873015873015872e-05,
116
+ "loss": 0.4971,
117
+ "step": 150
118
+ },
119
+ {
120
+ "epoch": 2.27,
121
+ "learning_rate": 1.3227513227513228e-05,
122
+ "loss": 0.4896,
123
+ "step": 160
124
+ },
125
+ {
126
+ "epoch": 2.41,
127
+ "learning_rate": 1.0582010582010582e-05,
128
+ "loss": 0.4267,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 2.55,
133
+ "learning_rate": 7.936507936507936e-06,
134
+ "loss": 0.4334,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 2.7,
139
+ "learning_rate": 5.291005291005291e-06,
140
+ "loss": 0.4326,
141
+ "step": 190
142
+ },
143
+ {
144
+ "epoch": 2.84,
145
+ "learning_rate": 2.6455026455026455e-06,
146
+ "loss": 0.4045,
147
+ "step": 200
148
+ },
149
+ {
150
+ "epoch": 2.98,
151
+ "learning_rate": 0.0,
152
+ "loss": 0.3858,
153
+ "step": 210
154
+ },
155
+ {
156
+ "epoch": 2.98,
157
+ "eval_accuracy": 0.8483033932135728,
158
+ "eval_loss": 0.41903090476989746,
159
+ "eval_runtime": 21.0738,
160
+ "eval_samples_per_second": 47.547,
161
+ "eval_steps_per_second": 1.518,
162
+ "step": 210
163
+ },
164
+ {
165
+ "epoch": 2.98,
166
+ "step": 210,
167
+ "total_flos": 2.124298819894358e+18,
168
+ "train_loss": 0.6434233381634666,
169
+ "train_runtime": 1365.6224,
170
+ "train_samples_per_second": 19.8,
171
+ "train_steps_per_second": 0.154
172
+ }
173
+ ],
174
+ "logging_steps": 10,
175
+ "max_steps": 210,
176
+ "num_train_epochs": 3,
177
+ "save_steps": 500,
178
+ "total_flos": 2.124298819894358e+18,
179
+ "trial_name": null,
180
+ "trial_params": null
181
+ }