jayanthspratap
commited on
Commit
•
6719fbb
1
Parent(s):
d14241d
End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.875,
|
4 |
+
"eval_loss": 0.6399165391921997,
|
5 |
+
"eval_runtime": 0.1762,
|
6 |
+
"eval_samples_per_second": 90.781,
|
7 |
+
"eval_steps_per_second": 22.695,
|
8 |
+
"total_flos": 1.33783041595392e+16,
|
9 |
+
"train_loss": 0.6580723881721496,
|
10 |
+
"train_runtime": 37.1608,
|
11 |
+
"train_samples_per_second": 16.953,
|
12 |
+
"train_steps_per_second": 1.076
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.875,
|
4 |
+
"eval_loss": 0.6399165391921997,
|
5 |
+
"eval_runtime": 0.1762,
|
6 |
+
"eval_samples_per_second": 90.781,
|
7 |
+
"eval_steps_per_second": 22.695
|
8 |
+
}
|
runs/May27_21-09-29_0922109e5cf6/events.out.tfevents.1685221840.0922109e5cf6.8213.29
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b6ecb7be64ef636f327761a50b62c21b7cdc63eab9822e17bd42121ab15c931
|
3 |
+
size 405
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 1.33783041595392e+16,
|
4 |
+
"train_loss": 0.6580723881721496,
|
5 |
+
"train_runtime": 37.1608,
|
6 |
+
"train_samples_per_second": 16.953,
|
7 |
+
"train_steps_per_second": 1.076
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.875,
|
3 |
+
"best_model_checkpoint": "resnet-50-drfx-surgery-classifier/checkpoint-8",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 40,
|
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": 0.8125,
|
13 |
+
"eval_loss": 0.6591495871543884,
|
14 |
+
"eval_runtime": 0.1233,
|
15 |
+
"eval_samples_per_second": 129.795,
|
16 |
+
"eval_steps_per_second": 32.449,
|
17 |
+
"step": 4
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.875,
|
22 |
+
"eval_loss": 0.6399165391921997,
|
23 |
+
"eval_runtime": 0.303,
|
24 |
+
"eval_samples_per_second": 52.801,
|
25 |
+
"eval_steps_per_second": 13.2,
|
26 |
+
"step": 8
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.5,
|
30 |
+
"learning_rate": 4.166666666666667e-06,
|
31 |
+
"loss": 0.6638,
|
32 |
+
"step": 10
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"eval_accuracy": 0.875,
|
37 |
+
"eval_loss": 0.6670691967010498,
|
38 |
+
"eval_runtime": 0.1445,
|
39 |
+
"eval_samples_per_second": 110.718,
|
40 |
+
"eval_steps_per_second": 27.68,
|
41 |
+
"step": 12
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 4.0,
|
45 |
+
"eval_accuracy": 0.8125,
|
46 |
+
"eval_loss": 0.6644818782806396,
|
47 |
+
"eval_runtime": 0.1229,
|
48 |
+
"eval_samples_per_second": 130.239,
|
49 |
+
"eval_steps_per_second": 32.56,
|
50 |
+
"step": 16
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 5.0,
|
54 |
+
"learning_rate": 2.7777777777777783e-06,
|
55 |
+
"loss": 0.6562,
|
56 |
+
"step": 20
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 5.0,
|
60 |
+
"eval_accuracy": 0.875,
|
61 |
+
"eval_loss": 0.6495161056518555,
|
62 |
+
"eval_runtime": 0.1279,
|
63 |
+
"eval_samples_per_second": 125.074,
|
64 |
+
"eval_steps_per_second": 31.269,
|
65 |
+
"step": 20
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 6.0,
|
69 |
+
"eval_accuracy": 0.875,
|
70 |
+
"eval_loss": 0.667277455329895,
|
71 |
+
"eval_runtime": 0.1224,
|
72 |
+
"eval_samples_per_second": 130.678,
|
73 |
+
"eval_steps_per_second": 32.67,
|
74 |
+
"step": 24
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 7.0,
|
78 |
+
"eval_accuracy": 0.875,
|
79 |
+
"eval_loss": 0.6539220809936523,
|
80 |
+
"eval_runtime": 0.1364,
|
81 |
+
"eval_samples_per_second": 117.345,
|
82 |
+
"eval_steps_per_second": 29.336,
|
83 |
+
"step": 28
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 7.5,
|
87 |
+
"learning_rate": 1.3888888888888892e-06,
|
88 |
+
"loss": 0.6527,
|
89 |
+
"step": 30
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 8.0,
|
93 |
+
"eval_accuracy": 0.875,
|
94 |
+
"eval_loss": 0.6519389152526855,
|
95 |
+
"eval_runtime": 0.1233,
|
96 |
+
"eval_samples_per_second": 129.77,
|
97 |
+
"eval_steps_per_second": 32.443,
|
98 |
+
"step": 32
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 9.0,
|
102 |
+
"eval_accuracy": 0.875,
|
103 |
+
"eval_loss": 0.6602637767791748,
|
104 |
+
"eval_runtime": 0.1675,
|
105 |
+
"eval_samples_per_second": 95.523,
|
106 |
+
"eval_steps_per_second": 23.881,
|
107 |
+
"step": 36
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 10.0,
|
111 |
+
"learning_rate": 0.0,
|
112 |
+
"loss": 0.6596,
|
113 |
+
"step": 40
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 10.0,
|
117 |
+
"eval_accuracy": 0.875,
|
118 |
+
"eval_loss": 0.6525369882583618,
|
119 |
+
"eval_runtime": 0.1937,
|
120 |
+
"eval_samples_per_second": 82.597,
|
121 |
+
"eval_steps_per_second": 20.649,
|
122 |
+
"step": 40
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 10.0,
|
126 |
+
"step": 40,
|
127 |
+
"total_flos": 1.33783041595392e+16,
|
128 |
+
"train_loss": 0.6580723881721496,
|
129 |
+
"train_runtime": 37.1608,
|
130 |
+
"train_samples_per_second": 16.953,
|
131 |
+
"train_steps_per_second": 1.076
|
132 |
+
}
|
133 |
+
],
|
134 |
+
"max_steps": 40,
|
135 |
+
"num_train_epochs": 10,
|
136 |
+
"total_flos": 1.33783041595392e+16,
|
137 |
+
"trial_name": null,
|
138 |
+
"trial_params": null
|
139 |
+
}
|