tommilyjones
commited on
Commit
•
6100d0f
1
Parent(s):
cc5a8bb
End of training
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +136 -0
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.95,
|
3 |
+
"eval_accuracy": 0.9973147153598282,
|
4 |
+
"eval_loss": 0.012631203979253769,
|
5 |
+
"eval_runtime": 4.7574,
|
6 |
+
"eval_samples_per_second": 391.393,
|
7 |
+
"eval_steps_per_second": 12.402,
|
8 |
+
"total_flos": 4.47059817899606e+17,
|
9 |
+
"train_loss": 0.12674185218857537,
|
10 |
+
"train_runtime": 92.7597,
|
11 |
+
"train_samples_per_second": 196.67,
|
12 |
+
"train_steps_per_second": 1.52
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.95,
|
3 |
+
"eval_accuracy": 0.9973147153598282,
|
4 |
+
"eval_loss": 0.012631203979253769,
|
5 |
+
"eval_runtime": 4.7574,
|
6 |
+
"eval_samples_per_second": 391.393,
|
7 |
+
"eval_steps_per_second": 12.402
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.95,
|
3 |
+
"total_flos": 4.47059817899606e+17,
|
4 |
+
"train_loss": 0.12674185218857537,
|
5 |
+
"train_runtime": 92.7597,
|
6 |
+
"train_samples_per_second": 196.67,
|
7 |
+
"train_steps_per_second": 1.52
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9973147153598282,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-cats_dogs\\checkpoint-95",
|
4 |
+
"epoch": 2.9528795811518327,
|
5 |
+
"global_step": 141,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.21,
|
12 |
+
"learning_rate": 3.3333333333333335e-05,
|
13 |
+
"loss": 0.6928,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.42,
|
18 |
+
"learning_rate": 4.801587301587302e-05,
|
19 |
+
"loss": 0.2636,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.63,
|
24 |
+
"learning_rate": 4.404761904761905e-05,
|
25 |
+
"loss": 0.0906,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.84,
|
30 |
+
"learning_rate": 4.007936507936508e-05,
|
31 |
+
"loss": 0.0832,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.98,
|
36 |
+
"eval_accuracy": 0.9908700322234156,
|
37 |
+
"eval_loss": 0.02349468320608139,
|
38 |
+
"eval_runtime": 5.9119,
|
39 |
+
"eval_samples_per_second": 314.957,
|
40 |
+
"eval_steps_per_second": 9.98,
|
41 |
+
"step": 47
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.05,
|
45 |
+
"learning_rate": 3.611111111111111e-05,
|
46 |
+
"loss": 0.1021,
|
47 |
+
"step": 50
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 1.26,
|
51 |
+
"learning_rate": 3.2142857142857144e-05,
|
52 |
+
"loss": 0.0882,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.47,
|
57 |
+
"learning_rate": 2.8174603174603175e-05,
|
58 |
+
"loss": 0.0583,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.68,
|
63 |
+
"learning_rate": 2.4206349206349206e-05,
|
64 |
+
"loss": 0.0643,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.88,
|
69 |
+
"learning_rate": 2.023809523809524e-05,
|
70 |
+
"loss": 0.0788,
|
71 |
+
"step": 90
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 1.99,
|
75 |
+
"eval_accuracy": 0.9973147153598282,
|
76 |
+
"eval_loss": 0.012631203979253769,
|
77 |
+
"eval_runtime": 5.1962,
|
78 |
+
"eval_samples_per_second": 358.336,
|
79 |
+
"eval_steps_per_second": 11.354,
|
80 |
+
"step": 95
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.09,
|
84 |
+
"learning_rate": 1.626984126984127e-05,
|
85 |
+
"loss": 0.067,
|
86 |
+
"step": 100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.3,
|
90 |
+
"learning_rate": 1.2301587301587301e-05,
|
91 |
+
"loss": 0.0499,
|
92 |
+
"step": 110
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.51,
|
96 |
+
"learning_rate": 8.333333333333334e-06,
|
97 |
+
"loss": 0.0459,
|
98 |
+
"step": 120
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.72,
|
102 |
+
"learning_rate": 4.365079365079365e-06,
|
103 |
+
"loss": 0.0449,
|
104 |
+
"step": 130
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.93,
|
108 |
+
"learning_rate": 3.9682539682539683e-07,
|
109 |
+
"loss": 0.0534,
|
110 |
+
"step": 140
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 2.95,
|
114 |
+
"eval_accuracy": 0.9957035445757251,
|
115 |
+
"eval_loss": 0.012667440809309483,
|
116 |
+
"eval_runtime": 5.1957,
|
117 |
+
"eval_samples_per_second": 358.371,
|
118 |
+
"eval_steps_per_second": 11.355,
|
119 |
+
"step": 141
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 2.95,
|
123 |
+
"step": 141,
|
124 |
+
"total_flos": 4.47059817899606e+17,
|
125 |
+
"train_loss": 0.12674185218857537,
|
126 |
+
"train_runtime": 92.7597,
|
127 |
+
"train_samples_per_second": 196.67,
|
128 |
+
"train_steps_per_second": 1.52
|
129 |
+
}
|
130 |
+
],
|
131 |
+
"max_steps": 141,
|
132 |
+
"num_train_epochs": 3,
|
133 |
+
"total_flos": 4.47059817899606e+17,
|
134 |
+
"trial_name": null,
|
135 |
+
"trial_params": null
|
136 |
+
}
|