End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.9196428571428571,
|
4 |
+
"eval_loss": 0.2128717005252838,
|
5 |
+
"eval_runtime": 1.7338,
|
6 |
+
"eval_samples_per_second": 64.599,
|
7 |
+
"eval_steps_per_second": 2.307,
|
8 |
+
"total_flos": 4.6849871171251814e+17,
|
9 |
+
"train_loss": 1.081290222349621,
|
10 |
+
"train_runtime": 252.638,
|
11 |
+
"train_samples_per_second": 74.419,
|
12 |
+
"train_steps_per_second": 0.582
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.9196428571428571,
|
4 |
+
"eval_loss": 0.2128717005252838,
|
5 |
+
"eval_runtime": 1.7338,
|
6 |
+
"eval_samples_per_second": 64.599,
|
7 |
+
"eval_steps_per_second": 2.307
|
8 |
+
}
|
runs/May13_20-55-46_24cc275b3536/events.out.tfevents.1715634012.24cc275b3536.549.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f64210bd2ec4ba73f1316d417a04574c00cf7b99ab1e0ae6c419b50fbbcb71a
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 4.6849871171251814e+17,
|
4 |
+
"train_loss": 1.081290222349621,
|
5 |
+
"train_runtime": 252.638,
|
6 |
+
"train_samples_per_second": 74.419,
|
7 |
+
"train_steps_per_second": 0.582
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9196428571428571,
|
3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-Lego-v2-3ep/checkpoint-147",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 147,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.20408163265306123,
|
13 |
+
"grad_norm": 4.521535396575928,
|
14 |
+
"learning_rate": 3.3333333333333335e-05,
|
15 |
+
"loss": 2.7556,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.40816326530612246,
|
20 |
+
"grad_norm": 7.520199775695801,
|
21 |
+
"learning_rate": 4.810606060606061e-05,
|
22 |
+
"loss": 2.4445,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6122448979591837,
|
27 |
+
"grad_norm": 13.214489936828613,
|
28 |
+
"learning_rate": 4.431818181818182e-05,
|
29 |
+
"loss": 1.8022,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.8163265306122449,
|
34 |
+
"grad_norm": 14.265619277954102,
|
35 |
+
"learning_rate": 4.053030303030303e-05,
|
36 |
+
"loss": 1.3415,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_accuracy": 0.7857142857142857,
|
42 |
+
"eval_loss": 0.6598730683326721,
|
43 |
+
"eval_runtime": 0.7369,
|
44 |
+
"eval_samples_per_second": 151.997,
|
45 |
+
"eval_steps_per_second": 5.428,
|
46 |
+
"step": 49
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.0204081632653061,
|
50 |
+
"grad_norm": 15.687291145324707,
|
51 |
+
"learning_rate": 3.6742424242424246e-05,
|
52 |
+
"loss": 1.138,
|
53 |
+
"step": 50
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.2244897959183674,
|
57 |
+
"grad_norm": 11.222309112548828,
|
58 |
+
"learning_rate": 3.295454545454545e-05,
|
59 |
+
"loss": 0.8949,
|
60 |
+
"step": 60
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.4285714285714286,
|
64 |
+
"grad_norm": 13.59701919555664,
|
65 |
+
"learning_rate": 2.916666666666667e-05,
|
66 |
+
"loss": 0.8637,
|
67 |
+
"step": 70
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 1.6326530612244898,
|
71 |
+
"grad_norm": 8.102276802062988,
|
72 |
+
"learning_rate": 2.537878787878788e-05,
|
73 |
+
"loss": 0.7632,
|
74 |
+
"step": 80
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.836734693877551,
|
78 |
+
"grad_norm": 10.037010192871094,
|
79 |
+
"learning_rate": 2.1590909090909093e-05,
|
80 |
+
"loss": 0.7005,
|
81 |
+
"step": 90
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.0,
|
85 |
+
"eval_accuracy": 0.8928571428571429,
|
86 |
+
"eval_loss": 0.3036225736141205,
|
87 |
+
"eval_runtime": 0.7855,
|
88 |
+
"eval_samples_per_second": 142.578,
|
89 |
+
"eval_steps_per_second": 5.092,
|
90 |
+
"step": 98
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.0408163265306123,
|
94 |
+
"grad_norm": 9.7354154586792,
|
95 |
+
"learning_rate": 1.7803030303030303e-05,
|
96 |
+
"loss": 0.6343,
|
97 |
+
"step": 100
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 2.2448979591836733,
|
101 |
+
"grad_norm": 8.97431468963623,
|
102 |
+
"learning_rate": 1.4015151515151515e-05,
|
103 |
+
"loss": 0.5505,
|
104 |
+
"step": 110
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.4489795918367347,
|
108 |
+
"grad_norm": 8.927824974060059,
|
109 |
+
"learning_rate": 1.0227272727272729e-05,
|
110 |
+
"loss": 0.5527,
|
111 |
+
"step": 120
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.6530612244897958,
|
115 |
+
"grad_norm": 7.921907424926758,
|
116 |
+
"learning_rate": 6.43939393939394e-06,
|
117 |
+
"loss": 0.4982,
|
118 |
+
"step": 130
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 2.857142857142857,
|
122 |
+
"grad_norm": 9.745354652404785,
|
123 |
+
"learning_rate": 2.651515151515152e-06,
|
124 |
+
"loss": 0.5615,
|
125 |
+
"step": 140
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 3.0,
|
129 |
+
"eval_accuracy": 0.9196428571428571,
|
130 |
+
"eval_loss": 0.2128717005252838,
|
131 |
+
"eval_runtime": 0.7718,
|
132 |
+
"eval_samples_per_second": 145.113,
|
133 |
+
"eval_steps_per_second": 5.183,
|
134 |
+
"step": 147
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.0,
|
138 |
+
"step": 147,
|
139 |
+
"total_flos": 4.6849871171251814e+17,
|
140 |
+
"train_loss": 1.081290222349621,
|
141 |
+
"train_runtime": 252.638,
|
142 |
+
"train_samples_per_second": 74.419,
|
143 |
+
"train_steps_per_second": 0.582
|
144 |
+
}
|
145 |
+
],
|
146 |
+
"logging_steps": 10,
|
147 |
+
"max_steps": 147,
|
148 |
+
"num_input_tokens_seen": 0,
|
149 |
+
"num_train_epochs": 3,
|
150 |
+
"save_steps": 500,
|
151 |
+
"total_flos": 4.6849871171251814e+17,
|
152 |
+
"train_batch_size": 32,
|
153 |
+
"trial_name": null,
|
154 |
+
"trial_params": null
|
155 |
+
}
|