File size: 1,849 Bytes
b6e0c22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
{
  "best_metric": 0.10923629999160767,
  "best_model_checkpoint": "./vit-base-beans/checkpoint-80",
  "epoch": 3.6363636363636362,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.45,
      "learning_rate": 0.00017727272727272728,
      "loss": 1.1791,
      "step": 10
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.7576,
      "step": 20
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001318181818181818,
      "loss": 0.4147,
      "step": 30
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.2625,
      "step": 40
    },
    {
      "epoch": 1.82,
      "eval_accuracy": 0.9705882352941176,
      "eval_loss": 0.20606106519699097,
      "eval_runtime": 73.8021,
      "eval_samples_per_second": 1.382,
      "eval_steps_per_second": 0.176,
      "step": 40
    },
    {
      "epoch": 2.27,
      "learning_rate": 8.636363636363637e-05,
      "loss": 0.1494,
      "step": 50
    },
    {
      "epoch": 2.73,
      "learning_rate": 6.363636363636364e-05,
      "loss": 0.0966,
      "step": 60
    },
    {
      "epoch": 3.18,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 0.0698,
      "step": 70
    },
    {
      "epoch": 3.64,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.0634,
      "step": 80
    },
    {
      "epoch": 3.64,
      "eval_accuracy": 0.9901960784313726,
      "eval_loss": 0.10923629999160767,
      "eval_runtime": 73.0157,
      "eval_samples_per_second": 1.397,
      "eval_steps_per_second": 0.178,
      "step": 80
    }
  ],
  "max_steps": 88,
  "num_train_epochs": 4,
  "total_flos": 9.733168363084186e+16,
  "trial_name": null,
  "trial_params": null
}