Hugging Face's logo

nateraw
/
pasta-shapes

Image Classification
Transformers
PyTorch
TensorBoard
vit
huggingpics
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
pasta-shapes
File size: 2,426 Bytes 
a8a1a12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "global_step": 96,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 1.0914,
      "step": 10
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 1.0328,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_acc": 0.746268630027771,
      "eval_loss": 0.9441611170768738,
      "eval_runtime": 0.9419,
      "eval_samples_per_second": 71.134,
      "eval_steps_per_second": 5.309,
      "step": 24
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 0.9558,
      "step": 30
    },
    {
      "epoch": 1.67,
      "learning_rate": 2e-05,
      "loss": 0.8742,
      "step": 40
    },
    {
      "epoch": 2.0,
      "eval_acc": 0.9402984976768494,
      "eval_loss": 0.7099391222000122,
      "eval_runtime": 0.9379,
      "eval_samples_per_second": 71.439,
      "eval_steps_per_second": 5.331,
      "step": 48
    },
    {
      "epoch": 2.08,
      "learning_rate": 2e-05,
      "loss": 0.7474,
      "step": 50
    },
    {
      "epoch": 2.5,
      "learning_rate": 2e-05,
      "loss": 0.6858,
      "step": 60
    },
    {
      "epoch": 2.92,
      "learning_rate": 2e-05,
      "loss": 0.6451,
      "step": 70
    },
    {
      "epoch": 3.0,
      "eval_acc": 0.9402984976768494,
      "eval_loss": 0.5049594044685364,
      "eval_runtime": 0.9359,
      "eval_samples_per_second": 71.588,
      "eval_steps_per_second": 5.342,
      "step": 72
    },
    {
      "epoch": 3.33,
      "learning_rate": 2e-05,
      "loss": 0.5587,
      "step": 80
    },
    {
      "epoch": 3.75,
      "learning_rate": 2e-05,
      "loss": 0.508,
      "step": 90
    },
    {
      "epoch": 4.0,
      "eval_acc": 0.9402984976768494,
      "eval_loss": 0.37610408663749695,
      "eval_runtime": 0.9323,
      "eval_samples_per_second": 71.866,
      "eval_steps_per_second": 5.363,
      "step": 96
    },
    {
      "epoch": 4.0,
      "step": 96,
      "total_flos": 0.0,
      "train_loss": 0.7672463009754816,
      "train_runtime": 44.747,
      "train_samples_per_second": 34.058,
      "train_steps_per_second": 2.145
    }
  ],
  "max_steps": 96,
  "num_train_epochs": 4,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}