Hugging Face's logo

t1msan
/
swin-base-patch4-window7-224-in22k-Kontur-competition-1.4K

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
swin-base-patch4-window7-224-in22k-Kontur-competition-1.4K
File size: 3,219 Bytes 
13f7d81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
 
{
  "best_metric": 0.05487216264009476,
  "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-Kontur-competition-1.4K/checkpoint-23",
  "epoch": 8.421052631578947,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.84,
      "eval_loss": 0.5903199911117554,
      "eval_runtime": 3.2368,
      "eval_samples_per_second": 41.09,
      "eval_steps_per_second": 0.927,
      "step": 4
    },
    {
      "epoch": 1.89,
      "eval_loss": 0.32031941413879395,
      "eval_runtime": 2.5544,
      "eval_samples_per_second": 52.067,
      "eval_steps_per_second": 1.174,
      "step": 9
    },
    {
      "epoch": 2.11,
      "grad_norm": 12.904247283935547,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.5582,
      "step": 10
    },
    {
      "epoch": 2.95,
      "eval_loss": 0.2519628703594208,
      "eval_runtime": 2.7088,
      "eval_samples_per_second": 49.1,
      "eval_steps_per_second": 1.108,
      "step": 14
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.09062427282333374,
      "eval_runtime": 2.6817,
      "eval_samples_per_second": 49.596,
      "eval_steps_per_second": 1.119,
      "step": 19
    },
    {
      "epoch": 4.21,
      "grad_norm": 2.254042148590088,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.1094,
      "step": 20
    },
    {
      "epoch": 4.84,
      "eval_loss": 0.05487216264009476,
      "eval_runtime": 2.5622,
      "eval_samples_per_second": 51.908,
      "eval_steps_per_second": 1.171,
      "step": 23
    },
    {
      "epoch": 5.89,
      "eval_loss": 0.14387370645999908,
      "eval_runtime": 2.8209,
      "eval_samples_per_second": 47.149,
      "eval_steps_per_second": 1.064,
      "step": 28
    },
    {
      "epoch": 6.32,
      "grad_norm": 2.9556210041046143,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.0533,
      "step": 30
    },
    {
      "epoch": 6.95,
      "eval_loss": 0.06752961128950119,
      "eval_runtime": 2.5525,
      "eval_samples_per_second": 52.106,
      "eval_steps_per_second": 1.175,
      "step": 33
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.12144926190376282,
      "eval_runtime": 2.5532,
      "eval_samples_per_second": 52.091,
      "eval_steps_per_second": 1.175,
      "step": 38
    },
    {
      "epoch": 8.42,
      "grad_norm": 0.5887470245361328,
      "learning_rate": 0.0,
      "loss": 0.0144,
      "step": 40
    },
    {
      "epoch": 8.42,
      "eval_loss": 0.1230710819363594,
      "eval_runtime": 2.6049,
      "eval_samples_per_second": 51.058,
      "eval_steps_per_second": 1.152,
      "step": 40
    },
    {
      "epoch": 8.42,
      "step": 40,
      "total_flos": 7.88469671840514e+17,
      "train_loss": 0.18382581882178783,
      "train_runtime": 367.9939,
      "train_samples_per_second": 32.446,
      "train_steps_per_second": 0.109
    }
  ],
  "logging_steps": 10,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 7.88469671840514e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}