Hugging Face's logo

jayanthspratap
/
swinv2-base-patch4-window8-256

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Model card Files Metrics Community
swinv2-base-patch4-window8-256
File size: 4,377 Bytes 
015fa88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
 
{
  "best_metric": 0.813953488372093,
  "best_model_checkpoint": "swinv2-base-patch4-window8-256/checkpoint-12",
  "epoch": 9.6,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.96,
      "eval_accuracy": 0.7906976744186046,
      "eval_loss": 0.602724552154541,
      "eval_runtime": 0.4667,
      "eval_samples_per_second": 92.138,
      "eval_steps_per_second": 23.57,
      "step": 6
    },
    {
      "epoch": 1.6,
      "grad_norm": 5.375301837921143,
      "learning_rate": 4.62962962962963e-06,
      "loss": 0.6492,
      "step": 10
    },
    {
      "epoch": 1.92,
      "eval_accuracy": 0.813953488372093,
      "eval_loss": 0.5212067365646362,
      "eval_runtime": 0.478,
      "eval_samples_per_second": 89.95,
      "eval_steps_per_second": 23.011,
      "step": 12
    },
    {
      "epoch": 2.88,
      "eval_accuracy": 0.813953488372093,
      "eval_loss": 0.4939202666282654,
      "eval_runtime": 0.4952,
      "eval_samples_per_second": 86.835,
      "eval_steps_per_second": 22.214,
      "step": 18
    },
    {
      "epoch": 3.2,
      "grad_norm": 7.962141036987305,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.5773,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.813953488372093,
      "eval_loss": 0.48294201493263245,
      "eval_runtime": 0.4872,
      "eval_samples_per_second": 88.252,
      "eval_steps_per_second": 22.576,
      "step": 25
    },
    {
      "epoch": 4.8,
      "grad_norm": 7.068347930908203,
      "learning_rate": 2.7777777777777783e-06,
      "loss": 0.6313,
      "step": 30
    },
    {
      "epoch": 4.96,
      "eval_accuracy": 0.813953488372093,
      "eval_loss": 0.48332729935646057,
      "eval_runtime": 0.5067,
      "eval_samples_per_second": 84.87,
      "eval_steps_per_second": 21.711,
      "step": 31
    },
    {
      "epoch": 5.92,
      "eval_accuracy": 0.813953488372093,
      "eval_loss": 0.4872807264328003,
      "eval_runtime": 0.5598,
      "eval_samples_per_second": 76.807,
      "eval_steps_per_second": 19.648,
      "step": 37
    },
    {
      "epoch": 6.4,
      "grad_norm": 7.162075042724609,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.5665,
      "step": 40
    },
    {
      "epoch": 6.88,
      "eval_accuracy": 0.813953488372093,
      "eval_loss": 0.48763200640678406,
      "eval_runtime": 0.4695,
      "eval_samples_per_second": 91.588,
      "eval_steps_per_second": 23.43,
      "step": 43
    },
    {
      "epoch": 8.0,
      "grad_norm": 6.575540542602539,
      "learning_rate": 9.259259259259259e-07,
      "loss": 0.5615,
      "step": 50
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.813953488372093,
      "eval_loss": 0.4861143231391907,
      "eval_runtime": 0.4886,
      "eval_samples_per_second": 88.012,
      "eval_steps_per_second": 22.515,
      "step": 50
    },
    {
      "epoch": 8.96,
      "eval_accuracy": 0.813953488372093,
      "eval_loss": 0.487347811460495,
      "eval_runtime": 0.4891,
      "eval_samples_per_second": 87.918,
      "eval_steps_per_second": 22.491,
      "step": 56
    },
    {
      "epoch": 9.6,
      "grad_norm": 5.972108840942383,
      "learning_rate": 0.0,
      "loss": 0.5712,
      "step": 60
    },
    {
      "epoch": 9.6,
      "eval_accuracy": 0.813953488372093,
      "eval_loss": 0.48711302876472473,
      "eval_runtime": 0.5016,
      "eval_samples_per_second": 85.725,
      "eval_steps_per_second": 21.93,
      "step": 60
    },
    {
      "epoch": 9.6,
      "step": 60,
      "total_flos": 9.748371434294477e+16,
      "train_loss": 0.5928216457366944,
      "train_runtime": 55.1953,
      "train_samples_per_second": 17.936,
      "train_steps_per_second": 1.087
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.748371434294477e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}