Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0484

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0484
File size: 4,037 Bytes 
5b0f12b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9514666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0484/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.1437719166278839,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5492,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9216,
      "eval_loss": 0.2685840427875519,
      "eval_runtime": 10.7948,
      "eval_samples_per_second": 347.389,
      "eval_steps_per_second": 5.466,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.2020721435546875,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1228,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.25076398253440857,
      "eval_runtime": 10.7358,
      "eval_samples_per_second": 349.297,
      "eval_steps_per_second": 5.496,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.4066358804702759,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0551,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9357333333333333,
      "eval_loss": 0.24587324261665344,
      "eval_runtime": 10.6847,
      "eval_samples_per_second": 350.968,
      "eval_steps_per_second": 5.522,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.009421214461326599,
      "learning_rate": 5e-05,
      "loss": 0.0229,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9448,
      "eval_loss": 0.22150962054729462,
      "eval_runtime": 11.7919,
      "eval_samples_per_second": 318.016,
      "eval_steps_per_second": 5.003,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.014440308324992657,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0073,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9498666666666666,
      "eval_loss": 0.21642786264419556,
      "eval_runtime": 11.2266,
      "eval_samples_per_second": 334.027,
      "eval_steps_per_second": 5.255,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.01787632331252098,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.002,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9501333333333334,
      "eval_loss": 0.21838298439979553,
      "eval_runtime": 10.7782,
      "eval_samples_per_second": 347.926,
      "eval_steps_per_second": 5.474,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 3.82861996937452e-06,
      "loss": 0.001,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9504,
      "eval_loss": 0.21514670550823212,
      "eval_runtime": 10.8633,
      "eval_samples_per_second": 345.2,
      "eval_steps_per_second": 5.431,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.05648856982588768,
      "learning_rate": 3.476732383100867e-11,
      "loss": 0.0009,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9514666666666667,
      "eval_loss": 0.21722640097141266,
      "eval_runtime": 10.7709,
      "eval_samples_per_second": 348.161,
      "eval_steps_per_second": 5.478,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}