Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0601

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0601
File size: 4,070 Bytes 
a785a97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9477333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0601/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": 0.166721373796463,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.6142,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9221333333333334,
      "eval_loss": 0.2759295701980591,
      "eval_runtime": 11.2941,
      "eval_samples_per_second": 332.032,
      "eval_steps_per_second": 5.224,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4502091705799103,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1339,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.2548469305038452,
      "eval_runtime": 11.034,
      "eval_samples_per_second": 339.859,
      "eval_steps_per_second": 5.347,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.03102213889360428,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0635,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9301333333333334,
      "eval_loss": 0.25677603483200073,
      "eval_runtime": 11.1747,
      "eval_samples_per_second": 335.578,
      "eval_steps_per_second": 5.28,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7135173678398132,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0335,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9373333333333334,
      "eval_loss": 0.24459801614284515,
      "eval_runtime": 12.6814,
      "eval_samples_per_second": 295.709,
      "eval_steps_per_second": 4.652,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.009617614559829235,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0111,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.94,
      "eval_loss": 0.2416512370109558,
      "eval_runtime": 11.5536,
      "eval_samples_per_second": 324.574,
      "eval_steps_per_second": 5.107,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.15883134305477142,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0027,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9469333333333333,
      "eval_loss": 0.237899512052536,
      "eval_runtime": 11.0164,
      "eval_samples_per_second": 340.402,
      "eval_steps_per_second": 5.356,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.1731488851999511e-05,
      "loss": 0.001,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9453333333333334,
      "eval_loss": 0.23779810965061188,
      "eval_runtime": 11.1425,
      "eval_samples_per_second": 336.548,
      "eval_steps_per_second": 5.295,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.006807507947087288,
      "learning_rate": 3.033320830114261e-06,
      "loss": 0.0007,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9477333333333333,
      "eval_loss": 0.2355157732963562,
      "eval_runtime": 11.3088,
      "eval_samples_per_second": 331.6,
      "eval_steps_per_second": 5.217,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}