Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0471

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0471
File size: 3,655 Bytes 
1b076a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9509333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0471/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 3.1082427501678467,
      "learning_rate": 2.5714285714285714e-05,
      "loss": 1.1315,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9405333333333333,
      "eval_loss": 0.2638862431049347,
      "eval_runtime": 12.4608,
      "eval_samples_per_second": 300.944,
      "eval_steps_per_second": 4.735,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6404333710670471,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.1632,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9456,
      "eval_loss": 0.1920280158519745,
      "eval_runtime": 12.4373,
      "eval_samples_per_second": 301.512,
      "eval_steps_per_second": 4.744,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.14122454822063446,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 0.0624,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9504,
      "eval_loss": 0.18297316133975983,
      "eval_runtime": 12.7249,
      "eval_samples_per_second": 294.697,
      "eval_steps_per_second": 4.637,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.05559397116303444,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 0.025,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9488,
      "eval_loss": 0.18986093997955322,
      "eval_runtime": 12.0875,
      "eval_samples_per_second": 310.239,
      "eval_steps_per_second": 4.881,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.07765389233827591,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.0113,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9498666666666666,
      "eval_loss": 0.19432637095451355,
      "eval_runtime": 12.8086,
      "eval_samples_per_second": 292.773,
      "eval_steps_per_second": 4.606,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.29620876908302307,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 0.0072,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9496,
      "eval_loss": 0.19282571971416473,
      "eval_runtime": 12.7238,
      "eval_samples_per_second": 294.724,
      "eval_steps_per_second": 4.637,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.2870012870012871e-08,
      "loss": 0.0059,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9509333333333333,
      "eval_loss": 0.19424590468406677,
      "eval_runtime": 12.4639,
      "eval_samples_per_second": 300.868,
      "eval_steps_per_second": 4.734,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}