Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0305

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0305
File size: 3,638 Bytes 
b5472d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9498666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0305/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": 2.9523117542266846,
      "learning_rate": 8.728616793536588e-05,
      "loss": 0.6312,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9232,
      "eval_loss": 0.2750612199306488,
      "eval_runtime": 7.4788,
      "eval_samples_per_second": 501.416,
      "eval_steps_per_second": 7.889,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05039806663990021,
      "learning_rate": 7.947199994035401e-05,
      "loss": 0.1401,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.23802122473716736,
      "eval_runtime": 6.7868,
      "eval_samples_per_second": 552.546,
      "eval_steps_per_second": 8.693,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.118083477020264,
      "learning_rate": 6.75e-05,
      "loss": 0.0652,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.2642131745815277,
      "eval_runtime": 6.7839,
      "eval_samples_per_second": 552.779,
      "eval_steps_per_second": 8.697,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2532743513584137,
      "learning_rate": 5.2814167995011876e-05,
      "loss": 0.0269,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9370666666666667,
      "eval_loss": 0.25039756298065186,
      "eval_runtime": 6.7973,
      "eval_samples_per_second": 551.691,
      "eval_steps_per_second": 8.68,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.01434257347136736,
      "learning_rate": 3.7185832004988136e-05,
      "loss": 0.0107,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.25416091084480286,
      "eval_runtime": 6.7115,
      "eval_samples_per_second": 558.744,
      "eval_steps_per_second": 8.791,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.02742774598300457,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.0037,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9445333333333333,
      "eval_loss": 0.2494526356458664,
      "eval_runtime": 7.5354,
      "eval_samples_per_second": 497.648,
      "eval_steps_per_second": 7.83,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.055833996679956e-05,
      "loss": 0.0016,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9498666666666666,
      "eval_loss": 0.23527829349040985,
      "eval_runtime": 6.6732,
      "eval_samples_per_second": 561.953,
      "eval_steps_per_second": 8.841,
      "step": 2331
    }
  ],
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}