Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0596

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0596
File size: 3,670 Bytes 
0f68d2b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9482666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0596/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": 1.4458703994750977,
      "learning_rate": 7.875e-05,
      "loss": 0.6108,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.24742089211940765,
      "eval_runtime": 12.4498,
      "eval_samples_per_second": 301.21,
      "eval_steps_per_second": 4.739,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.04738565906882286,
      "learning_rate": 6.75e-05,
      "loss": 0.1156,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9328,
      "eval_loss": 0.2287224680185318,
      "eval_runtime": 13.0496,
      "eval_samples_per_second": 287.364,
      "eval_steps_per_second": 4.521,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 5.628378378378378e-05,
      "loss": 0.0534,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9341333333333334,
      "eval_loss": 0.26288262009620667,
      "eval_runtime": 12.4635,
      "eval_samples_per_second": 300.88,
      "eval_steps_per_second": 4.734,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.014663777314126492,
      "learning_rate": 4.503378378378379e-05,
      "loss": 0.0248,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.24424658715724945,
      "eval_runtime": 12.3937,
      "eval_samples_per_second": 302.572,
      "eval_steps_per_second": 4.76,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.013429674319922924,
      "learning_rate": 3.3783783783783784e-05,
      "loss": 0.0094,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9426666666666667,
      "eval_loss": 0.2423509955406189,
      "eval_runtime": 12.4459,
      "eval_samples_per_second": 301.305,
      "eval_steps_per_second": 4.741,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.005661157891154289,
      "learning_rate": 2.2533783783783782e-05,
      "loss": 0.0026,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9453333333333334,
      "eval_loss": 0.224564790725708,
      "eval_runtime": 12.5509,
      "eval_samples_per_second": 298.783,
      "eval_steps_per_second": 4.701,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.036214157938957214,
      "learning_rate": 1.1283783783783785e-05,
      "loss": 0.0011,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9482666666666667,
      "eval_loss": 0.22295115888118744,
      "eval_runtime": 12.2084,
      "eval_samples_per_second": 307.164,
      "eval_steps_per_second": 4.833,
      "step": 2331
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}