Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0537

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0537
File size: 3,250 Bytes 
a6ccf49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.956,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0537/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 6.655434848731736e-05,
      "loss": 0.6601,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9389333333333333,
      "eval_loss": 0.2185075879096985,
      "eval_runtime": 10.3186,
      "eval_samples_per_second": 363.42,
      "eval_steps_per_second": 5.718,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09898105263710022,
      "learning_rate": 5.685900305529986e-05,
      "loss": 0.0988,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9426666666666667,
      "eval_loss": 0.20965999364852905,
      "eval_runtime": 10.4537,
      "eval_samples_per_second": 358.723,
      "eval_steps_per_second": 5.644,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.10027804970741272,
      "learning_rate": 4.28342139851007e-05,
      "loss": 0.0327,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9506666666666667,
      "eval_loss": 0.19185635447502136,
      "eval_runtime": 11.0703,
      "eval_samples_per_second": 338.744,
      "eval_steps_per_second": 5.33,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.01967179961502552,
      "learning_rate": 2.7257762754823102e-05,
      "loss": 0.0101,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9544,
      "eval_loss": 0.18630582094192505,
      "eval_runtime": 10.6005,
      "eval_samples_per_second": 353.758,
      "eval_steps_per_second": 5.566,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.05668722093105316,
      "learning_rate": 1.3214756563261342e-05,
      "loss": 0.0044,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9552,
      "eval_loss": 0.18552646040916443,
      "eval_runtime": 10.5083,
      "eval_samples_per_second": 356.861,
      "eval_steps_per_second": 5.615,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.02456258423626423,
      "learning_rate": 3.4865850128228307e-06,
      "loss": 0.0022,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.956,
      "eval_loss": 0.19408918917179108,
      "eval_runtime": 11.8329,
      "eval_samples_per_second": 316.912,
      "eval_steps_per_second": 4.986,
      "step": 1998
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}