Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0676

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0676
File size: 2,845 Bytes 
a950004
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9482666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0676/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.4117160439491272,
      "learning_rate": 6.531088913245535e-05,
      "loss": 0.6856,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9256,
      "eval_loss": 0.2715129256248474,
      "eval_runtime": 11.1567,
      "eval_samples_per_second": 336.12,
      "eval_steps_per_second": 5.288,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7975550889968872,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.13,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9264,
      "eval_loss": 0.26744455099105835,
      "eval_runtime": 10.8627,
      "eval_samples_per_second": 345.217,
      "eval_steps_per_second": 5.431,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.16067996621131897,
      "learning_rate": 3.5e-05,
      "loss": 0.0538,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.94,
      "eval_loss": 0.22905713319778442,
      "eval_runtime": 11.4179,
      "eval_samples_per_second": 328.432,
      "eval_steps_per_second": 5.167,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.140328049659729,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0211,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9402666666666667,
      "eval_loss": 0.2234363555908203,
      "eval_runtime": 11.2403,
      "eval_samples_per_second": 333.62,
      "eval_steps_per_second": 5.249,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.029369253665208817,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.0071,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9482666666666667,
      "eval_loss": 0.2065318524837494,
      "eval_runtime": 10.9646,
      "eval_samples_per_second": 342.009,
      "eval_steps_per_second": 5.381,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}