Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0285

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0285
File size: 3,286 Bytes 
2fafa34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9610666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0285/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": 1.382799506187439,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.1674,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9392,
      "eval_loss": 0.27335673570632935,
      "eval_runtime": 11.3935,
      "eval_samples_per_second": 329.134,
      "eval_steps_per_second": 5.178,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6274847984313965,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.1503,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9549333333333333,
      "eval_loss": 0.1808481067419052,
      "eval_runtime": 11.4677,
      "eval_samples_per_second": 327.005,
      "eval_steps_per_second": 5.145,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.4228242039680481,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.0639,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9554666666666667,
      "eval_loss": 0.17115090787410736,
      "eval_runtime": 11.5289,
      "eval_samples_per_second": 325.269,
      "eval_steps_per_second": 5.118,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.28031498193740845,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0315,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9528,
      "eval_loss": 0.1728556603193283,
      "eval_runtime": 11.472,
      "eval_samples_per_second": 326.883,
      "eval_steps_per_second": 5.143,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.06605438888072968,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0161,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9589333333333333,
      "eval_loss": 0.15747900307178497,
      "eval_runtime": 11.6696,
      "eval_samples_per_second": 321.348,
      "eval_steps_per_second": 5.056,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.19619157910346985,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.0086,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9610666666666666,
      "eval_loss": 0.16157716512680054,
      "eval_runtime": 11.5657,
      "eval_samples_per_second": 324.234,
      "eval_steps_per_second": 5.101,
      "step": 1998
    }
  ],
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}