Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0206

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0206
File size: 3,583 Bytes 
2681ed3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9485333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0206/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": 0.23543903231620789,
      "learning_rate": 7e-05,
      "loss": 0.6813,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9426666666666667,
      "eval_loss": 0.20305897295475006,
      "eval_runtime": 8.4548,
      "eval_samples_per_second": 443.537,
      "eval_steps_per_second": 6.978,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.287026405334473,
      "learning_rate": 7e-05,
      "loss": 0.1306,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9461333333333334,
      "eval_loss": 0.1948036402463913,
      "eval_runtime": 7.4883,
      "eval_samples_per_second": 500.782,
      "eval_steps_per_second": 7.879,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.10781341791152954,
      "learning_rate": 7e-05,
      "loss": 0.0675,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9434666666666667,
      "eval_loss": 0.21110756695270538,
      "eval_runtime": 9.1691,
      "eval_samples_per_second": 408.984,
      "eval_steps_per_second": 6.435,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.031217969954013824,
      "learning_rate": 7e-05,
      "loss": 0.0449,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9445333333333333,
      "eval_loss": 0.2352362722158432,
      "eval_runtime": 7.8162,
      "eval_samples_per_second": 479.772,
      "eval_steps_per_second": 7.548,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.06854312866926193,
      "learning_rate": 7e-05,
      "loss": 0.0295,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9410666666666667,
      "eval_loss": 0.2513515055179596,
      "eval_runtime": 7.0632,
      "eval_samples_per_second": 530.919,
      "eval_steps_per_second": 8.353,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.011678989976644516,
      "learning_rate": 7e-05,
      "loss": 0.0252,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.23778235912322998,
      "eval_runtime": 8.8325,
      "eval_samples_per_second": 424.569,
      "eval_steps_per_second": 6.68,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.08189805597066879,
      "learning_rate": 7e-05,
      "loss": 0.023,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9485333333333333,
      "eval_loss": 0.23201017081737518,
      "eval_runtime": 7.9421,
      "eval_samples_per_second": 472.167,
      "eval_steps_per_second": 7.429,
      "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
}