Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0368

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0368
File size: 4,424 Bytes 
93f8dee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.9504,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0368/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "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": 2.9100759384327822e-05,
      "loss": 1.1692,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9248,
      "eval_loss": 0.3104296326637268,
      "eval_runtime": 7.3589,
      "eval_samples_per_second": 509.59,
      "eval_steps_per_second": 8.018,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.1074323654174805,
      "learning_rate": 2.6500767323004636e-05,
      "loss": 0.1781,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9405333333333333,
      "eval_loss": 0.2088799774646759,
      "eval_runtime": 7.7595,
      "eval_samples_per_second": 483.279,
      "eval_steps_per_second": 7.604,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.5785893201828003,
      "learning_rate": 2.25136129892785e-05,
      "loss": 0.0809,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9469333333333333,
      "eval_loss": 0.19520941376686096,
      "eval_runtime": 7.0244,
      "eval_samples_per_second": 533.851,
      "eval_steps_per_second": 8.399,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 20.29998016357422,
      "learning_rate": 1.7620206039927677e-05,
      "loss": 0.0367,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.20007646083831787,
      "eval_runtime": 6.7376,
      "eval_samples_per_second": 556.58,
      "eval_steps_per_second": 8.757,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.042528510093688965,
      "learning_rate": 1.241076357203891e-05,
      "loss": 0.0181,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9458666666666666,
      "eval_loss": 0.19628219306468964,
      "eval_runtime": 6.9774,
      "eval_samples_per_second": 537.45,
      "eval_steps_per_second": 8.456,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.18889659643173218,
      "learning_rate": 7.513621230422123e-06,
      "loss": 0.0089,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.948,
      "eval_loss": 0.20025309920310974,
      "eval_runtime": 6.7753,
      "eval_samples_per_second": 553.478,
      "eval_steps_per_second": 8.708,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03880244493484497,
      "learning_rate": 3.519446655599853e-06,
      "loss": 0.0057,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9458666666666666,
      "eval_loss": 0.20074984431266785,
      "eval_runtime": 6.6747,
      "eval_samples_per_second": 561.825,
      "eval_steps_per_second": 8.839,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.74473237991333,
      "learning_rate": 9.099962490342784e-07,
      "loss": 0.0046,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.948,
      "eval_loss": 0.20650845766067505,
      "eval_runtime": 6.6787,
      "eval_samples_per_second": 561.489,
      "eval_steps_per_second": 8.834,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.3305164873600006,
      "learning_rate": 8.24114362751871e-12,
      "loss": 0.0043,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9504,
      "eval_loss": 0.20306861400604248,
      "eval_runtime": 6.7449,
      "eval_samples_per_second": 555.975,
      "eval_steps_per_second": 8.747,
      "step": 2997
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}