Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0585

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0585
File size: 4,453 Bytes 
59637b6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9496,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0585/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": 0.29169586300849915,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.8325,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9349333333333333,
      "eval_loss": 0.24127474427223206,
      "eval_runtime": 11.22,
      "eval_samples_per_second": 334.226,
      "eval_steps_per_second": 5.258,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9110438823699951,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.1266,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9405333333333333,
      "eval_loss": 0.20272308588027954,
      "eval_runtime": 11.2175,
      "eval_samples_per_second": 334.298,
      "eval_steps_per_second": 5.26,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04452028498053551,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.0474,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9376,
      "eval_loss": 0.22525645792484283,
      "eval_runtime": 11.5471,
      "eval_samples_per_second": 324.756,
      "eval_steps_per_second": 5.109,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.01526041328907013,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 0.0207,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9426666666666667,
      "eval_loss": 0.20911720395088196,
      "eval_runtime": 11.6824,
      "eval_samples_per_second": 320.996,
      "eval_steps_per_second": 5.05,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.04210159182548523,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.0087,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9488,
      "eval_loss": 0.20233090221881866,
      "eval_runtime": 11.5621,
      "eval_samples_per_second": 324.336,
      "eval_steps_per_second": 5.103,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.02021963708102703,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0047,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9458666666666666,
      "eval_loss": 0.20642739534378052,
      "eval_runtime": 12.0137,
      "eval_samples_per_second": 312.144,
      "eval_steps_per_second": 4.911,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 5.865744425999756e-06,
      "loss": 0.003,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9472,
      "eval_loss": 0.20538415014743805,
      "eval_runtime": 11.2538,
      "eval_samples_per_second": 333.22,
      "eval_steps_per_second": 5.243,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.027163198217749596,
      "learning_rate": 1.5166604150571306e-06,
      "loss": 0.0022,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9493333333333334,
      "eval_loss": 0.2027917355298996,
      "eval_runtime": 11.5604,
      "eval_samples_per_second": 324.384,
      "eval_steps_per_second": 5.104,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.012500536628067493,
      "learning_rate": 1.3735239379197851e-11,
      "loss": 0.0021,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9496,
      "eval_loss": 0.20453307032585144,
      "eval_runtime": 11.059,
      "eval_samples_per_second": 339.091,
      "eval_steps_per_second": 5.335,
      "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
}