Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0573

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0573
File size: 4,499 Bytes 
00e8834
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9477333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0573/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": 1.1896,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9258666666666666,
      "eval_loss": 0.3100385367870331,
      "eval_runtime": 13.2001,
      "eval_samples_per_second": 284.089,
      "eval_steps_per_second": 4.47,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 37.84109878540039,
      "learning_rate": 2.6500767323004636e-05,
      "loss": 0.1725,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9357333333333333,
      "eval_loss": 0.23746566474437714,
      "eval_runtime": 13.2577,
      "eval_samples_per_second": 282.855,
      "eval_steps_per_second": 4.45,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 13.16148567199707,
      "learning_rate": 2.25136129892785e-05,
      "loss": 0.0722,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9346666666666666,
      "eval_loss": 0.24406936764717102,
      "eval_runtime": 12.664,
      "eval_samples_per_second": 296.116,
      "eval_steps_per_second": 4.659,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.09024656563997269,
      "learning_rate": 1.7620206039927677e-05,
      "loss": 0.0319,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9397333333333333,
      "eval_loss": 0.2394251823425293,
      "eval_runtime": 13.1926,
      "eval_samples_per_second": 284.25,
      "eval_steps_per_second": 4.472,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.08432703465223312,
      "learning_rate": 1.241076357203891e-05,
      "loss": 0.0141,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9450666666666667,
      "eval_loss": 0.21969226002693176,
      "eval_runtime": 13.1605,
      "eval_samples_per_second": 284.943,
      "eval_steps_per_second": 4.483,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.15378177165985107,
      "learning_rate": 7.513621230422123e-06,
      "loss": 0.0078,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9450666666666667,
      "eval_loss": 0.2236633151769638,
      "eval_runtime": 13.0655,
      "eval_samples_per_second": 287.015,
      "eval_steps_per_second": 4.516,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.030893618240952492,
      "learning_rate": 3.519446655599853e-06,
      "loss": 0.0059,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9442666666666667,
      "eval_loss": 0.21965183317661285,
      "eval_runtime": 13.0304,
      "eval_samples_per_second": 287.789,
      "eval_steps_per_second": 4.528,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.030893318355083466,
      "learning_rate": 9.099962490342784e-07,
      "loss": 0.0042,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9472,
      "eval_loss": 0.23139528930187225,
      "eval_runtime": 13.6701,
      "eval_samples_per_second": 274.322,
      "eval_steps_per_second": 4.316,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.03994259983301163,
      "learning_rate": 8.24114362751871e-12,
      "loss": 0.0036,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9477333333333333,
      "eval_loss": 0.21924802660942078,
      "eval_runtime": 13.3281,
      "eval_samples_per_second": 281.361,
      "eval_steps_per_second": 4.427,
      "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
}