Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0143

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0143
File size: 4,481 Bytes 
112288b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9061333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0143/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": 0.0004446112779446113,
      "loss": 0.8521,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8082666666666667,
      "eval_loss": 0.6323592662811279,
      "eval_runtime": 7.1032,
      "eval_samples_per_second": 527.928,
      "eval_steps_per_second": 8.306,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.871102333068848,
      "learning_rate": 0.0003890557223890557,
      "loss": 0.4333,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8253333333333334,
      "eval_loss": 0.596873939037323,
      "eval_runtime": 7.1542,
      "eval_samples_per_second": 524.167,
      "eval_steps_per_second": 8.247,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.036282412707805634,
      "learning_rate": 0.00033350016683350017,
      "loss": 0.2975,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8578666666666667,
      "eval_loss": 0.5036653280258179,
      "eval_runtime": 6.3446,
      "eval_samples_per_second": 591.049,
      "eval_steps_per_second": 9.299,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.137360095977783,
      "learning_rate": 0.0002779446112779446,
      "loss": 0.1985,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.848,
      "eval_loss": 0.5732738375663757,
      "eval_runtime": 6.4747,
      "eval_samples_per_second": 579.173,
      "eval_steps_per_second": 9.112,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.005336934234946966,
      "learning_rate": 0.00022238905572238908,
      "loss": 0.1219,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8781333333333333,
      "eval_loss": 0.47219738364219666,
      "eval_runtime": 6.3996,
      "eval_samples_per_second": 585.978,
      "eval_steps_per_second": 9.219,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.3057951331138611,
      "learning_rate": 0.00016683350016683348,
      "loss": 0.0809,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.4686046242713928,
      "eval_runtime": 6.4561,
      "eval_samples_per_second": 580.846,
      "eval_steps_per_second": 9.139,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.08319225907325745,
      "learning_rate": 0.00011127794461127795,
      "loss": 0.0372,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8986666666666666,
      "eval_loss": 0.41961848735809326,
      "eval_runtime": 6.6039,
      "eval_samples_per_second": 567.843,
      "eval_steps_per_second": 8.934,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.004235462285578251,
      "learning_rate": 5.572238905572239e-05,
      "loss": 0.014,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9034666666666666,
      "eval_loss": 0.39623314142227173,
      "eval_runtime": 6.8852,
      "eval_samples_per_second": 544.646,
      "eval_steps_per_second": 8.569,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.004995493683964014,
      "learning_rate": 1.668335001668335e-07,
      "loss": 0.0045,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9061333333333333,
      "eval_loss": 0.3941395580768585,
      "eval_runtime": 6.7481,
      "eval_samples_per_second": 555.711,
      "eval_steps_per_second": 8.743,
      "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
}