Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0267

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0267
File size: 3,915 Bytes 
0d7199d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8208,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0267/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 0.0005,
      "loss": 0.8213,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8002666666666667,
      "eval_loss": 0.6668938994407654,
      "eval_runtime": 5.4579,
      "eval_samples_per_second": 687.072,
      "eval_steps_per_second": 10.81,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.08039126545190811,
      "learning_rate": 0.0005,
      "loss": 0.4907,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8093333333333333,
      "eval_loss": 0.6200566291809082,
      "eval_runtime": 5.674,
      "eval_samples_per_second": 660.915,
      "eval_steps_per_second": 10.398,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.441648483276367,
      "learning_rate": 0.0005,
      "loss": 0.3743,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7944,
      "eval_loss": 0.7007632851600647,
      "eval_runtime": 6.1754,
      "eval_samples_per_second": 607.244,
      "eval_steps_per_second": 9.554,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 15.427275657653809,
      "learning_rate": 0.0005,
      "loss": 0.3139,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8149333333333333,
      "eval_loss": 0.6663420796394348,
      "eval_runtime": 8.7039,
      "eval_samples_per_second": 430.839,
      "eval_steps_per_second": 6.779,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.08661292493343353,
      "learning_rate": 0.0005,
      "loss": 0.2685,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8008,
      "eval_loss": 0.7342987060546875,
      "eval_runtime": 5.831,
      "eval_samples_per_second": 643.115,
      "eval_steps_per_second": 10.118,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.3057519793510437,
      "learning_rate": 0.0005,
      "loss": 0.2335,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8088,
      "eval_loss": 0.6909195184707642,
      "eval_runtime": 5.8598,
      "eval_samples_per_second": 639.955,
      "eval_steps_per_second": 10.069,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.8569828867912292,
      "learning_rate": 0.0005,
      "loss": 0.2147,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8066666666666666,
      "eval_loss": 0.7109134197235107,
      "eval_runtime": 5.7967,
      "eval_samples_per_second": 646.916,
      "eval_steps_per_second": 10.178,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.2673887014389038,
      "learning_rate": 0.0005,
      "loss": 0.2073,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8208,
      "eval_loss": 0.6760216951370239,
      "eval_runtime": 5.4899,
      "eval_samples_per_second": 683.067,
      "eval_steps_per_second": 10.747,
      "step": 2664
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}