Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0881

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0881
File size: 4,076 Bytes 
85adb60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9106666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0881/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": 0.4023517668247223,
      "learning_rate": 0.0004809698831278217,
      "loss": 0.8192,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8125333333333333,
      "eval_loss": 0.6456325650215149,
      "eval_runtime": 13.2378,
      "eval_samples_per_second": 283.281,
      "eval_steps_per_second": 4.457,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.150508880615234,
      "learning_rate": 0.00042677669529663686,
      "loss": 0.4672,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8349333333333333,
      "eval_loss": 0.5571300983428955,
      "eval_runtime": 12.7801,
      "eval_samples_per_second": 293.424,
      "eval_steps_per_second": 4.617,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3305826485157013,
      "learning_rate": 0.0003456708580912725,
      "loss": 0.301,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8450666666666666,
      "eval_loss": 0.5168059468269348,
      "eval_runtime": 13.9367,
      "eval_samples_per_second": 269.074,
      "eval_steps_per_second": 4.233,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.006045862101018429,
      "learning_rate": 0.00025,
      "loss": 0.1812,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8741333333333333,
      "eval_loss": 0.4527629613876343,
      "eval_runtime": 13.0178,
      "eval_samples_per_second": 288.068,
      "eval_steps_per_second": 4.532,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.016291137784719467,
      "learning_rate": 0.00015432914190872756,
      "loss": 0.083,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.45716914534568787,
      "eval_runtime": 13.0462,
      "eval_samples_per_second": 287.44,
      "eval_steps_per_second": 4.522,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.06959958374500275,
      "learning_rate": 7.322330470336314e-05,
      "loss": 0.0299,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8946666666666667,
      "eval_loss": 0.3934752643108368,
      "eval_runtime": 12.9329,
      "eval_samples_per_second": 289.958,
      "eval_steps_per_second": 4.562,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.9143099846872597e-05,
      "loss": 0.0067,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.35998353362083435,
      "eval_runtime": 12.9435,
      "eval_samples_per_second": 289.721,
      "eval_steps_per_second": 4.558,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.03109845332801342,
      "learning_rate": 1.7383661915504333e-10,
      "loss": 0.0033,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9106666666666666,
      "eval_loss": 0.34563711285591125,
      "eval_runtime": 13.1045,
      "eval_samples_per_second": 286.161,
      "eval_steps_per_second": 4.502,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}