Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0515

Safetensors
vit
Model card Files
xet
Community
Model-J__SupViT__model_idx_0515
File size: 4,071 Bytes 
be3578c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9509333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0515/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": 0.4156893789768219,
      "learning_rate": 6.788924172750679e-05,
      "loss": 0.742,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9370666666666667,
      "eval_loss": 0.23697683215141296,
      "eval_runtime": 11.2878,
      "eval_samples_per_second": 332.217,
      "eval_steps_per_second": 5.227,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.8358726501464844,
      "learning_rate": 6.181155550916422e-05,
      "loss": 0.1378,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9349333333333333,
      "eval_loss": 0.21477626264095306,
      "eval_runtime": 17.0118,
      "eval_samples_per_second": 220.435,
      "eval_steps_per_second": 3.468,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5570909380912781,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.0633,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.2101936787366867,
      "eval_runtime": 11.1164,
      "eval_samples_per_second": 337.338,
      "eval_steps_per_second": 5.307,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04866684600710869,
      "learning_rate": 4.1077686218342566e-05,
      "loss": 0.0329,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9413333333333334,
      "eval_loss": 0.21334095299243927,
      "eval_runtime": 11.1973,
      "eval_samples_per_second": 334.903,
      "eval_steps_per_second": 5.269,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.012089965865015984,
      "learning_rate": 2.8922313781657438e-05,
      "loss": 0.0146,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9498666666666666,
      "eval_loss": 0.2047930657863617,
      "eval_runtime": 10.8512,
      "eval_samples_per_second": 345.584,
      "eval_steps_per_second": 5.437,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0317557193338871,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0061,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9496,
      "eval_loss": 0.21047349274158478,
      "eval_runtime": 10.9358,
      "eval_samples_per_second": 342.911,
      "eval_steps_per_second": 5.395,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 8.212042196399656e-06,
      "loss": 0.0032,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9504,
      "eval_loss": 0.21123065054416656,
      "eval_runtime": 11.1596,
      "eval_samples_per_second": 336.035,
      "eval_steps_per_second": 5.287,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.02519037015736103,
      "learning_rate": 2.1233245810799825e-06,
      "loss": 0.0023,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9509333333333333,
      "eval_loss": 0.20995165407657623,
      "eval_runtime": 11.1695,
      "eval_samples_per_second": 335.735,
      "eval_steps_per_second": 5.282,
      "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
}