Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0050

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0050
File size: 3,906 Bytes 
3012542
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.7501333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0050/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": 0.0003,
      "loss": 2.7532,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5146666666666667,
      "eval_loss": 1.7020994424819946,
      "eval_runtime": 5.0752,
      "eval_samples_per_second": 738.894,
      "eval_steps_per_second": 11.625,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 1.2855,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6565333333333333,
      "eval_loss": 1.1303194761276245,
      "eval_runtime": 4.6942,
      "eval_samples_per_second": 798.855,
      "eval_steps_per_second": 12.569,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.303204536437988,
      "learning_rate": 0.0003,
      "loss": 0.7956,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7029333333333333,
      "eval_loss": 0.9787096381187439,
      "eval_runtime": 5.1611,
      "eval_samples_per_second": 726.589,
      "eval_steps_per_second": 11.432,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 24.53734588623047,
      "learning_rate": 0.0003,
      "loss": 0.5508,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7304,
      "eval_loss": 0.916275680065155,
      "eval_runtime": 4.7878,
      "eval_samples_per_second": 783.24,
      "eval_steps_per_second": 12.323,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.6000784635543823,
      "learning_rate": 0.0003,
      "loss": 0.3972,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7152,
      "eval_loss": 1.0097609758377075,
      "eval_runtime": 4.7563,
      "eval_samples_per_second": 788.42,
      "eval_steps_per_second": 12.404,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.850257158279419,
      "learning_rate": 0.0003,
      "loss": 0.3028,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.744,
      "eval_loss": 0.9507958292961121,
      "eval_runtime": 4.8957,
      "eval_samples_per_second": 765.978,
      "eval_steps_per_second": 12.051,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.4819643199443817,
      "learning_rate": 0.0003,
      "loss": 0.2249,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.748,
      "eval_loss": 0.9511612057685852,
      "eval_runtime": 4.6512,
      "eval_samples_per_second": 806.24,
      "eval_steps_per_second": 12.685,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.3459586501121521,
      "learning_rate": 0.0003,
      "loss": 0.1933,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7501333333333333,
      "eval_loss": 1.0137704610824585,
      "eval_runtime": 4.5391,
      "eval_samples_per_second": 826.163,
      "eval_steps_per_second": 12.998,
      "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
}