Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0560

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0560
File size: 4,031 Bytes 
b5d77b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8973333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0560/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": 0.9565123319625854,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.4859,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8034666666666667,
      "eval_loss": 0.7110143303871155,
      "eval_runtime": 6.5424,
      "eval_samples_per_second": 573.182,
      "eval_steps_per_second": 9.018,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2026400566101074,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.4936,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8248,
      "eval_loss": 0.5687808394432068,
      "eval_runtime": 6.1146,
      "eval_samples_per_second": 613.283,
      "eval_steps_per_second": 9.649,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5551466941833496,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2811,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8605333333333334,
      "eval_loss": 0.4751076400279999,
      "eval_runtime": 6.791,
      "eval_samples_per_second": 552.198,
      "eval_steps_per_second": 8.688,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.6103554964065552,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.1627,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8592,
      "eval_loss": 0.5034127831459045,
      "eval_runtime": 6.233,
      "eval_samples_per_second": 601.634,
      "eval_steps_per_second": 9.466,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2995215952396393,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0909,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8757333333333334,
      "eval_loss": 0.4644870162010193,
      "eval_runtime": 5.914,
      "eval_samples_per_second": 634.085,
      "eval_steps_per_second": 9.976,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.90688157081604,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0484,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.42639780044555664,
      "eval_runtime": 7.0953,
      "eval_samples_per_second": 528.519,
      "eval_steps_per_second": 8.315,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.1731488851999511e-05,
      "loss": 0.0207,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.4405064582824707,
      "eval_runtime": 5.8946,
      "eval_samples_per_second": 636.178,
      "eval_steps_per_second": 10.009,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.06894773244857788,
      "learning_rate": 3.033320830114261e-06,
      "loss": 0.0084,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8973333333333333,
      "eval_loss": 0.41643521189689636,
      "eval_runtime": 5.8573,
      "eval_samples_per_second": 640.228,
      "eval_steps_per_second": 10.073,
      "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
}