Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0453

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0453
File size: 4,398 Bytes
01b51c4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.572,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0453/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "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": 0.0004850126564054637,
      "loss": 3.0577,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2784,
      "eval_loss": 2.6409528255462646,
      "eval_runtime": 5.7193,
      "eval_samples_per_second": 655.673,
      "eval_steps_per_second": 10.316,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00044184758936602033,
      "loss": 2.3671,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3464,
      "eval_loss": 2.305210590362549,
      "eval_runtime": 5.8104,
      "eval_samples_per_second": 645.394,
      "eval_steps_per_second": 10.154,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.437796592712402,
      "learning_rate": 0.0003754536287075859,
      "loss": 1.9843,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.42933333333333334,
      "eval_loss": 2.0532450675964355,
      "eval_runtime": 5.707,
      "eval_samples_per_second": 657.093,
      "eval_steps_per_second": 10.338,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.542871475219727,
      "learning_rate": 0.000293928108928647,
      "loss": 1.6441,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.45653333333333335,
      "eval_loss": 1.8933825492858887,
      "eval_runtime": 5.7355,
      "eval_samples_per_second": 653.817,
      "eval_steps_per_second": 10.287,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002073624094068776,
      "loss": 1.2507,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5189333333333334,
      "eval_loss": 1.6793755292892456,
      "eval_runtime": 5.6487,
      "eval_samples_per_second": 663.864,
      "eval_steps_per_second": 10.445,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 13.598700523376465,
      "learning_rate": 0.00012568147258031897,
      "loss": 0.7904,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.544,
      "eval_loss": 1.6365734338760376,
      "eval_runtime": 5.6929,
      "eval_samples_per_second": 658.717,
      "eval_steps_per_second": 10.364,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.7131162881851196,
      "learning_rate": 5.899518490663266e-05,
      "loss": 0.3329,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5608,
      "eval_loss": 1.694993495941162,
      "eval_runtime": 6.8506,
      "eval_samples_per_second": 547.401,
      "eval_steps_per_second": 8.612,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.04395256191492081,
      "learning_rate": 1.534689686405272e-05,
      "loss": 0.0895,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5693333333333334,
      "eval_loss": 1.767600655555725,
      "eval_runtime": 6.8236,
      "eval_samples_per_second": 549.565,
      "eval_steps_per_second": 8.646,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.645505428314209,
      "learning_rate": 1.2361706385188854e-09,
      "loss": 0.0335,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.572,
      "eval_loss": 1.7850971221923828,
      "eval_runtime": 5.6766,
      "eval_samples_per_second": 660.603,
      "eval_steps_per_second": 10.393,
      "step": 2997
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}