Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0851

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0851
File size: 4,280 Bytes 
bc90fa8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8632,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0851/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": 3e-05,
      "loss": 2.5209,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6933333333333334,
      "eval_loss": 1.3240679502487183,
      "eval_runtime": 5.7015,
      "eval_samples_per_second": 657.726,
      "eval_steps_per_second": 10.348,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.8933,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8002666666666667,
      "eval_loss": 0.733151912689209,
      "eval_runtime": 5.6329,
      "eval_samples_per_second": 665.726,
      "eval_steps_per_second": 10.474,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 21.797103881835938,
      "learning_rate": 3e-05,
      "loss": 0.5113,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8317333333333333,
      "eval_loss": 0.5647375583648682,
      "eval_runtime": 5.7914,
      "eval_samples_per_second": 647.514,
      "eval_steps_per_second": 10.188,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5299538373947144,
      "learning_rate": 3e-05,
      "loss": 0.3378,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8546666666666667,
      "eval_loss": 0.48622825741767883,
      "eval_runtime": 5.5635,
      "eval_samples_per_second": 674.033,
      "eval_steps_per_second": 10.605,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.511444568634033,
      "learning_rate": 3e-05,
      "loss": 0.2386,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8557333333333333,
      "eval_loss": 0.5034014582633972,
      "eval_runtime": 5.7383,
      "eval_samples_per_second": 653.507,
      "eval_steps_per_second": 10.282,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 25.44463539123535,
      "learning_rate": 3e-05,
      "loss": 0.1715,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8592,
      "eval_loss": 0.4946524202823639,
      "eval_runtime": 5.7903,
      "eval_samples_per_second": 647.64,
      "eval_steps_per_second": 10.19,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.1338,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.5048001408576965,
      "eval_runtime": 5.6496,
      "eval_samples_per_second": 663.762,
      "eval_steps_per_second": 10.443,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.10319014638662338,
      "learning_rate": 3e-05,
      "loss": 0.0959,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8525333333333334,
      "eval_loss": 0.5353767275810242,
      "eval_runtime": 5.7134,
      "eval_samples_per_second": 656.357,
      "eval_steps_per_second": 10.327,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 38.323238372802734,
      "learning_rate": 3e-05,
      "loss": 0.0721,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8632,
      "eval_loss": 0.5037660002708435,
      "eval_runtime": 6.0781,
      "eval_samples_per_second": 616.968,
      "eval_steps_per_second": 9.707,
      "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
}