Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0881

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0881
File size: 4,445 Bytes 
fa1bfd2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8968,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0881/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": 0.8090866208076477,
      "learning_rate": 8.892225558892226e-05,
      "loss": 1.8773,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7482666666666666,
      "eval_loss": 0.8664409518241882,
      "eval_runtime": 5.686,
      "eval_samples_per_second": 659.51,
      "eval_steps_per_second": 10.376,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.917519569396973,
      "learning_rate": 7.781114447781115e-05,
      "loss": 0.5343,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8512,
      "eval_loss": 0.5206353664398193,
      "eval_runtime": 6.4233,
      "eval_samples_per_second": 583.808,
      "eval_steps_per_second": 9.185,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 6.67334000667334e-05,
      "loss": 0.294,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8698666666666667,
      "eval_loss": 0.4400913417339325,
      "eval_runtime": 5.9315,
      "eval_samples_per_second": 632.219,
      "eval_steps_per_second": 9.947,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.342351198196411,
      "learning_rate": 5.562228895562229e-05,
      "loss": 0.1594,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8648,
      "eval_loss": 0.45906054973602295,
      "eval_runtime": 5.6562,
      "eval_samples_per_second": 662.99,
      "eval_steps_per_second": 10.431,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.4063358306884766,
      "learning_rate": 4.451117784451118e-05,
      "loss": 0.0863,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.43926483392715454,
      "eval_runtime": 6.0935,
      "eval_samples_per_second": 615.409,
      "eval_steps_per_second": 9.682,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.035604946315288544,
      "learning_rate": 3.340006673340007e-05,
      "loss": 0.0445,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8749333333333333,
      "eval_loss": 0.44652271270751953,
      "eval_runtime": 6.0706,
      "eval_samples_per_second": 617.735,
      "eval_steps_per_second": 9.719,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.35733702778816223,
      "learning_rate": 2.2288955622288957e-05,
      "loss": 0.019,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8877333333333334,
      "eval_loss": 0.44714048504829407,
      "eval_runtime": 6.346,
      "eval_samples_per_second": 590.919,
      "eval_steps_per_second": 9.297,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.11790935695171356,
      "learning_rate": 1.1177844511177845e-05,
      "loss": 0.0067,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8909333333333334,
      "eval_loss": 0.42244628071784973,
      "eval_runtime": 5.6951,
      "eval_samples_per_second": 658.459,
      "eval_steps_per_second": 10.36,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.04904548078775406,
      "learning_rate": 6.673340006673341e-08,
      "loss": 0.0037,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8968,
      "eval_loss": 0.41836419701576233,
      "eval_runtime": 5.9273,
      "eval_samples_per_second": 632.662,
      "eval_steps_per_second": 9.954,
      "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
}