Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0666

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0666
File size: 4,501 Bytes 
b39a608
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9069333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0666/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": 8.892225558892226e-05,
      "loss": 1.7112,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8234666666666667,
      "eval_loss": 0.6732024550437927,
      "eval_runtime": 11.0247,
      "eval_samples_per_second": 340.145,
      "eval_steps_per_second": 5.352,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1526763439178467,
      "learning_rate": 7.781114447781115e-05,
      "loss": 0.4686,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8378666666666666,
      "eval_loss": 0.5576264262199402,
      "eval_runtime": 11.922,
      "eval_samples_per_second": 314.545,
      "eval_steps_per_second": 4.949,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9550458192825317,
      "learning_rate": 6.670003336670004e-05,
      "loss": 0.2598,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8658666666666667,
      "eval_loss": 0.4691441059112549,
      "eval_runtime": 11.5018,
      "eval_samples_per_second": 326.036,
      "eval_steps_per_second": 5.13,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.13398264348506927,
      "learning_rate": 5.5588922255588925e-05,
      "loss": 0.1457,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.44271087646484375,
      "eval_runtime": 10.8946,
      "eval_samples_per_second": 344.207,
      "eval_steps_per_second": 5.416,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2806968688964844,
      "learning_rate": 4.447781114447781e-05,
      "loss": 0.0866,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.40574851632118225,
      "eval_runtime": 11.1098,
      "eval_samples_per_second": 337.54,
      "eval_steps_per_second": 5.311,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.08600737899541855,
      "learning_rate": 3.33667000333667e-05,
      "loss": 0.0423,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.43153759837150574,
      "eval_runtime": 10.9834,
      "eval_samples_per_second": 341.423,
      "eval_steps_per_second": 5.372,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.08914632350206375,
      "learning_rate": 2.225558892225559e-05,
      "loss": 0.0206,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9002666666666667,
      "eval_loss": 0.4012303352355957,
      "eval_runtime": 11.2923,
      "eval_samples_per_second": 332.086,
      "eval_steps_per_second": 5.225,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.08721788972616196,
      "learning_rate": 1.1144477811144478e-05,
      "loss": 0.0095,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9042666666666667,
      "eval_loss": 0.3703761696815491,
      "eval_runtime": 11.0291,
      "eval_samples_per_second": 340.01,
      "eval_steps_per_second": 5.349,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.6477776765823364,
      "learning_rate": 3.3366700033366706e-08,
      "loss": 0.0035,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9069333333333334,
      "eval_loss": 0.3776162564754486,
      "eval_runtime": 10.9809,
      "eval_samples_per_second": 341.501,
      "eval_steps_per_second": 5.373,
      "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
}