Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0530

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0530
File size: 4,351 Bytes 
1ddd45d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9152,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0530/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": 3.4219272136688232,
      "learning_rate": 8e-05,
      "loss": 1.5561,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8218666666666666,
      "eval_loss": 0.6303232908248901,
      "eval_runtime": 5.881,
      "eval_samples_per_second": 637.644,
      "eval_steps_per_second": 10.032,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.2703933715820312,
      "learning_rate": 7.000000000000001e-05,
      "loss": 0.4421,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8749333333333333,
      "eval_loss": 0.4547632038593292,
      "eval_runtime": 5.8394,
      "eval_samples_per_second": 642.192,
      "eval_steps_per_second": 10.104,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.8319900035858154,
      "learning_rate": 6e-05,
      "loss": 0.2513,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.884,
      "eval_loss": 0.40294113755226135,
      "eval_runtime": 5.8796,
      "eval_samples_per_second": 637.8,
      "eval_steps_per_second": 10.035,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.6404378414154053,
      "learning_rate": 5e-05,
      "loss": 0.1444,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.38875529170036316,
      "eval_runtime": 5.9224,
      "eval_samples_per_second": 633.193,
      "eval_steps_per_second": 9.962,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.29155468940734863,
      "learning_rate": 4e-05,
      "loss": 0.085,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8997333333333334,
      "eval_loss": 0.3648848235607147,
      "eval_runtime": 5.9435,
      "eval_samples_per_second": 630.939,
      "eval_steps_per_second": 9.927,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.0344908237457275,
      "learning_rate": 3e-05,
      "loss": 0.0512,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9064,
      "eval_loss": 0.3638738989830017,
      "eval_runtime": 6.2091,
      "eval_samples_per_second": 603.953,
      "eval_steps_per_second": 9.502,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.04689761623740196,
      "learning_rate": 2.0030030030030034e-05,
      "loss": 0.0222,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.35528990626335144,
      "eval_runtime": 6.6158,
      "eval_samples_per_second": 566.827,
      "eval_steps_per_second": 8.918,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.07108143717050552,
      "learning_rate": 1.0030030030030031e-05,
      "loss": 0.0098,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9136,
      "eval_loss": 0.3625781834125519,
      "eval_runtime": 6.0605,
      "eval_samples_per_second": 618.758,
      "eval_steps_per_second": 9.735,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.020532216876745224,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.006,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9152,
      "eval_loss": 0.3386712372303009,
      "eval_runtime": 5.925,
      "eval_samples_per_second": 632.915,
      "eval_steps_per_second": 9.958,
      "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
}