Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0259

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0259
File size: 4,444 Bytes 
4345a42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.908,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0259/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": 4.850126564054637e-05,
      "loss": 1.7244,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8064,
      "eval_loss": 0.7374852299690247,
      "eval_runtime": 10.449,
      "eval_samples_per_second": 358.886,
      "eval_steps_per_second": 5.646,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 4.4184758936602036e-05,
      "loss": 0.4628,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.48197174072265625,
      "eval_runtime": 10.4744,
      "eval_samples_per_second": 358.014,
      "eval_steps_per_second": 5.633,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5006320476531982,
      "learning_rate": 3.7545362870758595e-05,
      "loss": 0.222,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.43050333857536316,
      "eval_runtime": 10.2607,
      "eval_samples_per_second": 365.472,
      "eval_steps_per_second": 5.75,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3336784243583679,
      "learning_rate": 2.9392810892864702e-05,
      "loss": 0.1122,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8794666666666666,
      "eval_loss": 0.4262898564338684,
      "eval_runtime": 11.2163,
      "eval_samples_per_second": 334.335,
      "eval_steps_per_second": 5.26,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6457473635673523,
      "learning_rate": 2.0710421090307246e-05,
      "loss": 0.0466,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.38214758038520813,
      "eval_runtime": 10.2602,
      "eval_samples_per_second": 365.491,
      "eval_steps_per_second": 5.75,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.11344309151172638,
      "learning_rate": 1.2545417811701016e-05,
      "loss": 0.0191,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8989333333333334,
      "eval_loss": 0.38332682847976685,
      "eval_runtime": 10.4831,
      "eval_samples_per_second": 357.717,
      "eval_steps_per_second": 5.628,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.09066104888916016,
      "learning_rate": 5.882620955060414e-06,
      "loss": 0.0069,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9077333333333333,
      "eval_loss": 0.3661186993122101,
      "eval_runtime": 10.4659,
      "eval_samples_per_second": 358.308,
      "eval_steps_per_second": 5.637,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.35036709904670715,
      "learning_rate": 1.5256621537052152e-06,
      "loss": 0.0049,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9077333333333333,
      "eval_loss": 0.37003546953201294,
      "eval_runtime": 10.2961,
      "eval_samples_per_second": 364.215,
      "eval_steps_per_second": 5.73,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.12748342752456665,
      "learning_rate": 5.494094242330938e-11,
      "loss": 0.0042,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.908,
      "eval_loss": 0.37110674381256104,
      "eval_runtime": 10.3334,
      "eval_samples_per_second": 362.899,
      "eval_steps_per_second": 5.71,
      "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
}