Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0336

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0336
File size: 4,417 Bytes 
3d62902
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.5528,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0336/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": 0.00026676676676676677,
      "loss": 3.3386,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.20106666666666667,
      "eval_loss": 3.0462286472320557,
      "eval_runtime": 7.042,
      "eval_samples_per_second": 532.52,
      "eval_steps_per_second": 8.378,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002335335335335335,
      "loss": 2.7751,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.31146666666666667,
      "eval_loss": 2.5595245361328125,
      "eval_runtime": 6.3008,
      "eval_samples_per_second": 595.167,
      "eval_steps_per_second": 9.364,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002003003003003003,
      "loss": 2.3743,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.38826666666666665,
      "eval_loss": 2.234722375869751,
      "eval_runtime": 6.2409,
      "eval_samples_per_second": 600.871,
      "eval_steps_per_second": 9.454,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.473464012145996,
      "learning_rate": 0.00016696696696696695,
      "loss": 1.9943,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4248,
      "eval_loss": 2.0700955390930176,
      "eval_runtime": 6.3837,
      "eval_samples_per_second": 587.435,
      "eval_steps_per_second": 9.242,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 23.166091918945312,
      "learning_rate": 0.00013363363363363363,
      "loss": 1.632,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.47253333333333336,
      "eval_loss": 1.9276131391525269,
      "eval_runtime": 6.1791,
      "eval_samples_per_second": 606.883,
      "eval_steps_per_second": 9.548,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 26.6307373046875,
      "learning_rate": 0.00010030030030030029,
      "loss": 1.2266,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5130666666666667,
      "eval_loss": 1.7711154222488403,
      "eval_runtime": 6.5931,
      "eval_samples_per_second": 568.778,
      "eval_steps_per_second": 8.949,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 11.78028678894043,
      "learning_rate": 6.696696696696696e-05,
      "loss": 0.8158,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5312,
      "eval_loss": 1.7533860206604004,
      "eval_runtime": 6.6087,
      "eval_samples_per_second": 567.43,
      "eval_steps_per_second": 8.928,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 38.4607048034668,
      "learning_rate": 3.363363363363363e-05,
      "loss": 0.4649,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5485333333333333,
      "eval_loss": 1.7749868631362915,
      "eval_runtime": 6.7645,
      "eval_samples_per_second": 554.363,
      "eval_steps_per_second": 8.722,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 1.131514549255371,
      "learning_rate": 3.0030030030030027e-07,
      "loss": 0.2214,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.5528,
      "eval_loss": 1.7786575555801392,
      "eval_runtime": 8.5802,
      "eval_samples_per_second": 437.054,
      "eval_steps_per_second": 6.876,
      "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
}