Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0798

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0798
File size: 4,009 Bytes 
d69f86a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8864,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0798/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 9.700253128109275e-05,
      "loss": 1.7566,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.752,
      "eval_loss": 0.8661344647407532,
      "eval_runtime": 7.8904,
      "eval_samples_per_second": 475.259,
      "eval_steps_per_second": 7.477,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 8.836951787320407e-05,
      "loss": 0.5525,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8213333333333334,
      "eval_loss": 0.5656373500823975,
      "eval_runtime": 7.1742,
      "eval_samples_per_second": 522.709,
      "eval_steps_per_second": 8.224,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.24825040996074677,
      "learning_rate": 7.509072574151719e-05,
      "loss": 0.3131,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8416,
      "eval_loss": 0.5269912481307983,
      "eval_runtime": 6.6638,
      "eval_samples_per_second": 562.742,
      "eval_steps_per_second": 8.854,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0127614736557007,
      "learning_rate": 5.8785621785729404e-05,
      "loss": 0.177,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8602666666666666,
      "eval_loss": 0.47691816091537476,
      "eval_runtime": 6.8617,
      "eval_samples_per_second": 546.513,
      "eval_steps_per_second": 8.598,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 17.445119857788086,
      "learning_rate": 4.142084218061449e-05,
      "loss": 0.0898,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.864,
      "eval_loss": 0.4764133393764496,
      "eval_runtime": 6.7439,
      "eval_samples_per_second": 556.057,
      "eval_steps_per_second": 8.749,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.08413602411746979,
      "learning_rate": 2.5090835623402032e-05,
      "loss": 0.0397,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8698666666666667,
      "eval_loss": 0.499181866645813,
      "eval_runtime": 7.6192,
      "eval_samples_per_second": 492.176,
      "eval_steps_per_second": 7.744,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.09264644980430603,
      "learning_rate": 1.1765241910120828e-05,
      "loss": 0.0172,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8736,
      "eval_loss": 0.4576973021030426,
      "eval_runtime": 6.7176,
      "eval_samples_per_second": 558.238,
      "eval_steps_per_second": 8.783,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.04175420105457306,
      "learning_rate": 3.0513243074104303e-06,
      "loss": 0.0082,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.44842416048049927,
      "eval_runtime": 6.6694,
      "eval_samples_per_second": 562.269,
      "eval_steps_per_second": 8.846,
      "step": 2664
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}