Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0838

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0838
File size: 4,036 Bytes 
f762c2b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8896,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0838/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": 5.151315212249756,
      "learning_rate": 6.733578363789503e-05,
      "loss": 1.7052,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7805333333333333,
      "eval_loss": 0.7968711853027344,
      "eval_runtime": 7.5364,
      "eval_samples_per_second": 497.584,
      "eval_steps_per_second": 7.829,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 26.351585388183594,
      "learning_rate": 5.974873734152915e-05,
      "loss": 0.5582,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8170666666666667,
      "eval_loss": 0.5940748453140259,
      "eval_runtime": 7.4606,
      "eval_samples_per_second": 502.638,
      "eval_steps_per_second": 7.908,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 4.8470148469326895e-05,
      "loss": 0.3153,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8573333333333333,
      "eval_loss": 0.4855136573314667,
      "eval_runtime": 8.0498,
      "eval_samples_per_second": 465.851,
      "eval_steps_per_second": 7.329,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.43171101808547974,
      "learning_rate": 3.508254927997938e-05,
      "loss": 0.1815,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8629333333333333,
      "eval_loss": 0.47651907801628113,
      "eval_runtime": 7.2841,
      "eval_samples_per_second": 514.817,
      "eval_steps_per_second": 8.1,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.694359540939331,
      "learning_rate": 2.1682382711066092e-05,
      "loss": 0.0974,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.4322602152824402,
      "eval_runtime": 7.6153,
      "eval_samples_per_second": 492.428,
      "eval_steps_per_second": 7.748,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.11638703942298889,
      "learning_rate": 1.0309702649891636e-05,
      "loss": 0.045,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8805333333333333,
      "eval_loss": 0.42429375648498535,
      "eval_runtime": 7.2227,
      "eval_samples_per_second": 519.196,
      "eval_steps_per_second": 8.169,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.178540587425232,
      "learning_rate": 2.6958965421683553e-06,
      "loss": 0.0222,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.4039247930049896,
      "eval_runtime": 7.1721,
      "eval_samples_per_second": 522.86,
      "eval_steps_per_second": 8.226,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.1790260523557663,
      "learning_rate": 9.734847288167535e-11,
      "loss": 0.0141,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8896,
      "eval_loss": 0.4033202826976776,
      "eval_runtime": 7.2357,
      "eval_samples_per_second": 518.265,
      "eval_steps_per_second": 8.154,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}