Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0757

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0757
File size: 4,051 Bytes 
b77e3fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9090666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0757/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": 3.564793109893799,
      "learning_rate": 6.733578363789503e-05,
      "loss": 1.5266,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7962666666666667,
      "eval_loss": 0.7499122023582458,
      "eval_runtime": 11.0778,
      "eval_samples_per_second": 338.516,
      "eval_steps_per_second": 5.326,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4348245859146118,
      "learning_rate": 5.974873734152915e-05,
      "loss": 0.4667,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8458666666666667,
      "eval_loss": 0.5281817317008972,
      "eval_runtime": 10.4234,
      "eval_samples_per_second": 359.767,
      "eval_steps_per_second": 5.66,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.1750085949897766,
      "learning_rate": 4.839392013277814e-05,
      "loss": 0.2708,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8736,
      "eval_loss": 0.4400763213634491,
      "eval_runtime": 10.5107,
      "eval_samples_per_second": 356.781,
      "eval_steps_per_second": 5.613,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 11.888204574584961,
      "learning_rate": 3.5e-05,
      "loss": 0.1451,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.4033103883266449,
      "eval_runtime": 11.4532,
      "eval_samples_per_second": 327.419,
      "eval_steps_per_second": 5.151,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.44929036498069763,
      "learning_rate": 2.1606079867221858e-05,
      "loss": 0.0775,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8925333333333333,
      "eval_loss": 0.3933429718017578,
      "eval_runtime": 10.5779,
      "eval_samples_per_second": 354.513,
      "eval_steps_per_second": 5.578,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.191110134124756,
      "learning_rate": 1.0251262658470837e-05,
      "loss": 0.0357,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9045333333333333,
      "eval_loss": 0.3680976331233978,
      "eval_runtime": 10.5058,
      "eval_samples_per_second": 356.946,
      "eval_steps_per_second": 5.616,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 2.6800339785621635e-06,
      "loss": 0.0171,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9066666666666666,
      "eval_loss": 0.36272868514060974,
      "eval_runtime": 10.4101,
      "eval_samples_per_second": 360.226,
      "eval_steps_per_second": 5.668,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.1457793414592743,
      "learning_rate": 2.4337126681706066e-11,
      "loss": 0.0119,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9090666666666667,
      "eval_loss": 0.360490620136261,
      "eval_runtime": 10.5876,
      "eval_samples_per_second": 354.188,
      "eval_steps_per_second": 5.573,
      "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
}