Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0807

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0807
File size: 3,647 Bytes 
0324569
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8965333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0807/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 2.886495269365963e-05,
      "loss": 2.3765,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7285333333333334,
      "eval_loss": 1.2078495025634766,
      "eval_runtime": 6.8724,
      "eval_samples_per_second": 545.661,
      "eval_steps_per_second": 8.585,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.084773540496826,
      "learning_rate": 2.5619102456015873e-05,
      "loss": 0.7742,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8528,
      "eval_loss": 0.5998566150665283,
      "eval_runtime": 6.8544,
      "eval_samples_per_second": 547.091,
      "eval_steps_per_second": 8.608,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.5322933197021484,
      "learning_rate": 2.0756590131847176e-05,
      "loss": 0.4076,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.4760688543319702,
      "eval_runtime": 6.8096,
      "eval_samples_per_second": 550.689,
      "eval_steps_per_second": 8.664,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4490888714790344,
      "learning_rate": 1.5017689143724237e-05,
      "loss": 0.2462,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8784,
      "eval_loss": 0.4315999150276184,
      "eval_runtime": 7.4355,
      "eval_samples_per_second": 504.335,
      "eval_steps_per_second": 7.935,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5767269730567932,
      "learning_rate": 9.276095143821772e-06,
      "loss": 0.149,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.396463543176651,
      "eval_runtime": 6.8124,
      "eval_samples_per_second": 550.463,
      "eval_steps_per_second": 8.661,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5114113092422485,
      "learning_rate": 4.4059137709457125e-06,
      "loss": 0.0955,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.383965402841568,
      "eval_runtime": 7.3639,
      "eval_samples_per_second": 509.242,
      "eval_steps_per_second": 8.012,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 3.5936036109924316,
      "learning_rate": 1.1485859908123557e-06,
      "loss": 0.0641,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8965333333333333,
      "eval_loss": 0.3721623122692108,
      "eval_runtime": 7.4145,
      "eval_samples_per_second": 505.764,
      "eval_steps_per_second": 7.957,
      "step": 2331
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}