Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0730

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0730
File size: 3,613 Bytes 
81101ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9098666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0730/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": 8.559608050575152e-05,
      "loss": 1.7344,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7904,
      "eval_loss": 0.7971882820129395,
      "eval_runtime": 7.6128,
      "eval_samples_per_second": 492.592,
      "eval_steps_per_second": 7.75,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 7.319906209778102e-05,
      "loss": 0.5443,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8336,
      "eval_loss": 0.5727037787437439,
      "eval_runtime": 7.1078,
      "eval_samples_per_second": 527.591,
      "eval_steps_per_second": 8.301,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0642460584640503,
      "learning_rate": 5.5190743462682014e-05,
      "loss": 0.3188,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8656,
      "eval_loss": 0.46495911478996277,
      "eval_runtime": 7.1285,
      "eval_samples_per_second": 526.057,
      "eval_steps_per_second": 8.277,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2929232120513916,
      "learning_rate": 3.516402310353216e-05,
      "loss": 0.1773,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8850666666666667,
      "eval_loss": 0.40118488669395447,
      "eval_runtime": 8.487,
      "eval_samples_per_second": 441.852,
      "eval_steps_per_second": 6.952,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.7712008953094482,
      "learning_rate": 1.708543859906803e-05,
      "loss": 0.0887,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9064,
      "eval_loss": 0.35631829500198364,
      "eval_runtime": 7.544,
      "eval_samples_per_second": 497.085,
      "eval_steps_per_second": 7.821,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.08623501658439636,
      "learning_rate": 4.53567532968734e-06,
      "loss": 0.0417,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.908,
      "eval_loss": 0.35775285959243774,
      "eval_runtime": 7.517,
      "eval_samples_per_second": 498.869,
      "eval_steps_per_second": 7.849,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.1098228171467781,
      "learning_rate": 3.6782363693366185e-10,
      "loss": 0.0258,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.34874168038368225,
      "eval_runtime": 7.1744,
      "eval_samples_per_second": 522.694,
      "eval_steps_per_second": 8.224,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}