Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0849

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0849
File size: 3,643 Bytes 
dce81db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8941333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0849/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": 11.594162940979004,
      "learning_rate": 8.75e-05,
      "loss": 1.477,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7962666666666667,
      "eval_loss": 0.7082069516181946,
      "eval_runtime": 13.532,
      "eval_samples_per_second": 277.121,
      "eval_steps_per_second": 4.36,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.9049493074417114,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4959,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8362666666666667,
      "eval_loss": 0.5427099466323853,
      "eval_runtime": 15.4046,
      "eval_samples_per_second": 243.433,
      "eval_steps_per_second": 3.83,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 6.253753753753754e-05,
      "loss": 0.2816,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8698666666666667,
      "eval_loss": 0.4432482421398163,
      "eval_runtime": 12.3981,
      "eval_samples_per_second": 302.465,
      "eval_steps_per_second": 4.759,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.6436164379119873,
      "learning_rate": 5.0037537537537535e-05,
      "loss": 0.1578,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8632,
      "eval_loss": 0.47417324781417847,
      "eval_runtime": 10.8777,
      "eval_samples_per_second": 344.742,
      "eval_steps_per_second": 5.424,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 19.77275848388672,
      "learning_rate": 3.7537537537537536e-05,
      "loss": 0.0908,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8792,
      "eval_loss": 0.44444000720977783,
      "eval_runtime": 11.9063,
      "eval_samples_per_second": 314.96,
      "eval_steps_per_second": 4.955,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 2.5075075075075076e-05,
      "loss": 0.0492,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.4279140532016754,
      "eval_runtime": 10.8549,
      "eval_samples_per_second": 345.466,
      "eval_steps_per_second": 5.435,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0392611101269722,
      "learning_rate": 1.2575075075075077e-05,
      "loss": 0.0194,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8941333333333333,
      "eval_loss": 0.42607685923576355,
      "eval_runtime": 10.8537,
      "eval_samples_per_second": 345.503,
      "eval_steps_per_second": 5.436,
      "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
}