Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0667

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0667
File size: 3,257 Bytes 
f527b5a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8914666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0667/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "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": 4.1691691691691694e-05,
      "loss": 1.8473,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.784,
      "eval_loss": 0.8505350351333618,
      "eval_runtime": 10.4023,
      "eval_samples_per_second": 360.497,
      "eval_steps_per_second": 5.672,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1999403238296509,
      "learning_rate": 3.335835835835836e-05,
      "loss": 0.5686,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8504,
      "eval_loss": 0.5250648260116577,
      "eval_runtime": 10.6155,
      "eval_samples_per_second": 353.257,
      "eval_steps_per_second": 5.558,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6227526664733887,
      "learning_rate": 2.502502502502503e-05,
      "loss": 0.3144,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8741333333333333,
      "eval_loss": 0.4342179596424103,
      "eval_runtime": 10.4776,
      "eval_samples_per_second": 357.906,
      "eval_steps_per_second": 5.631,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.080256462097168,
      "learning_rate": 1.6691691691691692e-05,
      "loss": 0.1849,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8842666666666666,
      "eval_loss": 0.3961332142353058,
      "eval_runtime": 10.7658,
      "eval_samples_per_second": 348.324,
      "eval_steps_per_second": 5.48,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.506612539291382,
      "learning_rate": 8.358358358358359e-06,
      "loss": 0.1035,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8885333333333333,
      "eval_loss": 0.3798885941505432,
      "eval_runtime": 10.7954,
      "eval_samples_per_second": 347.369,
      "eval_steps_per_second": 5.465,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9671769738197327,
      "learning_rate": 2.5025025025025025e-08,
      "loss": 0.061,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.37949275970458984,
      "eval_runtime": 11.838,
      "eval_samples_per_second": 316.777,
      "eval_steps_per_second": 4.984,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}