Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0575

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0575
File size: 2,823 Bytes 
45bbd49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8738666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0575/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "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": 2.401801801801802e-05,
      "loss": 2.3546,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7506666666666667,
      "eval_loss": 1.159598708152771,
      "eval_runtime": 11.0756,
      "eval_samples_per_second": 338.584,
      "eval_steps_per_second": 5.327,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 1.8036036036036037e-05,
      "loss": 0.8043,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8256,
      "eval_loss": 0.6599905490875244,
      "eval_runtime": 10.7922,
      "eval_samples_per_second": 347.472,
      "eval_steps_per_second": 5.467,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.244184494018555,
      "learning_rate": 1.2036036036036036e-05,
      "loss": 0.4314,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8488,
      "eval_loss": 0.535408616065979,
      "eval_runtime": 10.8109,
      "eval_samples_per_second": 346.872,
      "eval_steps_per_second": 5.457,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 6.054054054054054e-06,
      "loss": 0.2594,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8624,
      "eval_loss": 0.47241196036338806,
      "eval_runtime": 10.757,
      "eval_samples_per_second": 348.611,
      "eval_steps_per_second": 5.485,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.2987496852874756,
      "learning_rate": 5.4054054054054056e-08,
      "loss": 0.163,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8738666666666667,
      "eval_loss": 0.44395196437835693,
      "eval_runtime": 10.8619,
      "eval_samples_per_second": 345.243,
      "eval_steps_per_second": 5.432,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}